Skip to content

GitLab

"include/vscode:/vscode.git/clone" did not exist on "f4d67cf8f5595b696a963c6064f62030b269d9c9"
Commit 2c5ad5b2 authored by Rosty Geyyer's avatar Rosty Geyyer
Browse files

Add debug info to DeviceGemmXdl_CShuffle and instances to gemm_add_add_fastgelu

parent f6224058
Hide whitespace changes
Inline Side-by-side
Showing with 224 additions and 81 deletions
include/ck/tensor_operation/gpu/device/device_gemm_multiple_d_xdl_cshuffle.hpp
View file @ 2c5ad5b2
...@@ -141,7 +141,8 @@ template <typename ALayout, ...@@ -141,7 +141,8 @@ template <typename ALayout,
index_t CShuffleNXdlPerWavePerShuffle, index_t CShuffleNXdlPerWavePerShuffle,
typename CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, typename CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock,
index_t CDEBlockTransferScalarPerVector_NPerBlock, index_t CDEBlockTransferScalarPerVector_NPerBlock,
LoopScheduler LoopSched = make_default_loop_scheduler()> LoopScheduler LoopSched = make_default_loop_scheduler(),
index_t PipelineVersion = 1>
struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout, struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
BLayout, BLayout,
DsLayout, DsLayout,
...@@ -285,7 +286,8 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout, ...@@ -285,7 +286,8 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
CShuffleNXdlPerWavePerShuffle, CShuffleNXdlPerWavePerShuffle,
CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock, CDEBlockTransferClusterLengths_MBlock_MPerBlock_NBlock_NPerBlock,
CDEBlockTransferScalarPerVector_NPerBlock, CDEBlockTransferScalarPerVector_NPerBlock,
LoopSched>; LoopSched,
PipelineVersion>;
using AGridDesc_AK0_M_AK1 = remove_cvref_t<decltype( using AGridDesc_AK0_M_AK1 = remove_cvref_t<decltype(
GridwiseGemm::MakeDefaultAGridDescriptor_AK0_M_AK1(AGridDesc_M_K{}))>; GridwiseGemm::MakeDefaultAGridDescriptor_AK0_M_AK1(AGridDesc_M_K{}))>;
...@@ -573,6 +575,9 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout, ...@@ -573,6 +575,9 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
{ {
auto str = std::stringstream(); auto str = std::stringstream();
std::map<LoopScheduler, std::string> LoopSchedToString{
{LoopScheduler::Default, "Default"}, {LoopScheduler::Interwave, "Interwave"}};
// clang-format off // clang-format off
str << "DeviceGemmMultipleD_Xdl_CShuffle" str << "DeviceGemmMultipleD_Xdl_CShuffle"
<< "<" << "<"
...@@ -583,7 +588,11 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout, ...@@ -583,7 +588,11 @@ struct DeviceGemmMultipleD_Xdl_CShuffle : public DeviceGemmMultipleD<ALayout,
<< AK1 << ", " << AK1 << ", "
<< BK1 << ", " << BK1 << ", "
<< getGemmSpecializationString(GemmSpec) << getGemmSpecializationString(GemmSpec)
<< ">"; << ">"
<< " LoopScheduler: "
<< LoopSchedToString[LoopSched] << ", "
<< "PipelineVersion: "
<< PipelineVersion;;
// clang-format on // clang-format on
return str.str(); return str.str();
......
include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_d_xdl_cshuffle.hpp
View file @ 2c5ad5b2
...@@ -94,7 +94,7 @@ struct GridwiseGemmMultipleD_xdl_cshuffle ...@@ -94,7 +94,7 @@ struct GridwiseGemmMultipleD_xdl_cshuffle
using ThisThreadBlock = ThisThreadBlock<BlockSize>; using ThisThreadBlock = ThisThreadBlock<BlockSize>;
using GridwiseGemmPipe = remove_cvref_t<decltype( using GridwiseGemmPipe = remove_cvref_t<decltype(
GridwiseGemmPipeline_Selector<PipelineVersion, NumGemmKPrefetchStage>())>; GridwiseGemmPipeline_Selector<PipelineVersion, NumGemmKPrefetchStage, LoopSched>())>;
__host__ __device__ static constexpr auto GetABlockDescriptor_AK0PerBlock_MPerBlock_AK1() __host__ __device__ static constexpr auto GetABlockDescriptor_AK0PerBlock_MPerBlock_AK1()
{ {
......
library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instance.cpp
View file @ 2c5ad5b2
...@@ -38,26 +38,61 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa ...@@ -38,26 +38,61 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instances = using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_kn_mn_mn_mn_instances =
std::tuple< std::tuple<
// clang-format off // clang-format off
//##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| //##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| LoopScheduler| Pipeline|
//##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| //##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| | |
//##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| //##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| | |
//##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | //##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, // pipeline v1, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8> DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
// pipeline v1, 2 waves
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
// pipeline v2, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 2, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 2, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 2, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 2, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 2, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 2, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>
// clang-format on // clang-format on
>; >;
......
library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instance.cpp
View file @ 2c5ad5b2
...@@ -38,26 +38,61 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa ...@@ -38,26 +38,61 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instances = using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_km_nk_mn_mn_mn_instances =
std::tuple< std::tuple<
// clang-format off // clang-format off
//##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| //##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| LoopScheduler| Pipeline|
//##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| //##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| | |
//##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| //##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| | |
//##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | //##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, // pipeline v1, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 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> DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 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, LoopScheduler::Default, 1>,
// pipeline v1, 2 waves
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 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, LoopScheduler::Interwave, 1>,
// pipeline v2, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 2, 8, 32, 32, 2, 4, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 2, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 2, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 2, 8, 32, 32, 2, 2, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 2, 8, 32, 32, 2, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 2, 8, 32, 32, 1, 2, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Col, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 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, LoopScheduler::Default, 2>
// clang-format on // clang-format on
>; >;
......
library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instance.cpp
View file @ 2c5ad5b2
...@@ -38,26 +38,61 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa ...@@ -38,26 +38,61 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instances = using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_kn_mn_mn_mn_instances =
std::tuple< std::tuple<
// clang-format off // clang-format off
//##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| //##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| LoopScheduler| Pipeline|
//##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| //##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| | |
//##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| //##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| | |
//##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | //##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, // pipeline v1, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 2, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 2, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8> DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 1>,
// pipeline v1, 2 waves
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 2, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Interwave, 1>,
// pipeline v2, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 256, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 2, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 2, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 2, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 2, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<16,16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 1, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 2, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 2, 0, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Row, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 64, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8, LoopScheduler::Default, 2>
// clang-format on // clang-format on
>; >;
......
library/src/tensor_operation_instance/gpu/gemm_add_add_fastgelu/device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instance.cpp
View file @ 2c5ad5b2
...@@ -38,23 +38,52 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa ...@@ -38,23 +38,52 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instances = using device_gemm_add_add_fastgelu_xdl_c_shuffle_f16_f16_f16_f16_f16_mk_nk_mn_mn_mn_instances =
std::tuple< std::tuple<
// clang-format off // clang-format off
//##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| //##############################| A| B| Ds| E| AData| BData| AccData| CShuffle| DsData| EData| A| B| CDE| GEMM| NumGemmK| 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| LoopScheduler| Pipeline|
//##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| //##############################| Layout| Layout| Layout| Layout| Type| Type| Type| DataType| Type| Type| Elementwise| Elementwise| Elementwise| Specialization| Prefetch| 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_MWaveMPerXdl| ScalarPerVector| | |
//##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| //##############################| | | | | | | | | | | 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_NWaveNPerXdl| _NWaveNPerXdl| | |
//##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | //##############################| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, // pipeline v1, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 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>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 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>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 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>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 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, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8>, DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 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>, 8> DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8, LoopScheduler::Default, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 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>, 8, LoopScheduler::Default, 1>,
// pipeline v1, 2 waves
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 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>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 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, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8, LoopScheduler::Interwave, 1>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 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>, 8, LoopScheduler::Interwave, 1>,
// pipeline v2, 1 wave
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 256, 32, 8, 8, 32, 32, 2, 4, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 128, 32, 8, 8, 32, 32, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 128, 32, 8, 8, 32, 32, 2, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 64, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 64, 128, 32, 8, 8, 32, 32, 2, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 64, 64, 32, 8, 8, 32, 32, 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>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 128, 64, 32, 8, 8, 32, 32, 2, 1, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 256, 64, 128, 32, 8, 8, 32, 32, 1, 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, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 128, 32, 32, 8, 8, 32, 32, 2, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 128, 32, 128, 32, 8, 8, 32, 32, 1, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, 1, 1, S<1, 16, 1, 8>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 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>, 8, LoopScheduler::Default, 2>,
DeviceGemmMultipleD_Xdl_CShuffle< Row, Col, Row_Row_Tuple, Row, F16, F16, F32, F32, F16_F16_Tuple, F16, PassThrough, PassThrough, AddAddFastGelu, GemmDefault, 1, 64, 32, 64, 32, 8, 8, 32, 32, 1, 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>, 8, LoopScheduler::Default, 2>
// clang-format on // clang-format on
>; >;
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment