ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-07-17 17:19:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge preshuffle device

Browse Source
This commit is contained in:
Ding, Yi
2025-05-28 07:02:28 +00:00
parent e2e0e0025e
commit 857ef9f8c4
10 changed files with 249 additions and 862 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
library/src/tensor_operation_instance/gpu/gemm_mx/device_gemm_mx_xdl_f4_f4_f16/device_gemm_mx_xdl_f4_f4_f16_mk_mfma_mn.hpp
View File

@@ -4,7 +4,7 @@
#include "ck/ck.hpp"
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3_mx_bpreshuffle.hpp"
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_v3_mx.hpp"
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
@@ -42,29 +42,29 @@ static constexpr auto ScaleBlockSize = 32;
template <BlockGemmPipelineScheduler BlkGemmPipeSched, GemmSpecialization GemmSpec>
using device_gemm_mx_xdl_f4_f4_f16_mk_mfma_mn_instances = std::tuple<
// clang-format off
//#################################| ALayout| BLayout| CLayout|AData| AScale|BData| BScale| CData| AccData| Cshuffle| A| B| C| GEMM| Scale Block| Block| MPer| NPer| KPer| AK1| BK1|MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Block-wiseGemm| Block-wiseGemm|
//#################################| | | | Type| Data| Type| Data| Type| Type| Type| Elementwise| Elementwise| Elementwise|Specialization| Size| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector| Pipeline| Pipeline|
//#################################| | | | | Type| | Type| | | | Operation| Operation| Operation| | | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl| Scheduler| Verision|
//#################################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 128, 128, 16, 16, 16, 16, 2, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 256, 128, 16, 16, 16, 16, 2, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 384, 128, 16, 16, 16, 16, 2, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 512, 128, 16, 16, 16, 16, 2, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
//#####################| ALayout| BLayout| CLayout|AData| AScale|BData| BScale| CData| AccData| Cshuffle| A| B| C| GEMM| Scale Block| Block| MPer| NPer| KPer| AK1| BK1|MPer| NPer| MXdl| NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle| CBlockTransferClusterLengths| CBlockTransfer| Block-wiseGemm| Block-wiseGemm|
//#####################| | | | Type| Data| Type| Data| Type| Type| Type| Elementwise| Elementwise| Elementwise|Specialization| Size| Size| Block| Block| Block| | | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector| Pipeline| Pipeline|
//#####################| | | | | Type| | Type| | | | Operation| Operation| Operation| | | | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl| Scheduler| Verision|
//#####################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 128, 128, 16, 16, 16, 16, 2, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 256, 128, 16, 16, 16, 16, 2, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 384, 128, 16, 16, 16, 16, 2, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 32, 512, 128, 16, 16, 16, 16, 2, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 128, 128, 16, 16, 16, 16, 4, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 256, 128, 16, 16, 16, 16, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 384, 128, 16, 16, 16, 16, 4, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 512, 128, 16, 16, 16, 16, 4, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 128, 128, 16, 16, 16, 16, 4, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 256, 128, 16, 16, 16, 16, 4, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 384, 128, 16, 16, 16, 16, 4, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 64, 512, 128, 16, 16, 16, 16, 4, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 128, 128, 16, 16, 16, 16, 6, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 256, 128, 16, 16, 16, 16, 6, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 384, 128, 16, 16, 16, 16, 6, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 512, 128, 16, 16, 16, 16, 6, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 128, 128, 16, 16, 16, 16, 6, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 256, 128, 16, 16, 16, 16, 6, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 384, 128, 16, 16, 16, 16, 6, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 96, 512, 128, 16, 16, 16, 16, 6, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 128, 128, 16, 16, 16, 16, 8, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 256, 128, 16, 16, 16, 16, 8, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 384, 128, 16, 16, 16, 16, 8, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3_BPreshuffle<Row, Col, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 512, 128, 16, 16, 16, 16, 8, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 128, 128, 16, 16, 16, 16, 8, 2, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 256, 128, 16, 16, 16, 16, 8, 4, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 384, 128, 16, 16, 16, 16, 8, 6, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
// DeviceGemmMX_Xdl_CShuffleV3<Row, MFMA, Row, F4, E8M0PK, F4, E8M0PK, F16, F32, F16, PassThrough, PassThrough, PassThrough, GemmSpec, ScaleBlockSize, 256, 128, 512, 128, 16, 16, 16, 16, 8, 8, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 16, 16, true, 2, 2, S<1, 32, 1, 8>, 8, BlkGemmPipeSched, BlockGemmPipelineVersion::v3>,
std::nullptr_t
// clang-format on
>;