2x1000x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1000x13x13x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 32, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 4, 1, 1, 1>+1
2x1000x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1000x13x13x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1008x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1008x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x1008x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x1024x112x112x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:23
2x1024x13x13x1x1x1x1x2048x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x1024x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1024x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x1024x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1024x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1024x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x14x14x1x1x1x1x2048x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1024x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1024x14x14x1x1x1x1x2048x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x1024x14x14x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1024x14x14x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x1024x14x14x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x2048x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16
2x1024x14x14x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1024x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x14x14x1x1x1x1x256x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x1024x14x14x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1024x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1024x14x14x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x14x14x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x14x14x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x14x14x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x14x14x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x14x14x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x14x14x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x14x14x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 32, 32, 32, Default, 8, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5
2x1024x14x14x1x3x3x1x1024x128x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 64, 64, Default, 8, 8, 2>+1
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5
2x1024x14x14x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 32, 32, 32, Default, 8, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1>+1
2x1024x14x14x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 64, 32, 64, Default, 8, 8, 8>+1
2x1024x14x14x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 32, 32, Default, 16, 16, 4, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x14x14x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2
2x1024x14x14x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, Default, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x1024x14x14x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 16, 16, 4, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x1024x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x15x15x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33
2x1024x15x15x1x1x1x1x2048x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x15x15x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x15x15x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x15x15x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x15x15x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1024x15x15x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x15x15x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x15x15x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:22
2x1024x15x15x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x15x15x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x15x15x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x1024x15x15x1x3x3x1x1024x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x15x15x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x15x15x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3
2x1024x15x15x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3
2x1024x15x15x1x3x3x1x1024x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x1024x15x15x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x1024x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1024x17x17x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1024x17x17x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x17x17x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1024x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1024x17x17x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x17x17x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x17x17x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x17x17x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x17x17x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x17x17x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x17x17x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1024x17x17x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x17x17x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1024x17x17x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x17x17x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x1x1x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x1x1x1x1x1x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x1x1x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x1x1x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:29
2x1024x256x256x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1024x28x28x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x1024x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1024x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x1024x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x28x28x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x28x28x1x3x3x1x1024x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5
2x1024x28x28x1x3x3x1x1024x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x1024x28x28x1x3x3x1x1024x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:5
2x1024x42x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x1024x44x60x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x1024x44x84x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x1024x48x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x1024x48x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x4x4x1x1x1x1x2048x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x1024x50x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x1024x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x1024x56x56x1x1x1x1x512x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:32
2x1024x58x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33
2x1024x60x50x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33
2x1024x62x40x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32
2x1024x64x128x1x1x1x1x19x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x64x64x1x1x1x1x2048x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x64x64x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1024x64x64x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x64x64x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x64x64x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1024x64x64x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x64x64x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x64x64x1x1x1x1x512x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1024x64x64x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x68x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x1024x68x50x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x1024x69x47x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x1024x72x50x1x1x1x1x2048x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x1024x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x1024x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1024x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1024x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1024x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1024x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1024x7x7x1x1x1x1x2048x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1024x7x7x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x1024x7x7x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 128, 64, Default, 8, 8, 8>+1
2x1024x7x7x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x1024x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1024x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1024x7x7x1x1x1x1x464x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1024x7x7x1x3x3x1x1024x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x7x7x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x7x7x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:3
2x1024x7x7x1x3x3x1x1024x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 64, 8, 8, Default, 16, 16, 4, 1, 8, 4, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x7x7x1x3x3x1x1024x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x7x7x1x3x3x1x1024x6x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x1024x7x7x1x3x3x1x1024x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x84x42x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x1024x84x48x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:28
2x1024x8x8x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:30
2x1024x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x1024x8x8x1x1x1x1x2048x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1024x8x8x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1024x8x8x1x3x3x1x1024x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:2
2x1024x8x8x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x8x8x1x3x3x1x1024x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:8
2x1024x8x8x1x3x3x1x1024x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x1024x8x8x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x1024x8x8x1x3x3x1x1024x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x1024x9x9x1x3x3x1x1024x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x104x256x256x1x1x1x1x208x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1056x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x1056x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1056x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1056x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1056x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1056x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x1056x256x256x1x1x1x1x176x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:30
2x1056x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1056x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1056x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:5
2x1056x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1056x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1056x7x7x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x1056x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1056x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1056x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1056x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1056x7x7x1x1x1x1x352x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1056x7x7x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1088x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1088x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1088x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1088x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1088x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1088x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1104x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1104x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1104x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x1104x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1104x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1104x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1104x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1120x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1120x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1120x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:5
2x1120x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1120x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1120x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1120x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x112x128x128x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x112x14x14x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x112x14x14x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x112x14x14x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x112x1x1x1x1x1x1x2688x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:31
2x112x1x1x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x112x1x1x1x1x1x1x448x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 32, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 4, 1, 1, 1>+1
2x112x1x1x1x1x1x1x896x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x112x64x128x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1152x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1152x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1152x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1152x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1152x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1152x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1152x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1152x64x64x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 8, 16, 16, 4, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x1152x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1152x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1152x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1152x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1152x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38
2x1152x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1152x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Filter1x1Stride1Pad0, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1152x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1152x7x7x1x5x5x1x1152x64x2x2x0x1x1x0x1x1x0x0x1152xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x116x14x14x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x116x14x14x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x116x14x14x1x3x3x1x116x1024x1x1x0x1x1x0x1x1x0x0x116xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3
2x116x14x14x1x3x3x1x116x64x1x1x0x2x2x0x1x1x0x0x116xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x116x28x28x1x1x1x1x116x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x116x28x28x1x1x1x1x116x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x116x28x28x1x1x1x1x116x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x116x28x28x1x1x1x1x116x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x116x28x28x1x1x1x1x116x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x116x28x28x1x1x1x1x116x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x116x28x28x1x5x1x1x116x4x2x0x0x1x1x0x1x1x0x0x116xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1184x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1184x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1184x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1184x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1184x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1184x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1200x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1200x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1200x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1200x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1200x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1200x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1200x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x120x128x128x1x5x5x1x120x4x2x2x0x1x1x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x120x13x13x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x120x14x14x1x1x1x1x60x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, OddC, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x120x14x14x1x3x3x1x120x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x120x14x14x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x120x14x14x1x3x3x1x120x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x120x14x14x1x3x3x1x120x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x120x14x14x1x3x3x1x120x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x120x14x14x1x3x3x1x120x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x120x14x14x1x3x3x1x120x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x120x7x7x1x1x1x1x480x1024x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10
2x120x7x7x1x1x1x1x480x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18
2x120x7x7x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9
2x120x7x7x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20
2x120x7x7x1x1x1x1x480x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10
2x120x7x7x1x1x1x1x480x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:8
2x120x7x7x1x3x3x1x120x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:10
2x120x7x7x1x3x3x1x120x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 64, 8, 8, Default, 16, 16, 4, 1, 8, 4, 1, 1>+1
2x120x7x7x1x3x3x1x120x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x120x8x8x1x3x3x1x120x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x1216x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1216x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1216x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1216x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1216x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1216x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1248x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1248x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1248x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1248x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1248x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1248x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1248x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1248x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1248x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1248x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1248x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1248x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1248x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1248x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1280x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1280x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1280x14x14x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x14x14x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1280x14x14x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1280x14x14x1x1x1x1x640x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x16x16x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1280x16x16x1x3x3x1x1280x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, OddC, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x1280x1x3000x1x1x3x1x1280x1x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1280x28x28x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x28x28x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1280x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1280x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1280x64x64x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1280x64x64x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Default, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1280x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 64, OddC, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1280x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1280x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1280x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x1280x8x8x1x1x1x1x1280x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1280x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1280x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1280x8x8x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1280x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1280x8x8x1x1x1x1x320x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1280x8x8x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x1280x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1280x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1280x8x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1280x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1280x8x8x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1280x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1280x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1280x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1280x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1280x8x8x1x1x1x1x448x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1280x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:33
2x1280x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x100x164x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x128x100x80x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x128x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x1024x1024x1x3x3x1x3x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x105x105x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x105x105x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x105x105x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x128x108x96x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x128x10x10x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x112x112x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x128x128x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x128x128x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x128x128x1x1x1x1x512x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x128x128x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x128x128x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x128x128x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x128x128x1x3x3x1x128x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x128x256x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x148x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x14x14x1x1x1x1x1056x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x14x14x1x1x1x1x1312x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:18
2x128x14x14x1x1x1x1x1312x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1376x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8
2x128x14x14x1x1x1x1x1408x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x1408x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1504x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x128x14x14x1x1x1x1x1504x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x128x14x14x1x1x1x1x1632x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x1664x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x128x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:9
2x128x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x128x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x288x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x14x14x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x14x14x1x1x1x1x352x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x128x14x14x1x1x1x1x352x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x14x14x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x14x14x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 32, 32, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x128x14x14x1x1x1x1x416x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x14x14x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x14x14x1x1x1x1x544x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x128x14x14x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x128x14x14x1x1x1x1x544x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x14x14x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x128x14x14x1x1x1x1x608x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x14x14x1x1x1x1x624x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:40
2x128x14x14x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x14x14x1x1x1x1x640x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x14x14x1x1x1x1x672x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x14x14x1x1x1x1x672x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x128x14x14x1x1x1x1x672x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x128x14x14x1x1x1x1x672x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x704x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x704x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x736x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x736x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x128x14x14x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x14x14x1x1x1x1x768x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x14x14x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 128, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x128x14x14x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x14x14x1x1x1x1x800x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x14x14x1x1x1x1x832x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x128x14x14x1x1x1x1x832x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x128x14x14x1x1x1x1x832x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x832x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x14x14x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x128x14x14x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20
2x128x14x14x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x928x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x928x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x960x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x128x14x14x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x1x1x1x992x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x1x1x1x992x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x128x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x128x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x128x14x14x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x14x14x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x128x14x14x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x152x84x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x128x160x88x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x128x168x84x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x128x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:36
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x128x17x17x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x17x17x1x1x1x1x768x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x17x17x1x1x7x1x128x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x17x17x1x1x7x1x128x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x128x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x128x17x17x1x7x1x1x128x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x17x17x1x7x1x1x128x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x128x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x128x17x17x1x7x1x1x192x4x3x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x1x1x1x1x1x1x64x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x1x3000x1x1x3x1x1280x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x20x30x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:16
2x128x27x27x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x27x27x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x27x27x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x27x27x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x27x27x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x128x27x27x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x128x27x27x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x128x27x27x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x27x27x1x3x3x1x160x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x27x27x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x27x27x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x27x27x1x3x3x1x32x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x128x27x27x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x28x28x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 64, 64, 32, Filter1x1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x128x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x128x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x128x28x28x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x1x1x1x224x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x28x28x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x256x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 128, 64, Default, 8, 8, 8>+1
2x128x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x28x28x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x28x28x1x1x1x1x288x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x288x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x28x28x1x1x1x1x352x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:17
2x128x28x28x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x416x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:34
2x128x28x28x1x1x1x1x416x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x28x28x1x1x1x1x416x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 128, 64, Filter1x1Stride1Pad0, 8, 8, 4>+1
2x128x28x28x1x1x1x1x480x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x1x1x1x480x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x28x28x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x28x28x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:21
2x128x28x28x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, OddC, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x128x28x28x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x28x28x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x28x28x1x1x1x1x56x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 4, 4, 4, 1, 1, 1>
2x128x28x28x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x28x28x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x28x28x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x28x28x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x28x28x1x3x3x1x128x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x28x28x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x28x28x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x28x28x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x128x28x28x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x128x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x28x28x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x128x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x128x28x28x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 32, 32, 64, Default, 8, 8, 8>+1
2x128x28x28x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x28x28x1x3x3x1x96x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:14
2x128x28x28x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:12
2x128x28x28x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x128xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x128x29x29x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x29x29x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x29x29x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x128x29x29x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x29x29x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x29x29x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x30x30x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x128x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x38x38x1x3x3x1x128x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x38x38x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x38x38x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x38x38x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x39x39x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x128x3x3x1x3x3x1x256x120x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x128x3x3x1x3x3x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, OddC, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x128x3x3x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x400x608x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x128x40x175x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x128x40x175x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x40x175x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x128x40x175x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x40x175x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x40x175x1x5x5x1x256x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x40x175x1x5x5x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x40x175x1x5x5x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x40x175x1x5x5x1x256x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x40x175x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x41x177x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x128x52x52x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x128x54x54x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x128x54x54x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x54x54x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x128x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<64, 32, 32, 64, Default, 8, 16, 16, 1, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x128x54x54x1x1x1x1x16x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x54x54x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x54x54x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x54x54x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x128x54x54x1x1x1x1x32x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x54x54x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x54x54x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x54x54x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x54x54x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x54x54x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x55x55x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x55x55x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x55x55x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x128x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x56x56x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x56x56x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24
2x128x56x56x1x1x1x1x224x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x128x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x56x56x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x56x56x1x1x1x1x256x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x56x56x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, OddC, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x56x56x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x56x56x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x128x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x128x56x56x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x128x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x128x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x56x56x1x3x3x1x128x48x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:5
2x128x56x56x1x3x3x1x128x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3
2x128x56x56x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x56x56x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x56x56x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x128x56x56x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x128x56x56x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4
2x128x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x57x57x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x57x57x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x57x57x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x57x57x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x128x57x57x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x128x57x57x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x57x57x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x128x57x57x1x3x3x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x58x58x1x3x3x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x128x58x58x1x3x3x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x5x5x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x128x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Default, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x5x5x1x3x3x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x64x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x128x7x7x1x1x1x1x1056x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 32, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 4, 1, 1, 1>+1
2x128x7x7x1x1x1x1x1184x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x1216x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:24
2x128x7x7x1x1x1x1x1248x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x7x7x1x1x1x1x1376x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x7x7x1x1x1x1x1376x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:29
2x128x7x7x1x1x1x1x1440x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x7x7x1x1x1x1x1632x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x128x7x7x1x1x1x1x1632x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
2x128x7x7x1x1x1x1x1664x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x128x7x7x1x1x1x1x1760x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:28
2x128x7x7x1x1x1x1x1760x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x7x7x1x1x1x1x1824x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38
2x128x7x7x1x1x1x1x1888x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x128x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 64, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x128x7x7x1x1x1x1x544x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x7x7x1x1x1x1x544x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x576x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x7x7x1x1x1x1x608x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x128x7x7x1x1x1x1x640x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x640x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x128x7x7x1x1x1x1x640x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x672x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x672x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x704x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x7x7x1x1x1x1x704x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x736x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x736x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x128x7x7x1x1x1x1x800x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x7x7x1x1x1x1x800x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x7x7x1x1x1x1x800x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x7x7x1x1x1x1x800x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x800x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x128x7x7x1x1x1x1x864x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x7x7x1x1x1x1x864x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x7x7x1x1x1x1x864x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x128x7x7x1x1x1x1x896x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x128x7x7x1x1x1x1x928x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x128x7x7x1x1x1x1x928x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x128x7x7x1x1x1x1x960x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:40
2x128x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x7x7x1x1x1x1x960x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x128x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x128x7x7x1x1x1x1x992x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x128x7x7x1x1x1x1x992x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x128x7x7x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x7x7x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x128x7x7x1x3x3x1x32x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x128x7x7x1x3x3x1x32x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x128x7x7x1x3x3x1x32x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:26
2x128x7x7x1x3x3x1x32x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x128x7x7x1x3x3x1x32x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x128x80x168x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x92x156x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x128x92x88x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x128x96x136x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x128x96x144x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x128x96x152x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x128x96x160x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20
2x128x96x96x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x1296x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1296x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1296x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x1296x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1296x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1296x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1296x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:34;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 96, 32, Default, 16, 16, 4, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x12x10x16x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8
2x12x113x113x1x2x2x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 64, 16, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x12x16x10x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8
2x12x176x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:16
2x12x21x41x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:28
2x12x320x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:20
2x12x44x60x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:9
2x12x48x84x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x12x74x44x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:11
2x12x84x112x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x1312x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1312x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1312x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1312x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1312x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1312x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1336x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1336x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Filter1x1Stride1Pad0, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1344x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1344x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1344x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1344x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1344x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1344x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1344x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1344x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1344x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1344x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x1344x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1344x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1344x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1344x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x1344x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1344x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1344x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1344x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1376x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1376x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1376x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1376x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1376x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x1376x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x1392x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1392x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1392x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1392x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1392x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1392x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1392x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1408x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1408x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1408x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1408x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1408x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1408x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1408x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1440x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1440x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1440x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1440x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1440x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x1440x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1440x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1440x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1440x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1440x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1440x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x1440x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x144x14x14x1x3x3x1x288x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x144x14x14x1x3x3x1x288x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x144x14x14x1x3x3x1x288x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x144x14x14x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x144x14x14x1x3x3x1x288x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x144x24x16x1x1x1x1x288x14x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x144x24x16x1x3x3x1x144x34x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, OddC, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x144x24x16x1x3x3x1x144x8x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, OddC, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x144x258x258x1x3x3x1x144x4x0x0x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x144x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x144x28x28x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x144x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, OddC, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x144x512x512x1x3x3x1x144x1x1x1x0x1x1x0x1x1x0x0x144xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x144x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x144x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x144x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x144x56x56x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x144x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x144x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x144x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x144x56x56x1x3x3x1x144x1x1x1x0x2x2x0x1x1x0x0x9xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x144x64x128x1x3x3x1x288x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x144x7x7x1x1x1x1x432x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x1472x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1472x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1472x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1472x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1472x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1472x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1488x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1488x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x1488x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1488x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1488x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1488x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1488x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1488x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1488x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1504x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1504x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1504x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1504x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1504x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1536x147x147x1x1x1x1x1536x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1536x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1536x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1536x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1536x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1536x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x1536x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1536x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1536x1x1271x1x1x1x1x768x19x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x141x1x1x1x1x768x177x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x196x1x1x1x1x768x127x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x219x1x1x1x1x768x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x338x1x1x1x1x768x74x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x438x1x1x1x1x768x57x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x453x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x45x1x1x1x1x768x561x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x495x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x502x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x504x1x1x1x1x768x49x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x544x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x551x1x1x1x1x768x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x57x1x1x1x1x768x438x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x643x1x1x1x1x768x38x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x676x1x1x1x1x768x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x700x1x1x1x1x768x35x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x1536x1x861x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x1x912x1x1x1x1x768x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x1536x6x6x1x3x3x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x1536x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1536x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x1536x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1536x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1536x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1536x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1536x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1536x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1536x8x8x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1536x8x8x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1536x8x8x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1536x8x8x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x1536x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1536x8x8x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1536x8x8x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1536x8x8x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1536x8x8x1x1x1x1x768x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1568x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1568x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1568x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1568x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1568x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1568x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1568x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1584x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1584x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1584x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1584x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1584x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1584x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1584x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1600x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1600x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1600x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1600x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1600x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1600x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:36
2x160x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x160x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x160x14x14x1x1x1x1x528x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x160x14x14x1x3x3x1x160x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x160x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x160x14x14x1x3x3x1x320x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x14x14x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x160x14x14x1x3x3x1x320x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x14x14x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x14x14x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x17x17x1x1x7x1x160x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x17x17x1x1x7x1x160x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x160x17x17x1x1x7x1x160x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x160x17x17x1x1x7x1x160x86x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, OddC, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x160x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x160x17x17x1x7x1x1x160x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x17x17x1x7x1x1x160x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x160x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x160x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x160x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x160x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x160x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x160x64x128x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x160x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x73x73x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x160x73x73x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x160x73x73x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x160x73x73x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x160x7x7x1x1x1x1x960x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x160x7x7x1x1x1x1x960x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x160x7x7x1x3x3x1x320x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x7x7x1x3x3x1x320x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x160x7x7x1x3x3x1x320x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x160x7x7x1x3x3x1x320x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x160x7x7x1x3x3x1x320x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x160x7x7x1x3x3x1x320x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x160x7x7x1x3x3x1x320x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1632x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1632x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1632x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x1632x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1632x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1632x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1632x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x1632x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 128, 64, 32, Filter1x1Pad0, 8, 16, 16, 4, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x1632x1x1x1x1x1x1x68x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x1632x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1632x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1632x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1632x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1632x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1632x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1632x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1632x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x1632x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1664x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1664x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1664x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1664x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1664x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1664x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1664x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1664x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1680x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1680x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1680x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x1680x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1680x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x1680x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1680x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1680x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x168x14x14x1x1x1x1x168x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x168x1x1x1x1x1x1x42x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 32, 32, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1696x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1696x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1696x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1696x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1696x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1696x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x16x112x112x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x16x112x112x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x16x112x112x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x16x112x112x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x16xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x16x128x256x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x16x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x14x14x1x3x3x1x48x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x14x14x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x16x14x14x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x14x14x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x16x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x16x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x16x14x14x1x5x5x1x48x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x16x14x14x1x5x5x1x48x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x16x1920x1080x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 32, 32, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x16x225x225x1x2x2x1x4x14x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 32, 32, 32, Default, 8, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1>+1
2x16x24x240x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x16x24x240x1x3x3x1x32x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x24x240x1x3x3x1x32x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x16x24x240x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x16x28x28x1x5x5x1x32x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x16x28x28x1x5x5x1x32x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x16x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x16x28x28x1x5x5x1x32x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x28x28x1x5x5x1x32x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x16x28x28x1x5x5x1x32x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x16x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x16x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x16x54x54x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x16x54x54x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x54x54x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x16x54x54x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x16x54x54x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x54x54x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x16x54x54x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x16x54x54x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x54x54x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x16x54x54x1x3x3x1x64x42x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x43x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x16x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x16x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x16x55x55x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x16x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x16x55x55x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x16x55x55x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x16x55x55x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x16x55x55x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1728x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1728x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1728x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1728x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1728x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1728x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1728x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x1728x1x30x1x1x1x1x576x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x1728x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1728x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1728x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1728x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1728x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x1728x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1728x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1760x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1760x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:4
2x1760x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1760x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1760x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x1760x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1760x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1760x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x1760x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x176x14x14x1x1x1x1x176x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:38
2x1776x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1776x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x1776x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1776x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x1776x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1776x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1776x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1776x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1792x14x14x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1792x14x14x1x1x1x1x896x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1792x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1792x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1792x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1792x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1824x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1824x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x1824x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1824x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1824x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1824x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1824x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1824x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1824x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1824x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x1856x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x1856x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x1872x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1872x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x1872x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1872x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1872x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x1872x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1872x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x1872x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x1888x28x28x1x1x1x1x640x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 32, Filter1x1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x1888x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1888x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1888x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1920x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1920x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1920x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1920x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1920x16x16x1x1x1x1x1280x280x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1920x32x32x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1920x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, OddC, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1920x64x64x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x1920x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 64, Default, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1920x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1920x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x1920x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x192x1024x1024x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x192x128x256x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x192x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x192x13x13x1x3x3x1x384x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x192x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x13x13x1x3x3x1x384x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x13x13x1x3x3x1x384x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x14x14x1x1x1x1x1152x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:22
2x192x14x14x1x1x1x1x1296x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x192x14x14x1x1x1x1x1392x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1440x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x192x14x14x1x1x1x1x1488x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x192x14x14x1x1x1x1x1488x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x1728x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36
2x192x14x14x1x1x1x1x1968x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:38
2x192x14x14x1x1x1x1x2016x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x2016x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x192x14x14x1x1x1x1x2064x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x192x14x14x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x14x14x1x1x1x1x576x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x192x14x14x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x192x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x192x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x14x14x1x1x1x1x816x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x14x14x1x1x1x1x864x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x192x14x14x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x14x14x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x192x14x14x1x3x3x1x48x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x192x14x14x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x192x14x14x1x3x3x1x48x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x192x17x17x1x1x7x1x128x4x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:36
2x192x17x17x1x1x7x1x192x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x17x17x1x1x7x1x192x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x192x17x17x1x1x7x1x192x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x192x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x17x17x1x3x3x1x192x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39
2x192x17x17x1x3x3x1x192x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x17x17x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x17x17x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x192x17x17x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x192x17x17x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x192x17x17x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x17x17x1x3x3x1x320x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x192x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x17x17x1x3x3x1x320x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x192x17x17x1x3x3x1x320x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x17x17x1x3x3x1x320x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x17x17x1x7x1x1x160x86x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x192x17x17x1x7x1x1x192x128x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x17x17x1x7x1x1x192x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x192x17x17x1x7x1x1x192x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x192x17x17x1x7x1x1x192x84x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x192x17x17x1x7x1x1x192x8x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x192x17x17x1x7x1x1x224x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x192x17x17x1x7x1x1x224x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x1x21x1x1x1x1x384x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x192x23x1x1x3x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x24x16x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x192x24x16x1x3x3x1x194x13x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 32, 32, 32, Default, 8, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1>+1
2x192x25x1x1x3x1x1x192x21x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x27x27x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x27x27x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x27x27x1x1x1x1x48x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x192x27x27x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x27x27x1x3x3x1x48x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x27x27x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x27x27x1x5x5x1x64x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x192x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x192x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x192x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x28x28x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x28x28x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x192x28x28x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x192x28x28x1x1x1x1x16x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x192x28x28x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 16, 16, 32, Filter1x1Pad0, 8, 16, 16, 1, 1> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x192x28x28x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x192x28x28x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x192x28x28x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x192x28x28x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:36
2x192x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x192x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x192x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x28x28x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x192x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x192x28x28x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:40
2x192x28x28x1x1x1x1x624x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:40
2x192x28x28x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x192x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x192x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x192x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x192x28x28x1x1x1x1x720x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x192x28x28x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x192x28x28x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x28x28x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x192x28x28x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x192x28x28x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x192x28x28x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x28x28x1x3x3x1x128x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:24
2x192x28x28x1x3x3x1x192x11x1x1x0x2x2x0x1x1x0x0x192xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x192x28x28x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x192x28x28x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x28x28x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x28x28x1x5x5x1x32x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x28x28x1x5x5x1x32x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x192x28x28x1x5x5x1x32x2x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x192x28x28x1x5x5x1x32x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x192x300x300x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Pad0, 8, 16, 16, 4, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x192x301x301x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x192xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x192x34x34x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x192x35x35x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x192x35x35x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x192x35x35x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x35x35x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x192x35x35x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<256, 64, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v3>
2x192x35x35x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x35x35x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x192x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x192x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x35x35x1x3x3x1x224x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x35x35x1x3x3x1x224x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x35x35x1x3x3x1x224x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x192x35x35x1x3x3x1x224x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x192x35x35x1x3x3x1x224x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x192x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x56x56x1x1x1x1x336x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22
2x192x56x56x1x3x3x1x48x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x56x56x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x192x56x56x1x3x3x1x48x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x56x56x1x3x3x1x48x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x192x64x64x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x192x69x69x1x3x3x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:18
2x192x70x70x1x3x3x1x192x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x192x71x71x1x3x3x1x192x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x71x71x1x3x3x1x192x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x71x71x1x3x3x1x192x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x192x71x71x1x3x3x1x192x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x71x71x1x3x3x1x192x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x64x64, WaveTile: 16x16, WaveMap: 2x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x192x7x7x1x1x1x1x1104x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x7x7x1x1x1x1x1104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1200x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 48x64x64, WaveTile: 16x16, WaveMap: 3x2, VmemReadVec: 6x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1392x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38
2x192x7x7x1x1x1x1x1872x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x1968x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:29
2x192x7x7x1x1x1x1x1968x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x192x7x7x1x1x1x1x2112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x192x7x7x1x1x1x1x2112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:37
2x192x7x7x1x3x3x1x192x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x192x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x192x7x7x1x3x3x1x320x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x192x7x7x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x192x7x7x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x192x7x7x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x192x7x7x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x7x7x1x3x3x1x384x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x192x7x7x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x192x7x7x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x192x7x7x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x192x7x7x1x3x3x1x48x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x192x7x7x1x3x3x1x48x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x192x7x7x1x3x3x1x48x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x1968x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1968x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1968x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x1968x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x1968x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x1968x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x1968x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x1968x7x7x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x1x1074x80x1x3x3x1x256x22x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x161x700x1x5x20x1x32x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x1x161x700x1x5x20x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x161x700x1x5x20x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1x161x700x1x5x20x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x161x700x1x5x20x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1x161x700x1x5x20x1x32x4x2x9x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1x161x700x1x5x20x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x161x700x1x5x20x1x32x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x1x161x700x1x5x5x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Default, 16, 16, 4, 2, 1, 1, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1x161x700x1x5x5x1x64x128x2x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x1x161x700x1x5x5x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x1x161x700x1x5x5x1x64x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x2928x80x1x3x3x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x48x480x1x3x3x1x16x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x48x480x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x48x480x1x3x3x1x16x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x1x48x480x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x1x48x480x1x3x3x1x16x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x48x480x1x3x3x1x16x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x598x80x1x3x3x1x256x76x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x1x647x80x1x3x3x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Default, 16, 16, 4, 2, 1, 1, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1x7x7x1x3x3x1x1x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x1x7x7x1x3x3x1x1x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x1x7x7x1x3x3x1x1x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x1x848x80x1x3x3x1x256x34x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, OddC, 16, 16, 4, 2, 1, 1, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x1x941x80x1x3x3x1x256x30x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x2016x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2016x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x2016x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2016x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2016x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x2016x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2016x59x91x1x1x1x1x896x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2016x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2016x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x2016x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x2048x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:39
2x2048x14x14x1x3x3x1x2048x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x2048x14x14x1x3x3x1x2048x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2
2x2048x14x14x1x3x3x1x2048x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x2048x14x14x1x3x3x1x2048x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:3
2x2048x14x14x1x3x3x1x2048x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x2048x1x1x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x1x1x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x2048x1x1x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x2048x1x1x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x1x30x1x1x1x1x576x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x2048x21x35x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x2048x22x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:28
2x2048x23x30x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x2048x23x35x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x2048x24x36x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x2048x26x34x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x2048x26x40x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x22x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x2048x28x28x1x1x1x1x1024x312x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x2048x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2048x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x2048x28x28x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x2048x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x28x28x1x3x3x1x256x8x24x24x0x1x1x0x24x24x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2048x29x25x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x2048x32x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x2048x32x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x2048x32x32x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x32x32x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x32x32x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x32x32x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16
2x2048x32x32x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x2048x32x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x32x32x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:26
2x2048x36x24x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x2048x48x32x1x1x1x1x576x11x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Filter1x1Pad0, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2048x48x32x1x1x1x1x576x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 32, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 4, 1, 1, 1>+1
2x2048x6x6x1x3x3x1x2048x32x0x0x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x2048x7x7x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x2048x7x7x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x2048x7x7x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x1024x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x2048x7x7x1x1x1x1x1536x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:40
2x2048x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x2048x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x3072x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x96x32, WaveTile: 16x16, WaveMap: 4x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x2048x7x7x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x7x7x1x1x1x1x512x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x2048x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x7x7x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x2048x7x7x1x1x1x1x512x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2048x7x7x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:8
2x2048x7x7x1x3x3x1x2048x128x1x1x0x1x1x0x1x1x0x0x64xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x2048x7x7x1x3x3x1x2048x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x2048x7x7x1x3x3x1x2048x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x2048x7x7x1x3x3x1x2048x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:2
2x2048x7x7x1x3x3x1x2048x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x2048x8x8x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2048x8x8x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x2048x8x8x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x2048x8x8x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x2048x8x8x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x2048x8x8x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2048x8x8x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x2048x8x8x1x1x1x1x320x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x2048x8x8x1x1x1x1x320x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2048x8x8x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x8x8x1x1x1x1x320x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2048x8x8x1x1x1x1x320x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x2048x8x8x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2048x8x8x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2048x8x8x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x2048x8x8x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x2048x8x8x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x2048x8x8x1x1x1x1x448x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2048x8x8x1x1x1x1x448x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x2048x8x8x1x1x1x1x448x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x8x8x1x1x1x1x448x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x448x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2048x8x8x1x1x1x1x448x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x448x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x2048x8x8x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x2048x8x8x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x8x8x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2048x8x8x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x2048x8x8x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x2048x8x8x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x2064x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x2064x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x2064x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2064x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x2064x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Filter1x1Pad0, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2064x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2064x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x2064x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x2064x7x7x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x2064x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2064x7x7x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x208x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 32, OddC, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x2112x14x14x1x1x1x1x1056x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2112x14x14x1x1x1x1x1056x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2112x14x14x1x1x1x1x1056x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x2112x14x14x1x1x1x1x1056x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x2112x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2112x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2112x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x2112x7x7x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x2112x7x7x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x2160x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Filter1x1Stride1Pad0, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2160x7x7x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x2160x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x2160x7x7x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x219x64x64x1x1x1x1x93x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Filter1x1Pad0, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
2x224x17x17x1x1x7x1x224x128x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x224x17x17x1x1x7x1x224x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x224x17x17x1x1x7x1x224x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x224x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x224x17x17x1x7x1x1x256x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x224x235x363x1x3x3x1x224x8x1x1x0x1x1x0x1x1x0x0x4xNCHWxFP16xF=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 64, OddC, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x224x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x224x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x224x35x35x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x224x35x35x1x3x3x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x224x35x35x1x3x3x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x224x35x35x1x3x3x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x224x35x35x1x3x3x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x224x35x35x1x3x3x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x224x35x35x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x224x470x725x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 32, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x224x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x224x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39
2x224x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x224x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x224x7x7x1x3x3x1x224x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x232x14x14x1x1x1x1x232x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x232x14x14x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x232x14x14x1x1x1x1x232x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x232x14x14x1x1x1x1x232x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x232x64x64x1x1x1x1x1130x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x232x7x7x1x1x1x1x232x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x232x7x7x1x1x1x1x232x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x232x7x7x1x1x1x1x232x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x232x7x7x1x3x3x1x232x1024x1x1x0x1x1x0x1x1x0x0x232xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:3
2x240x14x14x1x1x1x1x60x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1>+1
2x240x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x240x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x240x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x240x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x240x28x28x1x1x1x1x60x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:20
2x240x28x28x1x1x1x1x60x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:10
2x240x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x240x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x240x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x240x56x56x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x240x7x7x1x1x1x1x960x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21
2x240x7x7x1x1x1x1x960x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:10
2x240x7x7x1x1x1x1x960x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21
2x240x7x7x1x1x1x1x960x64x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP16xB=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1>+1
2x240x7x7x1x3x3x1x240x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x240x7x7x1x3x3x1x240x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x240x7x7x1x3x3x1x240x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x240x7x7x1x3x3x1x240x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x240x7x7x1x3x3x1x240x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x244x28x28x1x3x3x1x244x16x1x1x0x2x2x0x1x1x0x0x244xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, OddC, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
2x24x112x112x1x3x3x1x3x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:31
2x24x14x14x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x24x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x24x14x14x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x24x14x14x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x24x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x24x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x24x14x14x1x5x5x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x24x14x14x1x5x5x1x64x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x24x16x16x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x24x28x28x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x24x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x24x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x24x28x28x1x1x1x1x58x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x24x55x55x1x1x1x1x54x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x24x55x55x1x1x1x1x54x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x24x56x56x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x24x56x56x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:24
2x24x56x56x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x24x56x56x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x24x56x56x1x1x1x1x144x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x24x56x56x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x24x56x56x1x1x1x1x58x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x24x56x56x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x24x56x56x1x1x1x1x58x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x24x56x56x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x24x56x56x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x24x56x56x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x24x56x56x1x3x3x1x24x1024x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4
2x24x56x56x1x3x3x1x24x512x1x1x0x2x2x0x1x1x0x0x24xNCHWxFP32xF=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8
2x24x64x128x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x2560x32x32x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2560x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 256, 64, 64, OddC, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2560x7x7x1x1x1x1x768x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 96, 64, Filter1x1Pad0, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x100x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x1024x1024x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x1024x1024x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x1024x1024x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x104x80x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:34
2x256x10x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x256x10x6x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x256x112x112x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x112x80x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x112x88x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x256x121x19x1x3x3x1x256x118x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x256x124x92x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x128x128x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x256x128x128x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x128x128x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x128x128x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x128x128x1x3x3x1x512x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x128x256x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, OddC, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x128x256x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x128x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x12x14x1x3x3x1x2048x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x256x12x16x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x132x92x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x256x132x96x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:32
2x256x13x13x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x256x13x13x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x256x13x13x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x256x13x13x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x256x13x13x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x256x13x13x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x13x13x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x256x13x13x1x3x3x1x256x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x13x13x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x13x13x1x3x3x1x256x50x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x13x13x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:26
2x256x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x13x13x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x13x13x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x13x15x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x13x17x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x256x148x92x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x256x14x14x1x1x1x1x1024x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x14x14x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x256x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x14x14x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x14x14x1x1x1x1x1024x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x14x14x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x256x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x14x14x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x256x14x14x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x256x14x14x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x14x14x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x14x14x1x1x1x1x512x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x14x14x1x2x2x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:22
2x256x14x14x1x3x3x1x128x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:11
2x256x14x14x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x14x14x1x3x3x1x256x124x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x14x14x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x14x14x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x3x3x1x256x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x256x14x14x1x3x3x1x256x18x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x256x14x14x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:32
2x256x14x14x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x256x14x14x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39
2x256x14x14x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x256x14x14x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x256x14x14x1x3x3x1x256x35x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x256x14x14x1x3x3x1x256x38x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:33
2x256x14x14x1x3x3x1x256x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x14x14x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x14x14x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x14x14x1x3x3x1x256x800x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x14x14x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x256x14x14x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x256x152x84x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32
2x256x156x100x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x159x279x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x256x15x15x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x15x15x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x15x15x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x256x15x15x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x15x15x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x160x264x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:19
2x256x16x16x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x16x16x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x256x176x200x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x176x248x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x17x11x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x256x17x13x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:17
2x256x17x17x1x1x7x1x256x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x17x17x1x1x7x1x256x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x17x17x1x3x3x1x1024x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:38
2x256x17x17x1x7x1x1x320x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x17x17x1x7x1x1x320x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x184x176x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x256x184x240x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x256x184x272x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x192x232x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x256x19x12x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x256x19x19x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:19
2x256x19x83x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x1x1x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40
2x256x1x1x1x3x3x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:33
2x256x1x1x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x1x1x1x3x3x1x340x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Default, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x200x192x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x200x256x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x20x31x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:27
2x256x20x84x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x256x20x84x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x20x84x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x20x84x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x20x84x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x20x84x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x20x84x1x5x5x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x20x84x1x5x5x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x256x20x84x1x5x5x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x20x84x1x5x5x1x512x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x20x84x1x5x5x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x216x168x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x256x216x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x256x216x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:34
2x256x216x184x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x21x12x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x256x21x38x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:24
2x256x23x36x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x256x24x39x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x256x256x256x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x256x256x256x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x256x256x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x256x256x1x1x1x1x128x6x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x256x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x256x256x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x256x256x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x256x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x256x256x1x3x3x1x1024x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Default, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x256x256x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x256x256x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x256x256x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x256x256x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x256x256x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x26x26x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x26x26x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x270x39x1x3x3x1x1x74x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x256x272x200x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x27x27x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x27x27x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:3
2x256x27x27x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x27x27x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x256x27x27x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:26
2x256x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x27x27x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x256x27x27x1x1x1x1x48x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x256x27x27x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x27x27x1x3x3x1x256x6x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 64, 64, 64, Default, 8, 8, 8>+1
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x27x27x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:18
2x256x27x27x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x27x27x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x280x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x256x28x25x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x28x28x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x1280x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x256x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:27;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 64, 64, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x256x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x256x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x28x28x1x1x1x1x21x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x28x28x1x1x1x1x21x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, OddC, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x28x28x1x1x1x1x21x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x256x28x28x1x1x1x1x21x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x21x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x256x28x28x1x1x1x1x21x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x28x28x1x1x1x1x21x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x28x28x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x28x28x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x28x28x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x28x28x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x28x28x1x1x1x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x28x28x1x1x1x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x512x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x28x28x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x64x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x256x28x28x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x256x28x28x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x256x28x28x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x80x132x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x28x28x1x1x1x1x80x23x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x256x28x28x1x1x1x1x80x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x28x28x1x1x1x1x81x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x256x28x28x1x1x1x1x81x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x256x28x28x1x1x1x1x81x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x1x1x1x81x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x256x28x28x1x1x1x1x81x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x28x28x1x2x2x1x256x108x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x256x28x28x1x2x2x1x256x176x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x2x2x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x256x28x28x1x2x2x1x256x20x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:33
2x256x28x28x1x2x2x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x28x28x1x3x3x1x160x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x256x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x256x28x28x1x3x3x1x256x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 32, 64, 64, Default, 8, 8, 8>+1
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x28x28x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x28x28x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x256x28x28x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x28x28x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x28x28x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x256x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x28x28x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x256x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x256x296x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17
2x256x29x29x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x29x29x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x29x29x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:16
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x29x29x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, OddC, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x29x29x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x29x29x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:3
2x256x30x30x1x3x3x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x31x20x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40
2x256x32x20x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x32x21x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x256x32x32x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x32x32x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x32x32x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x32x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x256x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x256x35x35x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:33
2x256x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x256x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 8, 16, 16, 4, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x256x377x39x1x3x3x1x256x44x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, OddC, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x38x23x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x256x38x38x1x1x1x1x256x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x256x38x38x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x38x38x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x38x38x1x3x3x1x340x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x3x3x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x256x3x3x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x256x3x3x1x3x3x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:16
2x256x3x3x1x3x3x1x324x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x256x3x3x1x3x3x1x340x114x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x256x40x22x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:40
2x256x40x40x1x1x3x1x512x1x0x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x256x42x52x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x42x66x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x44x56x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x256x44x66x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:33
2x256x44x82x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:23
2x256x46x74x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x46x78x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x46x84x1x3x3x1x720x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x256x48x60x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x256x48x68x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:33
2x256x48x84x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x4x4096x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x4x4x1x3x3x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x50x60x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x50x74x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x512x512x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x256x52x50x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x52x52x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:34
2x256x53x53x1x3x3x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x53x53x1x3x3x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x53x53x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x55x55x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x256x55x55x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x55x55x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 32, 64, Default, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x256x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x256x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x56x56x1x1x1x1x128x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x256x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x56x56x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x256x56x56x1x1x1x1x128x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x256x56x56x1x1x1x1x128x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x128x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x56x56x1x1x1x1x128x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x56x56x1x1x1x1x512x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x56x56x1x1x1x1x512x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x56x56x1x1x1x1x512x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x56x56x1x1x1x1x512x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x1x1x1x64x15x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:8
2x256x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x256x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x256x56x56x1x1x1x1x64x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x256x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x56x56x1x1x1x1x64x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 64, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x256x56x56x1x1x1x1x64x51x0x0x0x1x1x0x1x1x0x0x1xNHWCxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle_V3_Large_Tensor<256, 64, 64, Default, 16, 16, 2, 1, 8, 8, 1, 1, 1>
2x256x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x56x56x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x56x56x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x56x56x1x3x3x1x256x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x2x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x256x56x56x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x256x56x56x1x3x3x1x256x42x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x256x56x56x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x56x56x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x256x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x56x56x1x3x3x1x96x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<64, 32, 32, 64, OddC, 8, 16, 16, 1, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x256x57x57x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x57x57x1x1x1x1x128x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x57x57x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x512x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x57x57x1x1x1x1x512x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x57x57x1x1x1x1x512x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x57x57x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x57x57x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x57x57x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x256x57x57x1x3x3x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x256x57x57x1x3x3x1x256x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5
2x256x57x57x1x3x3x1x256x48x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:1
2x256x57x57x1x3x3x1x256x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x256x57x57x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x256x58x42x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x256x58x58x1x3x3x1x256x208x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x256x5x5x1x1x1x1x128x114x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x256x5x5x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x256x5x5x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x5x5x1x3x3x1x128x19x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x5x5x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x256x644x39x1x3x3x1x1x18x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x256x64x48x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x256x64x64x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x64x64x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x256x64x64x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x64x64x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x64x64x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x64x64x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x64x64x1x3x3x1x256x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x64x64x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x64x64x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x256x66x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x256x66x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x256x66x48x1x1x1x1x3x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x70x46x1x3x3x1x720x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x256x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x256x7x7x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x7x7x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x256x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x7x7x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x256x7x7x1x3x3x1x832x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x256x7x7x1x7x7x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x7x7x1x7x7x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x7x7x1x7x7x1x1024x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x7x7x1x7x7x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x256x80x120x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x80x128x1x3x3x1x256x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x80x128x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x256x80x144x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x256x80x44x1x1x1x1x512x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x256x82x46x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x256x84x152x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x256x84x152x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x256x84x42x1x3x3x1x36x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x256x84x48x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:22
2x256x874x39x1x3x3x1x256x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:36
2x256x88x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x256x8x5x1x3x3x1x36x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x256x8x8x1x1x3x1x384x4x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x256x8x8x1x1x3x1x384x8x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x256x92x164x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x256x96x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33
2x256x96x124x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:33;ConvBinWinogradRxSf3x2:22
2x256x96x156x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:34
2x272x16x16x1x1x1x1x1632x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x288x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x288x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x288x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x288x14x14x1x3x3x1x144x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x288x14x14x1x3x3x1x288x64x1x1x0x1x1x0x1x1x0x0x288xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x288x24x16x1x1x1x1x288x31x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x288x24x16x1x3x3x1x288x37x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x288x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x288x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x288x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x288x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x288x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x288x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x28x28x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:35
2x288x35x35x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x35x35x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x288x35x35x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x288x35x35x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x288x35x35x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x288x35x35x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x288x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x288x35x35x1x3x3x1x384x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x288x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x288x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x288x48x32x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x288x48x32x1x1x1x1x384x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x288x56x56x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x288x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x288x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x288x56x56x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x288x7x7x1x5x5x1x288x16x2x2x0x2x2x0x1x1x0x0x288xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x296x128x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x2x24x16x1x1x1x1x2x7x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 2, 2, 2, 1, 2, 1, 1, 1>
2x2x3x3x1x3x3x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x3072x12x12x1x3x3x1x3072x4x1x1x0x1x1x0x1x1x0x0x3072xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x320x128x128x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x320x128x128x1x3x3x1x320x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 64, Default, 16, 16, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x320x128x128x1x3x3x1x4x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, OddC, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x320x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x320x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x320x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x320x17x17x1x3x3x1x320x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x320x17x17x1x3x3x1x320x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x320x17x17x1x3x3x1x320x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x320x17x17x1x7x1x1x256x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:19;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 32, 64, 64, Default, 8, 8, 8>+1
2x320x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x320x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x320x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x320x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x320x28x28x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x320x28x28x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x320x64x64x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x64x64x1x3x3x1x320x1x1x1x0x2x2x0x1x1x0x0x320xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x320x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x320x7x7x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x320x7x7x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x320x7x7x1x1x1x1x1280x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x320x7x7x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x320x7x7x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 128, 64, 32, Filter1x1Stride1Pad0, 8, 16, 16, 4, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x320x7x7x1x1x1x1x960x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x320x7x7x1x3x3x1x160x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x320x7x7x1x3x3x1x192x1024x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x320x8x8x1x1x1x1x1280x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:32
2x320x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x32x112x112x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x32x112x112x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x112x112x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x112x112x1x3x3x1x32x1x1x1x0x2x2x0x1x1x0x0x2xNCHWxFP16xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:13;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, OddC, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x32x113x113x1x3x3x1x3x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x32x128x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x32x128x256x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x12x120x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x12x120x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x12x120x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x32x12x120x1x3x3x1x64x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x12x120x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x32x12x120x1x3x3x1x64x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x12x120x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x32x147x147x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x147x147x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x147x147x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x32x147x147x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x32x147x147x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x147x147x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x147x147x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x149x149x1x3x3x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x149x149x1x3x3x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x149x149x1x3x3x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x149x149x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x32x149x149x1x3x3x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x149x149x1x3x3x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x149x149x1x3x3x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x32x149x149x1x3x3x1x32x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x149x149x1x3x3x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x149x149x1x3x3x1x32x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x14x14x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17
2x32x14x14x1x1x1x1x528x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x14x14x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x32x14x14x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x32x14x14x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 32, 32, 32, Default, 8, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1>+1
2x32x14x14x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x32x14x14x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x32x14x14x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x32x14x14x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x32x14x14x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x32x14x14x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x32x14x14x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x14x14x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x32x14x14x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:4
2x32x14x14x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x32x14x14x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x32x14x14x1x5x5x1x64x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x32x14x14x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x32x150x150x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x32x153x662x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x32x157x681x1x5x20x1x1x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x32x192x128x1x1x1x1x40x3x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x32x192x128x1x1x1x1x40x7x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, OddC, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x32x208x208x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x24x240x1x3x3x1x16x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5
2x32x257x257x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 64, 16, 32, Default, 8, 16, 16, 4, 1> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x32x27x27x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x27x27x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x32x27x27x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x32x27x27x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x27x27x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x32x27x27x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:8
2x32x27x27x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x27x27x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x32x27x27x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x32x27x27x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x27x27x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x32x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x32x28x28x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x28x28x1x3x3x1x96x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x32x28x28x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x32x28x28x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x32x28x28x1x5x5x1x192x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x32x28x28x1x5x5x1x96x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x28x28x1x5x5x1x96x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x32x28x28x1x5x5x1x96x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x32x28x28x1x5x5x1x96x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x28x28x1x5x5x1x96x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x32x28x28x1x5x5x1x96x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x32x28x28x1x5x5x1x96x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x32x416x416x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x32x417x417x1x3x3x1x64x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x417x417x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x469x724x1x1x1x1x224x10x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Default, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 1>
2x32x54x54x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x32x54x54x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x32x54x54x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x32x54x54x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x32x54x54x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x54x54x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x32x54x54x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x56x56x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x32x56x56x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x56x56x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x32x56x56x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x597x597x1x3x3x1x3x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x32x64x128x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x32x77x332x1x5x20x1x1x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x32x79x341x1x5x10x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x32x79x341x1x5x10x1x32x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x79x341x1x5x10x1x32x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x79x341x1x5x10x1x32x8x2x4x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 128, 32, 64, Default, 32, 32, 2, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x32x7x7x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x7x7x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x32x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x32x7x7x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x32x7x7x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x32x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x32x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x32x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x32x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x32x7x7x1x5x5x1x128x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x336x14x14x1x5x5x1x336x1x2x2x0x2x2x0x1x1x0x0x336xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x336x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x336x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x336x56x56x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x336x56x56x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x336x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x336x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x340x3x3x1x3x3x1x256x19x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:10
2x344x1x1x1x3x3x1x256x3x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:9
2x352x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x352x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x352x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x352x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x352x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x352x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x352x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x352x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x352x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x352x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x352x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x352x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x35x48x32x1x1x1x1x64x24x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x35x48x32x1x1x1x1x64x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x360x64x64x1x3x3x1x360x1x1x1x0x1x1x0x1x1x0x0x360xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x36x11x16x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:8
2x36x12x18x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:10
2x36x22x27x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x36x25x37x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x36x26x24x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x36x44x58x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:27
2x36x46x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:24
2x36x5x9x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:10
2x36x84x140x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:18
2x36x84x168x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:17
2x36x96x104x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x36x96x148x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:29
2x36x9x6x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:11
2x384x128x128x1x1x1x1x1152x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x128x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x13x13x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x384x13x13x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x13x13x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x384x13x13x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x384x13x13x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x384x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x384x13x13x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x384x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x384x13x13x1x3x3x1x192x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x13x13x1x3x3x1x192x4096x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x384x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:31;ConvBinWinogradRxSf3x2:37
2x384x13x13x1x3x3x1x256x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x384x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x384x13x13x1x3x3x1x256x2048x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x13x13x1x3x3x1x256x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x13x13x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x13x13x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x13x13x1x3x3x1x384x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x13x13x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x384x13x13x1x3x3x1x384x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x13x13x1x3x3x1x384x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x384x13x13x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x13x13x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x384x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x384x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x14x14x1x1x1x1x1312x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:21
2x384x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x384x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x384x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:3
2x384x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x384x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x384x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x384x14x14x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x384x14x14x1x1x1x1x96x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x384x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x384x17x17x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x1x21x1x1x1x1x192x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x384x1x21x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x384x256x256x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x27x27x1x1x1x1x48x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x384x27x27x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x27x27x1x1x1x1x48x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x384x27x27x1x1x1x1x48x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x384x27x27x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x27x27x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x27x27x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x384x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:24
2x384x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x384x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x384x28x28x1x1x1x1x768x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x384x28x28x1x3x3x1x384x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x384x35x35x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x384x35x35x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x384x35x35x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x384x35x35x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x384x35x35x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x35x35x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:18
2x384x35x35x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x35x35x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x35x35x1x3x3x1x384x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x384x35x35x1x3x3x1x384x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x384x35x35x1x3x3x1x384x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x384x35x35x1x3x3x1x384x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x384x48x32x1x1x1x1x384x9x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x384x48x32x1x1x1x1x419x216x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x384x48x32x1x3x3x1x384x80x1x1x0x1x1x0x1x1x0x0x6xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x384x48x48x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x384x512x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x384x56x56x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x56x56x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x56x56x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x384x64x128x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:36
2x384x7x7x1x1x1x1x832x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x384x7x7x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:6;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 32, 64, Default, 8, 8, 8>+1
2x384x7x7x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x384x8x8x1x1x1x1x1280x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40
2x384x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x384x8x8x1x1x3x1x256x512x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x384x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x8x8x1x1x3x1x384x128x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x8x8x1x1x3x1x384x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x384x8x8x1x1x3x1x448x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x384x8x8x1x1x3x1x448x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x384x8x8x1x3x1x1x256x16x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x384x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x384x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x384x8x8x1x3x1x1x384x128x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x384x8x8x1x3x1x1x384x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x384x8x8x1x3x3x1x448x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:35
2x384x96x96x1x3x3x1x768x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32
2x38x1024x1024x1x3x3x1x38x1x1x1x0x1x1x0x1x1x0x0x38xNCHWxFP16xF=ConvBinWinogradRxSf2x3:30;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
2x3x1024x2048x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x1030x1030x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x1030x1030x1x7x7x1x64x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x107x107x1x3x3x1x64x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x3x108x108x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x108x108x1x3x3x1x64x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x108x108x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x108x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:23
2x3x10x10x1x3x3x1x5x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x3x10x10x1x3x3x1x5x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x3x10x10x1x3x3x1x5x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x3x1199x1199x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x3x120x120x1x7x7x1x64x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 64, 32, Default, 32, 32, 2, 1, 1, 1, 8, 1, 1, 1>
2x3x164x96x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:19
2x3x1x1x1x3x3x1x4x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:11
2x3x1x1x1x3x3x1x4x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x3x200x272x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:13
2x3x2048x2048x1x14x14x1x768x1x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x223x223x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x3x223x223x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x3x223x223x1x7x7x1x64x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x3x224x224x1x14x14x1x1536x4x0x0x0x14x14x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x24x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x224x224x1x3x3x1x24x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x3x224x224x1x3x3x1x24x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x3x224x224x1x3x3x1x24x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x3x224x224x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x224x224x1x3x3x1x24x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x3x224x224x1x3x3x1x24x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x3x224x224x1x3x3x1x32x1024x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x3x224x224x1x3x3x1x32x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x3x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x3x224x224x1x3x3x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x3x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x3x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x3x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x3x224x224x1x3x3x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x3x224x224x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x3x224x224x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x3x224x224x1x7x7x1x64x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x224x224x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x7x7x1x64x48x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x3x224x224x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x3x224x224x1x7x7x1x64x6x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x7x7x1x64x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x3x224x224x1x7x7x1x96x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x224x224x1x7x7x1x96x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x3x224x224x1x7x7x1x96x2x3x3x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x3x224x224x1x7x7x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x224x224x1x7x7x1x96x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x225x225x1x3x3x1x32x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x3x225x225x1x7x7x1x64x128x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x225x225x1x7x7x1x64x16x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x225x225x1x7x7x1x64x1x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x225x225x1x7x7x1x64x64x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x3x225x225x1x7x7x1x64x8x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x227x227x1x7x7x1x64x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x227x227x1x7x7x1x64x32x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x22x36x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:9
2x3x230x230x1x7x7x1x64x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x230x230x1x7x7x1x64x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x230x230x1x7x7x1x64x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x3x230x230x1x7x7x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x25x20x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:8
2x3x299x299x1x3x3x1x32x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x3x299x299x1x3x3x1x32x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x3x299x299x1x3x3x1x32x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x3x299x299x1x3x3x1x32x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x299x299x1x3x3x1x32x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x3x299x299x1x7x7x1x64x24x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x3x299x299x1x7x7x1x64x58x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x3x304x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:8
2x3x312x176x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:20
2x3x32x32x1x1x1x1x3x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x3x32x32x1x1x1x1x3x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x32x32x1x3x3x1x32x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x3x32x32x1x3x3x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x3x416x416x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x3x672x1248x1x7x7x1x64x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x3x6x6x1x3x3x1x4x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x3x6x6x1x3x3x1x4x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x3x6x6x1x3x3x1x4x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x3x6x6x1x3x3x1x4x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x3x6x6x1x3x3x1x4x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x3x80x144x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:14
2x3x832x640x1x7x7x1x64x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x3x895x895x1x7x7x1x96x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x3x896x896x1x3x3x1x24x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x3x96x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x3x96x160x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10
2x4096x1x1x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x4096x1x1x1x1x1x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x40x112x112x1x3x3x1x40x64x1x1x0x1x1x0x1x1x0x0x40xNCHWxFP32xF=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:7
2x40x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x40x192x128x1x1x1x1x32x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x40x192x128x1x1x1x1x32x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x40x192x128x1x3x3x1x40x23x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x40x256x256x1x3x3x1x40x1x1x1x0x2x2x0x1x1x0x0x40xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x40x96x64x1x1x1x1x32x11x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x40x96x64x1x1x1x1x40x27x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x40x96x64x1x1x1x1x40x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x40x96x64x1x1x1x1x48x17x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Filter1x1Stride1Pad0, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x40x96x64x1x1x1x1x96x23x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x416x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x416x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x416x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x416x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x416x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x416x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x416x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x432x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x432x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x432x14x14x1x3x3x1x432x32x1x1x0x1x1x0x1x1x0x0x432xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x432x14x14x1x3x3x1x432x64x1x1x0x1x1x0x1x1x0x0x432xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x432x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x432x28x28x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x432x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x432x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x432x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x448x118x181x1x3x3x1x448x14x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x448x118x182x1x1x1x1x896x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x448x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x448x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x448x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x448x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x448x256x256x1x1x1x1x224x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32
2x448x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x448x28x28x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x448x8x8x1x1x1x1x1280x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40
2x448x8x8x1x3x1x1x512x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x448x8x8x1x3x1x1x512x400x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x448x8x8x1x3x1x1x512x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x448x8x8x1x3x3x1x384x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x448x8x8x1x3x3x1x384x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x448x8x8x1x3x3x1x384x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x448x8x8x1x3x3x1x384x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x448x8x8x1x3x3x1x384x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x448x8x8x1x3x3x1x384x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x464x7x7x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x464x7x7x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x464x7x7x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x120x256x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:31
2x480x14x14x1x1x1x1x120x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:10
2x480x14x14x1x1x1x1x120x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 32, 64, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x480x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x480x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x480x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x480x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x480x14x14x1x1x1x1x16x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x480x14x14x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x480x14x14x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x480x14x14x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x480x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x480x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x480x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x480x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x480x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x480x14x14x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x480x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x480x14x14x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x480x14x14x1x1x1x1x64x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x480x14x14x1x1x1x1x96x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x480x14x14x1x1x1x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x480x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x480x14x14x1x1x1x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x480x14x14x1x1x1x1x96x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x480x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x480x28x28x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x480x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x480x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x480x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x480x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x480x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x480x64x128x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x480x64x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x48x1024x1024x1x3x3x1x24x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, Default, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x48x112x112x1x3x3x1x48x16x1x1x0x2x2x0x1x1x0x0x48xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:5
2x48x128x128x1x3x3x1x48x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, OddC, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x48x13x13x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
2x48x13x13x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x48x13x13x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x48x13x13x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x48x13x13x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x48x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x13x13x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x48x13x13x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x48x13x13x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x48x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:14;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 64, Default, 16, 16, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x48x13x13x1x3x3x1x192x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x48x14x14x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:25
2x48x14x14x1x3x3x1x192x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x48x27x27x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x48x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x48x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x48x27x27x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x64x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 2x8, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x48x27x27x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x48x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x48x27x27x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x48x27x27x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x48x27x27x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x48x27x27x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x48x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 32, 32, 32, Filter1x1Stride1Pad0, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=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>+1
2x48x35x35x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x48x35x35x1x1x1x1x288x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:23
2x48x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x48x35x35x1x1x1x1x288x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x48x35x35x1x3x3x1x64x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x48x35x35x1x5x5x1x64x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x48x35x35x1x5x5x1x64x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x48x48x32x1x3x3x1x48x33x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x48x48x32x1x3x3x1x48x34x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x48x7x7x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x48x7x7x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x48x7x7x1x3x3x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x48x7x7x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x48x7x7x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x48x7x7x1x5x5x1x128x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x48x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x48x7x7x1x5x5x1x128x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:4
2x48x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x48x7x7x1x5x5x1x128x32x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39
2x48x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x48x96x64x1x3x3x1x48x35x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x4x128x128x1x1x1x1x4x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x4x128x128x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
2x4x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x4x2x2x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x4x2x2x1x3x3x1x3x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x4x2x2x1x3x3x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x4x2x2x1x3x3x1x3x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:11;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x4x3x3x1x3x3x1x3x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x4x3x3x1x3x3x1x3x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x4x3x3x1x3x3x1x3x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x504x14x14x1x1x1x1x95x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x510x10x10x1x3x3x1x512x100x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x510x10x10x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:37
2x510x19x19x1x3x3x1x512x24x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x510x5x5x1x3x3x1x256x200x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x510x5x5x1x3x3x1x256x59x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x512x100x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x100x140x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x512x100x144x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:38;ConvBinWinogradRxSf3x2:34
2x512x100x152x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x103x83x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x512x108x92x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x512x10x10x1x3x3x1x24x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x10x10x1x3x3x1x24x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x512x10x10x1x3x3x1x486x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x10x10x1x3x3x1x510x56x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:35
2x512x10x42x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x512x10x42x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x10x42x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x112x112x1x1x1x1x1024x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:16
2x512x112x112x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xB=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10
2x512x112x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x512x112x88x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x114x114x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x512x116x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x512x128x128x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x128x128x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x128x128x1x1x1x1x1024x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x128x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x128x128x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x128x128x1x1x1x1x128x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x512x128x128x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x128x128x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x128x128x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x128x128x1x1x1x1x12x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x128x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x128x128x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x128x128x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x128x128x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x128x128x1x1x1x1x256x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x128x128x1x1x1x1x256x400x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x128x128x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x128x128x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x512x128x128x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x128x128x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x128x88x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x128x92x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x512x136x100x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x512x13x13x1x1x1x1x1000x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x13x13x1x1x1x1x1000x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x13x13x1x1x1x1x1000x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x13x13x1x1x1x1x1000x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x13x13x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x13x13x1x1x1x1x64x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x512x13x13x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
2x512x13x13x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:14
2x512x13x13x1x3x3x1x512x4x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x512x14x14x1x1x1x1x1024x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x14x14x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x1024x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x112x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x1x1x1x112x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x512x14x14x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x512x14x14x1x1x1x1x112x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x1x1x1x112x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x112x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x512x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x512x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x512x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x512x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x144x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x144x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x14x14x1x1x1x1x144x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x512x14x14x1x1x1x1x144x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x144x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x512x14x14x1x1x1x1x144x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:5
2x512x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x512x14x14x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x512x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x512x14x14x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 64x64x32, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x14x14x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x14x14x1x1x1x1x24x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x1x1x1x24x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x512x14x14x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x512x14x14x1x1x1x1x24x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x512x14x14x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x512x14x14x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x512x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x512x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x512x14x14x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x512x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:5
2x512x14x14x1x1x1x1x32x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x512x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x512x14x14x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x14x14x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:3
2x512x14x14x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x1x1x1x64x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x512x14x14x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x14x14x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxINT8xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 16, 16, 64, OddC, 16, 16, 16, 1, 1> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 16, BBlockTransferSrcScalarPerVector: 16
2x512x14x14x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x14x14x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x14x14x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x512x14x14x1x3x3x1x512x48x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x14x14x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x14x14x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x14x14x1x3x3x1x512x96x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x14x14x1x5x5x1x48x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x5x5x1x48x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x14x14x1x5x5x1x48x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x14x14x1x5x5x1x48x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x512x14x14x1x5x5x1x48x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x15x15x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x15x15x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x15x15x1x1x1x1x1024x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x15x15x1x1x1x1x1024x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x512x15x15x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x512x15x15x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x15x15x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x512x15x15x1x3x3x1x512x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x15x15x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x15x15x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:2
2x512x15x15x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x15x15x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x16x16x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x512x16x16x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x512x16x16x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:3
2x512x16x16x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x512x16x16x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x16x16x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x512x16x16x1x3x3x1x512x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x512x16x16x1x3x3x1x512x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x19x19x1x1x1x1x256x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x512x19x19x1x3x3x1x256x3x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:27
2x512x19x19x1x3x3x1x486x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x1x111x1x1x3x1x512x95x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x130x1x1x3x1x512x82x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x512x1x131x1x1x3x1x512x88x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x157x1x1x3x1x512x57x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x512x1x173x1x1x3x1x512x50x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x512x1x184x1x1x3x1x512x40x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x512x1x1x1x7x7x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x512x1x202x1x1x3x1x512x42x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x220x1x1x3x1x512x34x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x278x1x1x3x1x512x22x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x1x320x1x1x3x1x512x16x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x331x1x1x3x1x512x14x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xW=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x1x467x1x1x3x1x512x8x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x512x1x56x1x1x3x1x512x313x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x512x1x624x1x1x3x1x512x5x0x2x0x1x1x0x1x1x0x0x512xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x512x1x70x1x1x3x1x512x237x0x2x0x1x1x0x1x1x0x0x512xNCHWxFP16xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x512x24x26x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x24x29x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x512x24x34x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x512x24x40x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x512x256x256x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x512x256x256x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x256x256x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x512x256x256x1x1x1x1x208x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, Filter1x1Stride1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x512x256x256x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x512x256x256x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x256x256x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x512x256x256x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x25x41x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:30
2x512x27x27x1x3x3x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x512x27x27x1x3x3x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x27x27x1x3x3x1x512x8x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x512x28x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x512x28x28x1x1x1x1x1024x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x28x28x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x512x28x28x1x1x1x1x1024x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x28x28x1x1x1x1x1024x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x512x28x28x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x28x28x1x1x1x1x1024x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x48x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x512x28x28x1x1x1x1x1024x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 64, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x1x1x1x1024x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x1024x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x28x28x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x28x28x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x28x28x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x28x28x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x512x28x28x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x512x28x28x1x1x1x1x128x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 64, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 4, 1, 1>+1
2x512x28x28x1x1x1x1x128x51x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x512x28x28x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x512x28x28x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x28x28x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x2048x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x256x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x28x28x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x512x28x28x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x28x28x1x1x1x1x256x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x512x28x28x1x1x1x1x256x208x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x512x28x28x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x28x28x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x256x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x256x56x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x512x28x28x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x28x28x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x512x28x28x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x28x28x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x512x28x28x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x28x28x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x28x28x1x1x1x1x512x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x512x28x28x1x1x1x1x512x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x1x1x1x768x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x512x28x28x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x28x28x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x3x3x1x512x128x4x4x0x1x1x0x4x4x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x512x28x28x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x512x28x28x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x512x28x28x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x43x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xW=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x28x28x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:2
2x512x28x28x1x3x3x1x512x64x4x4x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x512x28x28x1x3x3x1x512x6x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x28x28x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x29x29x1x1x1x1x1024x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x1024x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x1024x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x29x29x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x29x29x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x512x29x29x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x29x29x1x1x1x1x512x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x29x29x1x3x3x1x512x16x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xB=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:5;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 64, 256, 64, Default, 8, 8, 8>+1
2x512x29x29x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x29x29x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x512x29x29x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x30x21x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:28
2x512x31x25x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:4
2x512x32x32x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x512x32x32x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x32x32x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x32x32x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x1x1x1x2048x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:5
2x512x32x32x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x512x32x32x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x32x32x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x32x32x1x1x1x1x6x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x512x32x32x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x3x3x1x512x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x3x3x1x512x6x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x32x32x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x512x35x24x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x512x37x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:38
2x512x39x23x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:29
2x512x40x25x1x3x3x1x512x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:37
2x512x4x4x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x4x4x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x512x4x4x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x512x4x4x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x512x512x512x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x512x512x512x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x512x512x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x53x53x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x512x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x512x56x56x1x1x1x1x128x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:31
2x512x56x56x1x3x3x1x512x120x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x56x56x1x3x3x1x512x1x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x56x56x1x3x3x1x512x2x0x0x0x2x2x0x1x1x0x0x32xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 32, 32, Default, 16, 16, 4, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:5
2x512x56x56x1x3x3x1x512x32x1x1x0x2x2x0x1x1x0x0x64xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x56x56x1x3x3x1x512x4x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:1
2x512x56x56x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:3
2x512x56x56x1x3x3x1x512x8x1x1x0x2x2x0x1x1x0x0x32xNCHWxFP32xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x512x64x128x1x1x1x1x112x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x512x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x512x64x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x512x64x128x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x512x64x128x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x64x64x1x1x1x1x12x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x64x64x1x1x1x1x12x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x64x64x1x1x1x1x12x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x64x64x1x1x1x1x12x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x512x64x64x1x1x1x1x6x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x64x64x1x1x1x1x6x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:34
2x512x64x64x1x1x1x1x6x400x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x64x64x1x1x1x1x6x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x6x6x1x3x3x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x512x6x6x1x3x3x1x512x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Default, 16, 16, 2, 1, 8, 8, 1, 1>+1
2x512x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x512x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x512x7x7x1x1x1x1x2048x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x2048x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x512x7x7x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x512x7x7x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x7x7x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:19
2x512x7x7x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:30
2x512x7x7x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x7x7x1x1x1x1x2048x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x2048x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x512x7x7x1x1x1x1x512x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x7x7x1x1x1x1x512x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x7x7x1x1x1x1x512x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x512x7x7x1x1x1x1x512x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x1x1x1x512x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x7x7x1x3x3x1x256x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 64, 8, 8, Default, 16, 16, 4, 1, 8, 4, 1, 1>+1
2x512x7x7x1x3x3x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x512x7x7x1x3x3x1x512x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x12x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x7x7x1x3x3x1x512x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x7x7x1x3x3x1x512x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x56x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 128, 64, Default, 8, 8, 4>+1
2x512x7x7x1x3x3x1x512x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x7x7x1x7x7x1x4096x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x512x80x116x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x80x156x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x512x80x80x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:31
2x512x84x124x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x512x88x168x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x512x8x8x1x1x1x1x2048x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x512x8x8x1x1x1x1x2048x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x8x8x1x1x1x1x2048x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x8x8x1x1x1x1x2048x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x512x8x8x1x1x1x1x2048x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x8x8x1x1x3x1x256x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x512x8x8x1x1x3x1x256x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:24
2x512x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<256, 64, 256, 32, OddC, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x512x8x8x1x1x3x1x256x64x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x512x8x8x1x3x1x1x256x1x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x512x8x8x1x3x1x1x256x64x1x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x8x8x1x3x3x1x512x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x512x8x8x1x3x3x1x512x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x512x8x8x1x3x3x1x512x624x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x512x8x8x1x3x3x1x512x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x512x91x83x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x512x92x160x1x1x1x1x1024x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:38
2x512x96x140x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x512x99x167x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x512x9x41x1x5x5x1x256x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x512x9x9x1x3x3x1x512x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x512x9x9x1x3x3x1x512x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x528x14x14x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x528x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x528x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x528x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x528x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x528x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x528x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x528x14x14x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x528x14x14x1x1x1x1x160x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x528x14x14x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x528x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x528x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x528x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x528x14x14x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x528x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x528x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x528x14x14x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x528x14x14x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x528x14x14x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x528x14x14x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x528x14x14x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x528x14x14x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x528x14x14x1x1x1x1x32x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x528x14x14x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x528x14x14x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x528x14x14x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x528x14x14x1x1x1x1x32x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x528x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x528x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x528x4x4x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x528x4x4x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x528x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x528x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x528x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x544x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x544x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x544x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x544x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x544x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x544x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x54x1025x1025x1x3x3x1x54x1x0x0x0x2x2x0x1x1x0x0x54xNCHWxFP16xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
2x54x28x28x1x1x1x1x216x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:32
2x54x28x28x1x1x1x1x216x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:9
2x54x28x28x1x1x1x1x216x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:7;ConvBinWinogradRxSf3x2:7
2x54x28x28x1x1x1x1x216x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:20
2x54x29x29x1x3x3x1x54x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 32, 32, 32, Default, 8, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1>+1
2x54x55x55x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2
2x54x55x55x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x576x12x8x1x1x1x1x192x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x576x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x576x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x576x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x576x14x14x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x576x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x576x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x576x14x14x1x1x1x1x224x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x576x14x14x1x1x1x1x224x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x14x14x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x576x14x14x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x576x14x14x1x1x1x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x576x14x14x1x1x1x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x14x14x1x1x1x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x576x14x14x1x1x1x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x14x14x1x1x1x1x96x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x576x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x48x32x1x1x1x1x2048x12x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x576x4x4x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x576x4x4x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x576x69x69x1x3x3x1x576x4x0x0x0x1x1x0x2x2x0x0x576xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x576x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x576x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x576x7x7x1x1x1x1x160x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x576x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x576x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x58x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Filter1x1Stride1Pad0, 8, 1, 1>+1
2x58x28x28x1x1x1x1x58x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x58x28x28x1x1x1x1x58x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x58x28x28x1x1x1x1x58x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x58x28x28x1x1x1x1x58x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x58x28x28x1x3x3x1x58x1024x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:16
2x58x28x28x1x3x3x1x58x512x1x1x0x1x1x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:6
2x58x56x56x1x3x3x1x58x1024x1x1x0x2x2x0x1x1x0x0x58xNCHWxFP32xF=ConvBinWinogradRxSf2x3:15;ConvBinWinogradRxSf3x2:16
2x5x10x10x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x5x10x10x1x3x3x1x3x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x5x10x10x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x5x225x225x1x3x3x1x64x25x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, OddC, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x608x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x608x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 64, 128, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x608x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x608x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x608x14x14x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x608x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x608x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x608x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x608x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x60x111x111x1x3x3x1x60x512x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x60x14x14x1x1x1x1x240x128x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:21;ConvBinWinogradRxSf3x2:9
2x60x14x14x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:10
2x60x14x14x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:10;ConvBinWinogradRxSf3x2:7
2x60x14x14x1x3x3x1x60x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:17
2x60x28x28x1x1x1x1x240x32x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:9
2x60x28x28x1x3x3x1x60x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x60x28x28x1x3x3x1x60x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x60x28x28x1x3x3x1x60x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x60x28x28x1x3x3x1x60x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x60x28x28x1x3x3x1x60x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x60x28x28x1x3x3x1x60x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x60x28x28x1x3x3x1x60x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x624x14x14x1x1x1x1x104x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:40;ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x624x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x624x14x14x1x3x3x1x624x64x1x1x0x1x1x0x1x1x0x0x624xNCHWxFP32xB=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:1
2x624x28x28x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x624x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x624x28x28x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x624x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x640x128x128x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:30;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x640x128x128x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 256, 64, 64, Default, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x640x128x128x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x640x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x640x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x640x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x640x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x640x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x640x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x640x32x32x1x1x1x1x1280x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x640x32x32x1x3x3x1x1280x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x640x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x640x64x64x1x3x3x1x640x2x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 128, 32, OddC, 16, 16, 4, 4, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x640x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x640x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x104x104x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x108x108x1x3x3x1x3x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x112x112x1x1x1x1x64x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x1x1x1x64x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x112x112x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x64x112x112x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x112x112x1x3x3x1x128x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x3x3x1x128x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x112x112x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x64x112x112x1x7x7x1x3x12x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x112x112x1x7x7x1x3x204x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x112x112x1x7x7x1x3x42x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x112x112x1x7x7x1x3x43x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x64x113x113x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x114x114x1x7x7x1x3x16x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x114x114x1x7x7x1x3x32x2x2x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x114x114x1x7x7x1x3x64x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x64x115x115x1x7x7x1x3x256x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x64x115x115x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x117x117x1x7x7x1x3x1x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:25
2x64x117x117x1x7x7x1x3x8x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:36
2x64x12x12x1x3x3x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:22;ConvBinWinogradRxSf3x2:36
2x64x13x13x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x64x13x13x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x13x13x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x13x13x1x1x1x1x256x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x13x13x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x64x13x13x1x1x1x1x512x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x64x13x13x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x64x13x13x1x1x1x1x512x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:32
2x64x13x13x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x13x13x1x3x3x1x256x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x13x13x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x64x13x13x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x13x13x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x146x146x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x64x147x147x1x3x3x1x32x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x64x147x147x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x147x147x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x147x147x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x147x147x1x3x3x1x96x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x147x147x1x3x3x1x96x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x147x147x1x7x7x1x3x120x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x64x14x14x1x1x1x1x192x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:14;ConvBinWinogradRxSf3x2:18
2x64x14x14x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x14x14x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmXdlUniversal<MNKPadding, CRR> BlkSize: 128, BlkTile: 16x128x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2, BlkGemmPipelinePrefetchStages: 2>+1
2x64x14x14x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:24
2x64x14x14x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x14x14x1x1x1x1x480x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x64x14x14x1x3x3x1x64x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x64x14x14x1x5x5x1x64x1x2x2x0x2x2x0x1x1x0x0x64xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x64x150x150x1x7x7x1x3x18x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x64x150x150x1x7x7x1x3x4x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40
2x64x150x150x1x7x7x1x3x56x3x3x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x160x192x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x64x168x224x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x64x168x240x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x64x168x272x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:9
2x64x168x304x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:36
2x64x176x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:31
2x64x184x168x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:7
2x64x184x296x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:19;ConvBinWinogradRxSf3x2:21
2x64x184x320x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:7
2x64x192x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:33
2x64x19x19x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x1x1x1x1x1x1x128x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x1x1x1x1x1x1x1x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x64x200x216x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x64x200x216x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x64x200x272x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:10
2x64x208x192x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:30
2x64x209x209x1x3x3x1x128x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x64x209x209x1x3x3x1x128x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x218x218x1x11x11x1x3x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:11;ConvBinWinogradRxSf3x2:5
2x64x224x200x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:22
2x64x224x224x1x3x3x1x3x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x224x224x1x3x3x1x3x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x224x224x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40
2x64x224x224x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x224x224x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x224x224x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x64x224x224x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x225x225x1x3x3x1x13x11x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x225x225x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x64x232x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x64x24x16x1x1x1x1x192x33x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x256x184x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x64x256x256x1x1x1x1x1x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 32, 32, Filter1x1Stride1Pad0, 16, 16, 4, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x256x256x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x256x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x256x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x256x1x1x1x1x256x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x256x256x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x256x256x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x256x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x64x256x256x1x1x1x1x64x6x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x256x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x256x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x256x256x1x3x3x1x64x400x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x512x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x256x512x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x2624x1408x1x7x7x1x3x2x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x64x27x27x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x27x27x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x64x27x27x1x1x1x1x384x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x27x27x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x27x27x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x27x27x1x1x1x1x384x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x3x3x1x256x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x64x27x27x1x3x3x1x256x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x3x3x1x256x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x3x3x1x256x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x64x27x27x1x5x5x1x192x128x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x5x5x1x192x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x27x27x1x5x5x1x192x1x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x27x27x1x5x5x1x192x2048x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x5x5x1x192x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x5x5x1x192x512x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x5x5x1x192x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x27x27x1x5x5x1x192x8x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x64x280x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:20
2x64x288x200x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x64x28x28x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x64x28x28x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:12;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
2x64x28x28x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x28x28x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x64x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x64x296x176x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:34
2x64x312x168x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:17
2x64x312x200x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x64x319x383x1x7x7x1x3x2x2x2x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x64x320x320x1x3x1x1x64x1x1x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<64, 64, 32, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x64x336x184x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x64x336x192x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x64x35x35x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x64x35x35x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:17;ConvBinWinogradRxSf3x2:17
2x64x35x35x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x35x35x1x1x1x1x288x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x64x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x64x35x35x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x38x19x1x1x3x1x64x23x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x64x38x19x1x1x3x1x64x36x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x64x38x19x1x5x1x1x64x14x2x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x64x53x53x1x3x3x1x3x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, Filter1x1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x54x54x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x64x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x54x54x1x1x1x1x16x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x54x54x1x3x3x1x16x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x64x54x54x1x3x3x1x16x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x64x54x54x1x3x3x1x3x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x54x54x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x64x54x54x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x54x54x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x54x54x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x54x54x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x64x55x55x1x11x11x1x3x1024x3x3x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x55x55x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 32, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x64x55x55x1x1x1x1x16x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x55x55x1x1x1x1x16x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 32, 32, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x64x55x55x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x55x55x1x1x1x1x16x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x55x55x1x1x1x1x256x4x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 32, Default, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x64x55x55x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x64x55x55x1x3x3x1x128x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 64, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x55x55x1x3x3x1x3x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x56x56x1x11x11x1x3x4096x2x2x0x4x4x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x56x56x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x64x56x56x1x1x1x1x128x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x64x56x56x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x64x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x128x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 32, 128, 32, Filter1x1Stride1Pad0, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
2x64x56x56x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x256x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x256x256x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x256x2x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x64x56x56x1x1x1x1x256x312x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16
2x64x56x56x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x256x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x256x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x64x56x56x1x1x1x1x256x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x56x56x1x1x1x1x512x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:39
2x64x56x56x1x1x1x1x64x100x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 32, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x64x56x56x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x1x1x1x64x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x1x1x1x64x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x64x56x56x1x1x1x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x56x56x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x56x56x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x3x3x1x128x12x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x56x56x1x3x3x1x128x12x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x64x56x56x1x3x3x1x128x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x64x56x56x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x56x56x1x3x3x1x128x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x64x56x56x1x3x3x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x3x3x1x192x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x3x3x1x192x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x64x56x56x1x3x3x1x192x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x3x3x1x192x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x56x56x1x3x3x1x192x352x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:35;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x56x56x1x3x3x1x192x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x3x3x1x192x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x3x3x1x192x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x56x56x1x3x3x1x64x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x64x56x56x1x3x3x1x64x16x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x56x56x1x3x3x1x64x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x64x56x56x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x56x56x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x56x56x1x3x3x1x64x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x64x56x56x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x56x56x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x56x56x1x3x3x1x64x64x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x64x56x56x1x3x3x1x64x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x64x57x57x1x11x11x1x3x16x4x4x0x4x4x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x64x57x57x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x57x57x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x57x57x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x64x57x57x1x1x1x1x256x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x57x57x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x64x57x57x1x1x1x1x256x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x57x57x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x57x57x1x1x1x1x64x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x64x57x57x1x1x1x1x64x48x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x57x57x1x1x1x1x64x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x57x57x1x3x3x1x64x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:23
2x64x57x57x1x3x3x1x64x48x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x6x60x1x3x3x1x128x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x6x60x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x64x6x60x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x64x6x60x1x3x3x1x128x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x64x71x77x1x3x3x1x64x32x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x64x73x73x1x1x1x1x80x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x73x73x1x1x1x1x80x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x73x73x1x1x1x1x80x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x73x73x1x1x1x1x80x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x73x73x1x1x1x1x80x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x73x73x1x1x1x1x80x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x73x73x1x1x7x1x64x16x0x3x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 64, Default, 16, 16, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x73x73x1x1x7x1x64x1x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x64x73x73x1x1x7x1x64x64x0x3x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x73x73x1x3x3x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x73x73x1x3x3x1x96x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x64x73x73x1x3x3x1x96x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x73x73x1x3x3x1x96x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x73x73x1x3x3x1x96x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x64x73x73x1x3x3x1x96x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x73x73x1x7x1x1x64x1x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x64x73x73x1x7x1x1x64x256x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>+1
2x64x73x73x1x7x1x1x64x64x3x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x75x75x1x1x1x1x128x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x75x75x1x3x3x1x128x112x1x1x0x2x2x0x1x1x0x0x1xNHWCxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x64x75x75x1x3x3x1x64x120x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x64x75x75x1x3x3x1x64x22x1x1x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x64x75x75x1x3x3x1x64x24x1x1x0x3x3x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x64x79x348x1x5x5x1x1x256x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x64x80x349x1x5x5x1x1x1x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x64x80x350x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x64x80x350x1x3x3x1x64x1024x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x64x80x350x1x3x3x1x64x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x80x350x1x3x3x1x64x4x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x80x350x1x3x3x1x64x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x80x350x1x5x5x1x128x128x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x64x80x350x1x5x5x1x128x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x64x80x350x1x5x5x1x128x8x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x672x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x672x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x672x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x672x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x672x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x672x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x672x28x28x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x672x48x32x1x1x1x1x576x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x672x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x672x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:28;ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x672x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x6x14x14x1x5x5x1x16x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:25
2x6x64x64x1x1x1x1x512x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:9;ConvBinWinogradRxSf3x2:6
2x704x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x704x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x704x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x704x7x7x1x1x1x1x1024x10x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x704x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x704x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x704x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x704x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x704x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x720x128x128x1x1x1x1x144x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Filter1x1Stride1Pad0, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x720x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x720x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:6
2x720x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x720x14x14x1x1x1x1x192x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x720x24x35x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:26
2x720x28x28x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x720x28x28x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
2x720x28x28x1x1x1x1x192x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x720x40x78x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:32
2x720x50x68x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:35
2x720x54x42x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:20
2x720x5x5x1x1x1x1x120x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:17;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x720x68x50x1x3x3x1x256x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:37;ConvBinWinogradRxSf3x2:38
2x720x92x120x1x3x3x1x256x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x72x28x28x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:27
2x72x28x28x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 32, 32, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x72x515x515x1x5x5x1x72x4x0x0x0x2x2x0x1x1x0x0x72xNCHWxFP16xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:8;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Default, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x72x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:37
2x72x56x56x1x3x3x1x72x64x1x1x0x1x1x0x1x1x0x0x72xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>+1
2x72x56x56x1x3x3x1x72x64x1x1x0x2x2x0x1x1x0x0x72xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x736x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 16, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
2x736x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x736x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x736x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x736x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x736x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x736x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x736x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x736x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:16;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
2x736x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x768x14x14x1x1x1x1x1024x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x768x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x768x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x768x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x768x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x14x14x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x768x14x14x1x1x1x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x768x14x14x1x3x3x1x768x32x1x1x0x1x1x0x1x1x0x0x768xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x768x17x17x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x17x17x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x768x17x17x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x768x17x17x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x17x17x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x768x17x17x1x1x1x1x160x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x17x17x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x768x17x17x1x1x1x1x160x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x17x17x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x17x17x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x768x17x17x1x1x1x1x192x84x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Filter1x1Pad0, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x768x17x17x1x3x3x1x160x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:40
2x768x1x1018x1x1x3x1x80x49x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:12
2x768x1x1028x1x1x3x1x768x24x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x1047x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18
2x768x1x104x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x1052x1x1x3x1x768x47x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x1052x1x1x3x1x80x47x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18
2x768x1x1095x1x1x1x1x768x22x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x1186x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16
2x768x1x1206x1x1x3x1x768x41x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x146x1x1x1x1x768x171x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x158x1x1x3x1x768x158x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x1647x1x1x3x1x768x30x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x165x1x1x1x1x768x151x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x167x1x1x3x1x768x149x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x176x1x1x3x1x768x284x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x179x1x1x3x1x768x140x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:16
2x768x1x184x1x1x3x1x768x135x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x196x1x1x3x1x768x127x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x207x1x1x3x1x768x121x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x248x1x1x1x1x768x101x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x768x1x2548x1x1x3x1x768x19x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x267x1x1x1x1x768x93x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x768x1x274x1x1x3x1x768x182x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x284x1x1x3x1x80x176x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:12
2x768x1x285x1x1x3x1x768x87x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x286x1x1x3x1x768x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Default, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x768x1x290x1x1x1x1x768x86x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:24;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x290x1x1x3x1x768x86x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x292x1x1x3x1x768x171x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x303x1x1x1x1x768x82x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:33;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x768x1x320x1x1x3x1x768x156x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x323x1x1x1x1x768x77x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x334x1x1x3x1x768x74x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x361x1x1x3x1x768x69x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x386x1x1x3x1x768x64x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x394x1x1x3x1x768x63x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x395x1x1x3x1x768x63x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x409x1x1x3x1x768x61x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x422x1x1x3x1x768x59x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x430x1x1x3x1x80x116x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:12
2x768x1x437x1x1x3x1x768x114x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x444x1x1x1x1x768x56x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:18;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x449x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x768x1x452x1x1x1x1x768x55x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x459x1x1x1x1x768x54x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x463x1x1x1x1x768x53x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x468x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:36;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x479x1x1x1x1x768x52x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x484x1x1x3x1x768x51x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x500x1x1x1x1x768x50x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x768x1x542x1x1x1x1x1536x46x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x547x1x1x3x1x768x45x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x552x1x1x3x1x80x90x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18
2x768x1x556x1x1x1x1x1536x45x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x556x1x1x3x1x768x44x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:36;ConvBinWinogradRxSf3x2:22
2x768x1x571x1x1x1x1x768x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:16;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x573x1x1x3x1x80x87x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13
2x768x1x578x1x1x3x1x768x86x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x587x1x1x3x1x768x42x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x58x1x1x3x1x768x434x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:39;ConvBinWinogradRxSf3x2:20
2x768x1x592x1x1x1x1x768x42x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x603x1x1x3x1x768x41x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, OddC, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x768x1x618x1x1x3x1x80x80x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13
2x768x1x619x1x1x1x1x768x40x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 8x8, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x628x1x1x1x1x768x39x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x768x1x643x1x1x3x1x768x38x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:12
2x768x1x670x1x1x3x1x768x37x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>+1
2x768x1x708x1x1x3x1x768x70x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x745x1x1x3x1x768x67x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x748x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:13
2x768x1x753x1x1x3x1x80x66x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18
2x768x1x781x1x1x3x1x768x32x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x802x1x1x3x1x768x31x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Default, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x768x1x840x1x1x1x1x768x29x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x866x1x1x3x1x80x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:24
2x768x1x90x1x1x1x1x1536x277x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x912x1x1x3x1x80x54x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:20;ConvBinWinogradRxSf3x2:18
2x768x1x92x1x1x1x1x1536x271x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x938x1x1x3x1x768x53x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x958x1x1x3x1x768x26x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, OddC, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x768x1x964x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x976x1x1x3x1x768x51x0x1x0x1x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x768x1x979x1x1x1x1x768x25x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x768x1x997x1x1x3x1x768x50x0x1x0x1x2x0x1x1x0x0x1xNCHWxFP16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x768x28x28x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x28x28x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x768x28x28x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x768x6x6x1x3x3x1x768x1x0x0x0x2x2x0x1x1x0x0x32xNCHWxFP32xB=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1
2x768x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x768x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x784x14x14x1x3x3x1x784x4x1x1x0x2x2x0x1x1x0x0x49xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<64, 32, 64, 32, Default, 8, 16, 16, 1, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x800x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x800x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x800x14x14x1x1x1x1x128x43x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x800x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x800x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:37
2x800x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x800x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x800x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x800x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x800x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x80x1x1372x1x1x3x1x768x36x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x1432x1x1x3x1x768x34x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x174x1x1x3x1x768x287x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x208x1x1x3x1x768x240x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x2372x1x1x3x1x768x21x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x423x1x1x3x1x768x118x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x562x1x1x3x1x768x88x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x642x1x1x3x1x768x77x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:38;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x745x1x1x3x1x768x67x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x866x1x1x3x1x768x57x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x895x1x1x3x1x768x55x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x1x929x1x1x3x1x768x53x0x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x80x28x28x1x1x1x1x256x156x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
2x80x28x28x1x1x1x1x256x235x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:26;ConvBinWinogradRxSf3x2:30
2x80x28x28x1x1x1x1x256x243x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:26
2x80x28x28x1x1x1x1x256x28x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x80x28x28x1x1x1x1x256x34x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x80x73x73x1x1x1x1x64x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 64, 64, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x80x73x73x1x3x3x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x80x73x73x1x3x3x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x80x73x73x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:22;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
2x80x73x73x1x3x3x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x80x73x73x1x3x3x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x80x73x73x1x3x3x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x80x73x73x1x3x3x1x192x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x816x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Default, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x816x14x14x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x816x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x816x14x14x1x1x1x1x192x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x81x28x28x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x824x64x64x1x1x1x1x4944x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<256, 64, 256, 32, Filter1x1Stride1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x832x14x14x1x1x1x1x1024x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 128, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x832x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x14x14x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x832x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x832x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x832x64x128x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x832x64x128x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x832x64x128x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x832x64x128x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x832x64x128x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x832x64x128x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x832x7x7x1x1x1x1x128x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:29
2x832x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x832x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x832x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:5
2x832x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x832x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x832x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x832x7x7x1x1x1x1x160x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x832x7x7x1x1x1x1x160x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x832x7x7x1x1x1x1x160x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x832x7x7x1x1x1x1x160x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x832x7x7x1x1x1x1x160x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x7x7x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x832x7x7x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x832x7x7x1x1x1x1x192x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x256x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x832x7x7x1x1x1x1x256x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x256x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x832x7x7x1x1x1x1x256x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x7x7x1x1x1x1x256x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x256x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x832x7x7x1x1x1x1x256x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x256x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x7x7x1x1x1x1x32x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x32x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:7
2x832x7x7x1x1x1x1x32x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x832x7x7x1x1x1x1x32x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x832x7x7x1x1x1x1x32x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x832x7x7x1x1x1x1x32x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x384x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x384x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x832x7x7x1x1x1x1x384x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x832x7x7x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 64, 32, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x832x7x7x1x1x1x1x384x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x7x7x1x1x1x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x832x7x7x1x1x1x1x384x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x832x7x7x1x1x1x1x384x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x48x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x48x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x48x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x832x7x7x1x1x1x1x48x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x832x7x7x1x1x1x1x48x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x1x1x1x48x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x1x1x1x48x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x832x7x7x1x5x5x1x128x1024x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x5x5x1x128x16x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:22
2x832x7x7x1x5x5x1x128x256x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x832x7x7x1x5x5x1x128x4x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:8
2x832x7x7x1x5x5x1x128x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x864x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x864x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x864x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x864x14x14x1x3x3x1x864x4x1x1x0x1x1x0x1x1x0x0x864xNCHWxFP16xF=ConvBinWinogradRxSf2x3:1;ConvBinWinogradRxSf3x2:1;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 16>
2x864x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:21
2x864x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x864x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x87x1x1x1x1x1x1x1044x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:21;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Filter1x1Pad0, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
2x88x28x28x1x1x1x1x24x20x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:33
2x88x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:5;ConvBinWinogradRxSf3x2:6
2x88x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:13;ConvBinWinogradRxSf3x2:5
2x896x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x896x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x896x14x14x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:26
2x896x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x896x59x91x1x1x1x1x2016x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x896x59x91x1x3x3x1x896x4x1x1x0x2x2x0x1x1x0x0x16xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
2x896x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x896x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:29;ConvBinWinogradRxSf3x2:28
2x896x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:10
2x896x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:24
2x896x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x8x1024x1024x1x3x3x1x8x4x1x1x0x1x1x0x1x1x0x0x8xNCHWxFP16xF=ConvBinWinogradRxSf2x3:8;ConvBinWinogradRxSf3x2:4;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 16, 16, Filter3x3, 16, 16, 4, 1, 4, 1, 1, 1, 1, 8>
2x912x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:11
2x912x14x14x1x1x1x1x192x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x928x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x928x14x14x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x928x14x14x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:20;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Filter1x1Stride1Pad0, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x928x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x928x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x928x7x7x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x928x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x960x128x128x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:26;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x960x128x128x1x3x3x1x320x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 256, 64, 64, OddC, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x960x14x14x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x960x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x960x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x960x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x960x14x14x1x1x1x1x192x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x960x14x14x1x1x1x1x192x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x960x14x14x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x960x256x256x1x3x3x1x960x1x1x1x0x2x2x0x1x1x0x0x120xNCHWxFP16xF=ConvBinWinogradRxSf2x3:2;ConvBinWinogradRxSf3x2:2;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
2x960x64x64x1x1x1x1x640x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x960x64x64x1x3x3x1x640x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:31;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, OddC, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x960x7x7x1x1x1x1x128x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x960x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x960x7x7x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x960x7x7x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x960x7x7x1x1x1x1x160x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x960x7x7x1x1x1x1x160x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:23;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>+1
2x960x7x7x1x1x1x1x240x16x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:5
2x960x7x7x1x1x1x1x240x1x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:3;ConvBinWinogradRxSf3x2:3
2x960x7x7x1x1x1x1x240x2x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:4;ConvBinWinogradRxSf3x2:5
2x960x7x7x1x1x1x1x240x512x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xF=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:21
2x960x7x7x1x1x1x1x240x8x0x0x0x1x1x0x1x1x0x0x3xNCHWxFP32xB=ConvBinWinogradRxSf2x3:6;ConvBinWinogradRxSf3x2:9
2x960x7x7x1x1x1x1x320x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x960x7x7x1x1x1x1x320x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x960x7x7x1x1x1x1x320x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x960x7x7x1x1x1x1x320x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x960x7x7x1x1x1x1x320x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x960x7x7x1x1x1x1x320x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x96x106x106x1x7x7x1x3x512x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>+1
2x96x109x109x1x7x7x1x3x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x96x109x109x1x7x7x1x3x42x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x96x112x112x1x3x3x1x192x4x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, OddC, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x112x112x1x7x7x1x3x128x3x3x0x2x2x0x1x1x0x0x1xNCHWxFP16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
2x96x14x14x1x1x1x1x384x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:28;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 128, 64, Filter1x1Stride1Pad0, 8, 8, 8>+1
2x96x14x14x1x1x1x1x480x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x14x14x1x1x1x1x576x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x14x14x1x1x1x1x576x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x96x14x14x1x1x1x1x576x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:32;ConvBinWinogradRxSf3x2:18;ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x32x128, WaveTile: 16x16, WaveMap: 2x1, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
2x96x14x14x1x1x1x1x576x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x96x14x14x1x1x1x1x576x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x14x14x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:25
2x96x14x14x1x3x3x1x208x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x14x14x1x3x3x1x208x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:19
2x96x14x14x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x96x14x14x1x3x3x1x208x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x24x16x1x1x3x1x96x5x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x96x24x16x1x3x1x1x96x20x4x0x0x1x1x0x4x4x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
2x96x24x16x1x3x1x1x96x2x2x0x0x1x1x0x2x2x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 128, 16, 64, OddC, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
2x96x28x28x1x3x3x1x128x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x28x28x1x3x3x1x128x16x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x96x28x28x1x3x3x1x128x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:16
2x96x28x28x1x3x3x1x128x256x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x28x28x1x3x3x1x128x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x96x28x28x1x3x3x1x128x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x28x28x1x3x3x1x128x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x96x28x28x1x3x3x1x32x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:25;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 64, 32, 64, Default, 8, 8, 8>+1
2x96x28x28x1x3x3x1x96x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:29
2x96x28x28x1x3x3x1x96x32x1x1x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x96x28x28x1x5x5x1x32x64x2x2x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 64, 32, 64, Default, 8, 8, 8>+1
2x96x294x294x1x3x3x1x64x64x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x96x31x31x1x3x3x1x96x1024x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xW=ConvBinWinogradRxSf2x3:12;ConvBinWinogradRxSf3x2:10
2x96x33x33x1x3x3x1x384x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:39
2x96x35x35x1x1x1x1x384x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x35x35x1x3x3x1x64x32x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:32
2x96x35x35x1x3x3x1x96x128x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x35x35x1x3x3x1x96x128x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x96x35x35x1x3x3x1x96x16x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x96x35x35x1x3x3x1x96x1x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:13
2x96x35x35x1x3x3x1x96x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:15
2x96x35x35x1x3x3x1x96x2x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x96x35x35x1x3x3x1x96x512x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x35x35x1x3x3x1x96x64x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x35x35x1x3x3x1x96x84x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:39;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, OddC, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x35x35x1x3x3x1x96x8x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x96x35x35x1x3x3x1x96x8x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP16xB=ConvBinWinogradRxSf3x2:37;ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 64, 64, 64, Default, 8, 8, 8>+1
2x96x48x32x1x1x1x1x288x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 64, 32, Filter1x1Pad0, 16, 16, 4, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x48x32x1x1x1x1x40x33x0x0x0x2x2x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>+1
2x96x48x32x1x1x1x1x48x36x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 48, 64, Filter1x1Stride1Pad0, 16, 16, 2, 3, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x48x32x1x1x3x1x96x1x0x1x0x1x1x0x1x1x0x0x1xNCHWxBF16xB=ConvHipImplicitGemmGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>+1
2x96x512x512x1x1x1x1x20x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:29;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 32, 64, Default, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x54x54x1x1x1x1x16x128x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x54x54x1x1x1x1x16x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x54x54x1x1x1x1x16x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x96x54x54x1x1x1x1x16x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:27
2x96x56x56x1x1x1x1x128x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x56x56x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x96x56x56x1x1x1x1x128x32x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x56x56x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:30
2x96x56x56x1x1x1x1x192x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x56x56x1x1x1x1x192x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:40;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 192, 32, Filter1x1Stride1Pad0, 16, 16, 2, 6, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x56x56x1x1x1x1x24x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x96x56x56x1x1x1x1x24x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x96x56x56x1x1x1x1x24x256x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:31
2x96x56x56x1x1x1x1x24x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x56x56x1x1x1x1x24x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x96x56x56x1x1x1x1x24x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:32;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<64, 64, 32, 32, Filter1x1Pad0, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
2x96x56x56x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:40
2x96x56x56x1x1x1x1x304x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:34;ConvBinWinogradRxSf3x2:32
2x96x64x128x1x3x3x1x208x1x1x1x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x96x69x69x1x3x3x1x96x32x0x0x0x2x2x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:38
2x96x71x71x1x3x3x1x64x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xW=ConvBinWinogradRxSf2x3:24;ConvBinWinogradRxSf3x2:13
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP16xF=ConvBinWinogradRxSf3x2:15;ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 32, 32, Default, 16, 16, 4, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x96x7x7x1x1x1x1x96x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x96x96x64x1x3x1x1x96x26x1x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xF=ConvHipImplicitGemmGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 96, 32, Default, 16, 16, 4, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
2x992x14x14x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:18
2x992x14x14x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x992x14x14x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:17
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxBF16xW=ConvHipImplicitGemmGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
2x992x14x14x1x1x1x1x128x512x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:32
2x992x14x14x1x1x1x1x128x8x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:28
2x992x7x7x1x1x1x1x128x16x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:20
2x992x7x7x1x1x1x1x128x1x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:14
2x992x7x7x1x1x1x1x128x2x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:9
2x992x7x7x1x1x1x1x128x4x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xF=ConvBinWinogradRxSf3x2:12
2x992x7x7x1x1x1x1x128x64x0x0x0x1x1x0x1x1x0x0x1xNCHWxFP32xB=ConvBinWinogradRxSf3x2:36
3x1024x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Filter1x1Pad0, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x1024x32x32x1x1x1x1x2048x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<256, 64, 256, 32, Filter1x1Stride1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x1024x32x32x1x3x3x1x1024x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 32, 64, 64, Default, 32, 32, 1, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v2>
3x1088x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 64, Filter1x1Stride1Pad0, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x116x32x32x1x1x1x1x116x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x1280x32x32x1x1x1x1x640x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x16x16x1x1x1x1x64x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<32, 16, 64, 64, Default, 8, 8, 8>
3x128x32x32x1x1x1x1x1600x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>
3x128x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>
3x128x32x32x1x1x1x1x1792x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>
3x128x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>
3x128x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x128x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x128x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+16
3x128x32x32x1x1x1x1x528x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x128x32x32x1x1x1x1x544x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x576x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 64, 64, Default, 16, 16, 2, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x128x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x128x32x32x1x1x1x1x768x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x800x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x1x1x896x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x128x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x128x32x32x1x3x3x1x128x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle_V3_Large_Tensor<256, 128, 128, Default, 16, 16, 4, 2, 8, 8, 1, 1, 1>
3x128x32x32x1x3x3x1x128x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x128x32x32x1x3x3x1x128x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 64, Default, 16, 16, 4, 2, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x128x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x1296x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x1536x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, OddC, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x160x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x16x128x128x1x1x1x1x16x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Filter1x1Stride1Pad0, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x16x130x130x3x3x3x3x384x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x16x32x32x1x1x1x1x480x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 32, 128, 32, Default, 32, 32, 1, 2, 8, 8, 8, 1, 1, 1>
3x16x480x640x1x1x1x1x16x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x16x480x640x1x1x1x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x16x480x640x1x3x3x1x3x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x10x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x16x480x640x1x3x3x1x3x12x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x192x256x256x1x1x1x1x384x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x192x258x258x3x3x3x3x384x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 128, 32, Default, 16, 16, 4, 4, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x192x32x32x1x1x1x1x1056x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>
3x192x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
3x192x32x32x1x1x1x1x1152x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
3x192x32x32x1x1x1x1x1440x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 32x96x64, WaveTile: 16x16, WaveMap: 2x3, VmemReadVec: 4x6, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
3x192x32x32x1x1x1x1x1584x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 64, BlkTile: 64x64x64, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
3x192x32x32x1x1x1x1x1872x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>
3x192x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Filter1x1Pad0, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x192x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x192x32x32x1x1x1x1x912x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+4
3x192x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>
3x192x514x514x3x3x3x3x192x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x2048x32x32x1x1x1x1x320x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, Filter1x1Stride1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x2048x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, Filter1x1Stride1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x224x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>
3x224x32x32x1x1x7x1x192x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 64, 64, Default, 8, 8, 2>
3x224x32x32x1x1x7x1x224x256x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 256, 32, Filter1x1Stride1Pad0, 16, 16, 4, 4, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x232x32x32x1x1x1x1x232x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x256x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>
3x256x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 64, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x256x32x32x1x1x1x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x64, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x256x32x32x1x1x1x1x512x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x2048x256x36x36x0x1x1x1x36x36x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Default, 8, 8, 8>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle_V3_Large_Tensor<256, 128, 128, Default, 16, 16, 4, 2, 8, 8, 1, 1, 1>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 128, 128, 64, Default, 8, 8, 4>
3x256x32x32x1x3x3x1x384x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 64, 64, 32, Filter1x1Stride1Pad0, 16, 16, 1, 2, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x288x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x288x48x32x2x1x1x3x288x10x0x0x1x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x2x3x3x1x288x21x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 96, 32, Default, 16, 16, 4, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x288x48x32x2x3x3x1x288x33x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x288x48x32x4x1x1x2x288x8x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x20x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x288x48x32x4x3x3x1x288x4x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x4x3x3x1x288x5x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
3x288x48x32x4x3x3x1x288x7x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x288x48x32x8x1x1x2x288x29x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x1x1x2x288x4x0x0x0x1x1x2x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x2x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 64, 96, 64, Default, 16, 16, 2, 3, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x288x48x32x8x3x3x1x288x30x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x288x48x32x8x3x3x1x288x6x1x1x0x1x1x1x1x1x1x0x3xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
3x32x120x160x1x1x1x1x64x14x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 64, 64, Filter1x1Stride1Pad0, 8, 8, 2>
3x32x120x160x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Default, 16, 16, 8, 1, 8, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1024x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x15x15x1x3x3x1x3x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x16x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>
3x32x15x15x1x3x3x1x3x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x312x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x15x15x1x3x3x1x3x32x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x400x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x50x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x512x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x15x15x1x3x3x1x3x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x15x15x1x3x3x1x3x8x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x100x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x1024x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x16x16x1x3x3x1x3x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x16x16x1x3x3x1x3x128x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x12x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x1x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x16x16x1x3x3x1x3x4x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x16x16x1x3x3x1x3x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x16x16x1x3x3x1x3x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x17x17x1x3x3x1x3x128x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x18x18x1x3x3x1x3x100x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x128x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x12x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x1x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x204x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x208x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x18x18x1x3x3x1x3x48x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x512x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x64x3x3x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x6x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x18x18x1x3x3x1x3x8x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x240x320x1x2x2x1x32x10x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<32, 16, 64, 32, Default, 8, 16, 16, 1, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x32x240x320x1x2x2x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 32, 32, Default, 16, 16, 4, 1, 8, 8, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x32x240x320x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 8, 1, 1, 1>
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x1024x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x204x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x208x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x400x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x58x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x30x1x3x3x1x3x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x32x1x3x3x1x3x512x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x32x1x3x3x1x3x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x36x1x3x3x1x3x128x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x30x36x1x3x3x1x3x16x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x30x36x1x3x3x1x3x1x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x30x1x3x3x1x3x128x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x30x1x3x3x1x3x1x1x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x30x1x3x3x1x3x4x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x30x1x3x3x1x3x64x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x1x1x1x512x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x32x32x32x1x3x3x1x3x100x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x112x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x120x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x208x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x256x2x2x0x1x1x1x2x2x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x2x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x32x12x12x0x1x1x1x12x12x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x48x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x4x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x50x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x32x32x1x3x3x1x3x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x3x3x1x3x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x32x32x1x5x5x1x128x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x128x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x1x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x4x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x512x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x64x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x34x34x1x3x3x1x3x8x2x2x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x36x30x1x3x3x1x3x2x3x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x36x36x1x3x3x1x3x32x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 1, 1>
3x32x36x36x1x3x3x1x3x32x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x32x8x8x1x3x3x1x3x512x0x0x0x4x4x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>
3x32x9x9x1x3x3x1x3x8x2x2x0x4x4x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x340x32x32x1x3x3x1x256x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 4, 4, 1, 1>
3x352x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x384x130x130x3x3x3x3x384x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 128, 32, Default, 16, 16, 4, 4, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x384x258x258x3x3x3x3x384x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<128, 128, 128, 32, Default, 16, 16, 4, 4, 8, 8, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x384x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+64
3x384x32x32x1x1x1x1x48x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 32, 32, 128, 8, 8, Filter1x1Stride1Pad0, 16, 16, 2, 1, 8, 8, 1, 1>
3x3x15x15x1x3x3x1x4x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x3x32x32x1x11x11x1x64x256x0x0x0x4x4x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x100x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1024x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x112x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x114x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x114x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x120x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x120x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, OddC, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x128x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x128x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x128x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x16x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x16x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x16x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x19x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x19x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, OddC, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x1x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x204x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x24x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Default, 16, 16, 4, 2, 1, 1, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x24x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, OddC, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x2x2x2x0x1x1x1x2x2x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x32x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x32x0x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x32x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x48x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x4x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 32, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 1, BBlockTransferSrcScalarPerVector: 1
3x3x32x32x1x3x3x1x32x4x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x32x50x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x50x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x512x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x56x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x59x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x0x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x0x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x64x0x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x64x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x8x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Default, 16, 16, 4, 2, 1, 1, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x32x8x1x1x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 128, 128, 32, Default, 32, 32, 2, 2, 1, 1, 8, 1, 1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x3x32x32x1x3x3x1x64x256x1x1x0x2x2x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<64, 64, 64, 32, Default, 16, 16, 4, 2, 1, 1, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x3x480x640x1x3x3x1x16x14x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>
3x416x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x448x32x32x1x1x1x1x1280x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<Default, CRR> BlkSize: 64, BlkTile: 64x64x32, WaveTile: 16x16, WaveMap: 4x2, VmemReadVec: 4x4, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+1
3x448x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x48x32x32x1x5x5x1x16x256x2x2x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 32, 32, 8, 8, Default, 16, 16, 4, 1, 8, 1, 1, 1>
3x512x16x16x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
3x512x32x32x1x1x1x1x1000x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>
3x512x32x32x1x1x1x1x1024x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x512x32x32x1x1x1x1x1024x256x0x0x0x2x2x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<256, 64, 256, 32, Filter1x1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x512x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+128
3x512x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 64, 64, Default, 8, 16, 16, 2, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<256, 128, 256, 64, Filter1x1Stride1Pad0, 8, 8, 8>
3x512x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<128, 64, 128, 64, Filter1x1Stride1Pad0, 8, 16, 16, 2, 4> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x512x32x32x1x3x3x1x512x256x1x1x0x1x1x1x1x1x1x0x32xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Wmma_CShuffleV3<64, 64, 64, 64, Default, 8, 4, 2, 8, 8, 8, 8, 1, 1, 8, 1, 1>+1
3x512x32x32x1x3x3x1x512x256x1x1x0x2x2x1x1x1x1x0x32xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted_MergedGroups<256, 128, 32, 32, Default, 32, 32, 2, 1, 4, 4, 4, 1, 1, BlkGemmPipelineScheduler: Interwave, BlkGemmPipelineVersion: v1, 8>
3x544x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x54x32x32x1x1x1x1x216x256x0x0x0x1x1x1x1x1x1x0x3xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<256, 128, 128, 32, Filter1x1Stride1Pad0, 16, 16, 4, 2, 1, 1, 8, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 1, 1, 1, 1, 1, 1>
3x5x32x32x1x3x3x1x3x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x60x32x32x1x3x3x1x60x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<64, 64, 64, 32, 8, 8, Default, 16, 16, 4, 2, 1, 1, 1, 1>
3x64x120x160x1x1x1x1x32x12x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleD_Wmma_CShuffle<64, 32, 32, 64, Filter1x1Stride1Pad0, 8, 16, 16, 1, 2> AEnableLds: 1, BEnableLds: 1, ABlockTransferSrcScalarPerVector: 8, BBlockTransferSrcScalarPerVector: 8
3x64x15x15x1x7x7x1x3x256x2x2x0x2x2x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x64x16x16x1x7x7x1x3x256x3x3x0x2x2x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x64x32x32x1x1x1x1x16x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<256, 256, 128, 32, Default, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x256x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x64x32x32x1x1x1x1x288x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffleV3<128, 128, 64, 32, 8, 8, Filter1x1Stride1Pad0, 16, 16, 8, 1, 8, 1, 1, 1>
3x64x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x64x32x32x1x3x3x1x16x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_V3_WmmaPorted<128, 128, 16, 64, Default, 16, 16, 4, 1, 8, 8, 2, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v2>
3x64x32x32x1x3x3x1x64x256x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 64, 32, Default, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x64x60x80x1x3x3x1x64x1x1x1x0x1x1x1x1x1x1x0x1xNCDHWxFP16xB=ConvHipImplicitGemm3DGroupBwdXdlops:DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<64, 32, 64, 64, Default, 8, 8, 8>
3x672x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+8
3x720x32x32x1x1x1x1x192x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 64, 32, Filter1x1Stride1Pad0, 32, 32, 2, 2, 8, 8, 8, 1, 1, 1>
3x768x32x32x1x1x1x1x384x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<128, 128, 128, 32, Filter1x1Stride1Pad0, 32, 32, 4, 2, 8, 8, 8, 1, 1, 1>
3x80x32x32x1x1x1x1x64x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x32x64, WaveTile: 16x16, WaveMap: 1x2, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
3x896x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+32
3x96x1026x1026x3x3x3x3x3x1x0x0x0x1x1x1x1x1x1x0x1xNCDHWxBF16xF=ConvHipImplicitGemm3DGroupFwdXdlops:DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle_WmmaPorted<64, 64, 32, 32, Default, 32, 32, 2, 1, 8, 8, 1, 1, 1, 1>
3x96x32x32x1x7x7x1x3x256x3x3x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3<32, 16, 16, 32, Default, 8, 1, 1, 1, 4, 1, 4, 1, 1, 1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, 1>+1
3x992x32x32x1x1x1x1x128x256x0x0x0x1x1x1x1x1x1x0x1xNCDHWxFP16xW=ConvHipImplicitGemm3DGroupWrwXdlops:DeviceGroupedConvBwdWeight_Explicit_Xdl<DeviceBatchedGemmMultipleD_Wmma_CShuffleV3<MNKPadding, CRR> BlkSize: 256, BlkTile: 128x64x32, WaveTile: 16x16, WaveMap: 1x4, VmemReadVec: 1x1, BlkGemmPipelineScheduler: Intrawave, BlkGemmPipelineVersion: v1, BlkGemmPipelinePrefetchStages: 1>+-1
