Skip to content

GitLab

Commit 57a9b92a authored by M.Emin Ozturk's avatar M.Emin Ozturk
Browse files

clang

parent 58d75b7a
Hide whitespace changes
Inline Side-by-side
Showing with 29 additions and 9 deletions
example/01_gemm/gemm_xdl_bf16_streamk_v3.cpp 100755 → 100644
View file @ 57a9b92a
...@@ -23,14 +23,36 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa ...@@ -23,14 +23,36 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecializa
// // clang-format off // // clang-format off
// using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle // using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle
// // ######| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A| B| C| 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| // // ######| ALayout| BLayout| CLayout| AData| BData| CData| AccData| CShuffle| A|
// // ######| | | | Type| Type| Type| Type| DataType| Elementwise| Elementwise| Elementwise| Spacialization| 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| // B| C| GEMM| NumGemmK| Block| MPer| NPer| KPer| AK1| BK1| MPer| NPer| MXdl|
// // ######| | | | | | | | | 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| // NXdl| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer|
// // ######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | // ABlockTransfer| ABlockLds| BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer|
// < ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, CShuffleDataType, AElementOp, BElementOp, CElementOp, 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>; // BBlockTransfer| BBlockTransfer| BBlockLds| CShuffle| CShuffle|
// CBlockTransferClusterLengths| CBlockTransfer|
// // ######| | | | Type| Type| Type| Type| DataType|
// Elementwise| Elementwise| Elementwise| Spacialization| 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|
// // ######| | | | | | | | | | | | | |
// | | | | | | | | | | | | | | |
// | | | | | | | | |
// | | | |
// < ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType,
// CShuffleDataType, AElementOp, BElementOp, CElementOp, 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>;
// // clang-format on // // clang-format on
// clang-format off // clang-format off
using DeviceGemmV2_Streamk_Instance = using DeviceGemmV2_Streamk_Instance =
ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle_Streamk_V3< ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle_Streamk_V3<
...@@ -50,7 +72,6 @@ using DeviceGemmV2_Streamk_Instance = ...@@ -50,7 +72,6 @@ using DeviceGemmV2_Streamk_Instance =
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3>; ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3>;
// clang-format on // clang-format on
using ReferenceGemmInstance = ck::tensor_operation::host:: using ReferenceGemmInstance = ck::tensor_operation::host::
ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>; ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
......
example/01_gemm/run_gemm_example_streamk_v2.inc 100755 → 100644
View file @ 57a9b92a
...@@ -182,8 +182,7 @@ bool run_gemm(const ProblemType& problem_size, const ExecutionConfig& config) ...@@ -182,8 +182,7 @@ bool run_gemm(const ProblemType& problem_size, const ExecutionConfig& config)
std::cout << "b_k_n: " << b_k_n.mDesc << std::endl; std::cout << "b_k_n: " << b_k_n.mDesc << std::endl;
std::cout << "c_m_n: " << c_m_n_host_result.mDesc << std::endl; std::cout << "c_m_n: " << c_m_n_host_result.mDesc << std::endl;
//Added By Emin // Added By Emin
// Added By Emin // Added By Emin
......
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