From f26e00e676ccaff4dd004cf77e5c417337937df9 Mon Sep 17 00:00:00 2001 From: kiefer Date: Thu, 25 Sep 2025 09:27:55 +0000 Subject: [PATCH] Extend scaleadd_ab instance lists --- ...d_wmma_cshufflev3_scaleadd_ab_instance.hpp | 87 ++++++++++--------- 1 file changed, 48 insertions(+), 39 deletions(-) diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp index de3ce2c5ce..83a2a2bc50 100644 --- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp +++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp @@ -40,63 +40,72 @@ template -using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_bf16_instances = std::tuple< - // clang-format off - //########################################| NumDim| A| B| Ds| E| AData| BData| AccData| CShuffle| Ds| EData| A| B| CDE| ConvForward| GEMM| NumGemmK| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MWmma| NWmma| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| - //########################################| Spatial| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| DataType| Type| Elementwise| Elementwise| Elementwise| Specialization| Specialization| Prefetch| Size| Block| Block| Block| | | WMMA| WMMA| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave| _MBlock_MWaveMPerWmma| ScalarPerVector| TODO: Other pipelines - //########################################| | | | | | | | | | | | Operation| Operation| Operation| | | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerWmma| _NWaveNPerWmma| - //########################################| | | | | | | | | | | | | | | | | TODO: ??| | | | | | | | | | | | | | | | | | | | | | | | | | | | | +using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_bf16_instances = + std::tuple< + // clang-format off + //########################################| NumDim| A| B| Ds| E| AData| BData| AccData| CShuffle| Ds| EData| A| B| CDE| ConvForward| GEMM| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MWmma| NWmma| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Pipeline scheduler | Pipeline version | + //########################################| Spatial| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| DataType| Type| Elementwise| Elementwise| Elementwise| Specialization| Specialization| Size| Block| Block| Block| | | WMMA| WMMA| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave| _MBlock_MWaveMPerWmma| ScalarPerVector| | | + //########################################| | | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerWmma| _NWaveNPerWmma| | | + //########################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | // generic instance - DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 64, 32, 8, 8, 16, 16, 4, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 64, 32, 8, 8, 16, 16, 4, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + #ifndef ONE_INSTANCE_PER_LIST + , // instances for small conv.K and conv.C - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 64, 64, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 4>, 1>, - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 32, 1, 8>, 8>, - - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8> - // clang-format on - >; + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3,ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 32, 32, 8, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3,ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 256, 128, 128, 32, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3,ELayout, ck::Tuple, ck::Tuple, F32, BF16, ck::Tuple<>, BF16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 256, 256, 128, 32, 8, 8, 16, 16, 8, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + #endif + // clang-format on + >; template -using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_f16_instances = std::tuple< - // clang-format off - //########################################| NumDim| A| B| Ds| E| AData| BData| AccData| CShuffle| Ds| EData| A| B| CDE| ConvForward| GEMM| NumGemmK| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MWmma| NWmma| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| - //########################################| Spatial| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| DataType| Type| Elementwise| Elementwise| Elementwise| Specialization| Specialization| Prefetch| Size| Block| Block| Block| | | WMMA| WMMA| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave| _MBlock_MWaveMPerWmma| ScalarPerVector| TODO: Other pipelines - //########################################| | | | | | | | | | | | Operation| Operation| Operation| | | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerWmma| _NWaveNPerWmma| - //########################################| | | | | | | | | | | | | | | | | TODO: ??| | | | | | | | | | | | | | | | | | | | | | | | | | | | | +using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_f16_instances = + std::tuple< + // clang-format off + //########################################| NumDim| A| B| Ds| E| AData| BData| AccData| CShuffle| Ds| EData| A| B| CDE| ConvForward| GEMM| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MWmma| NWmma| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Pipeline scheduler | Pipeline version | + //########################################| Spatial| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| DataType| Type| Elementwise| Elementwise| Elementwise| Specialization| Specialization| Size| Block| Block| Block| | | WMMA| WMMA| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave| _MBlock_MWaveMPerWmma| ScalarPerVector| | | + //########################################| | | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerWmma| _NWaveNPerWmma| | | + //########################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | // generic instance - DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 64, 32, 8, 8, 16, 16, 4, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 64, 32, 8, 8, 16, 16, 4, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + #ifndef ONE_INSTANCE_PER_LIST + , // instances for small conv.K and conv.C - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 64, 64, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 4>, 1>, - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 32, 1, 8>, 8>, - - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8> - // clang-format on - >; + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 32, 32, 8, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 256, 128, 128, 32, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, F32, F16, ck::Tuple<>, F16, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 256, 256, 128, 32, 8, 8, 16, 16, 8, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + #endif + // clang-format on + >; template -using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_int8_instances = std::tuple< - // clang-format off - //########################################| NumDim| A| B| Ds| E| AData| BData| AccData| CShuffle| Ds| EData| A| B| CDE| ConvForward| GEMM| NumGemmK| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MWmma| NWmma| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| - //########################################| Spatial| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| DataType| Type| Elementwise| Elementwise| Elementwise| Specialization| Specialization| Prefetch| Size| Block| Block| Block| | | WMMA| WMMA| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave| _MBlock_MWaveMPerWmma| ScalarPerVector| TODO: Other pipelines - //########################################| | | | | | | | | | | | Operation| Operation| Operation| | | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerWmma| _NWaveNPerWmma| - //########################################| | | | | | | | | | | | | | | | | TODO: ??| | | | | | | | | | | | | | | | | | | | | | | | | | | | | +using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_int8_instances = + std::tuple< + // clang-format off + //########################################| NumDim| A| B| Ds| E| AData| BData| AccData| CShuffle| Ds| EData| A| B| CDE| ConvForward| GEMM| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MWmma| NWmma| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Pipeline scheduler | Pipeline version | + //########################################| Spatial| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| DataType| Type| Elementwise| Elementwise| Elementwise| Specialization| Specialization| Size| Block| Block| Block| | | WMMA| WMMA| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MWmmaPerWave| NWmmaPerWave| _MBlock_MWaveMPerWmma| ScalarPerVector| | | + //########################################| | | | | | | | | | | | Operation| Operation| Operation| | | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerWmma| _NWaveNPerWmma| | | + //########################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | // generic instance - DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, int32_t, I8, ck::Tuple<>, I8, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 64, 32, 8, 8, 16, 16, 4, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, int32_t, I8, ck::Tuple<>, I8, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 64, 32, 8, 8, 16, 16, 4, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + #ifndef ONE_INSTANCE_PER_LIST + , // instances for small conv.K and conv.C - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, int32_t, int8_t, ck::Tuple<>, int8_t, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 64, 64, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 4>, 1>, - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, int32_t, int8_t, ck::Tuple<>, int8_t, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 32, 1, 8>, 8>, - - // DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle,ELayout, ck::Tuple, ck::Tuple, int32_t, int8_t, ck::Tuple<>, int8_t, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8> - // clang-format on - >; + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, int32_t, I8, ck::Tuple<>, I8, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 64, 64, 32, 32, 8, 8, 16, 16, 2, 2, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 16, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 4>, 1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, int32_t, I8, ck::Tuple<>, I8, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 256, 128, 128, 32, 8, 8, 16, 16, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 1, 1, 1, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, + DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3, ELayout, ck::Tuple, ck::Tuple, int32_t, I8, ck::Tuple<>, I8, ScaleAdd, ScaleAdd, PassThrough, ConvSpec, GemmMNKPadding, 256, 256, 128, 32, 8, 8, 16, 16, 8, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1> + #endif + // clang-format on + >; } // namespace instance } // namespace device