Skip to content

GitLab

Commit 7a6c4b63 authored by Adam Osewski's avatar Adam Osewski
Browse files

Code formatting in example gemm direct c writeout.

parent 8812a11d
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 5 deletions
example/01_gemm/gemm_xdl_direct_c_write_out_fp16.cpp
View file @ 7a6c4b63
......@@ -28,18 +28,18 @@ static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpeci
static constexpr auto LoopSchedDefault = ck::LoopScheduler::Default;
static constexpr auto GemmPipeline = ck::PipelineVersion::v1;
using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemm_Xdl_DirectCWriteOut
using DeviceGemmDirectCWriteOut = ck::tensor_operation::device::DeviceGemm_Xdl_DirectCWriteOut
// clang-format off
// ######| ALayout| BLayout| CLayout| AData| BData| CData| AccData| 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| LoopScheduler| PipelineVersion|
// ######| | | | Type| Type| Type| Type| 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| | |
// ######| | | | | | | | Operation| Operation| Operation| | Stage| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | | |
// ######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
// < ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, 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, LoopSchedDefault, GemmPipeline>;
< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp, GemmDefault, 1, 64, 32, 32, 32, 8, 8, 32, 32, 1, 1, S<2, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<2, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, LoopSchedDefault, GemmPipeline>;
< ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, 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, LoopSchedDefault, GemmPipeline>;
// < ALayout, BLayout, CLayout, ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp, GemmDefault, 1, 64, 32, 32, 32, 8, 8, 32, 32, 1, 1, S<2, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<2, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, LoopSchedDefault, GemmPipeline>;
// clang-format on
// clang-format off
using DeviceGemmInstance1 = ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle
using DeviceGemmXdlCShuffle = 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| LoopScheduler| PipelineVersion|
// ######| | | | 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| | |
......@@ -47,7 +47,7 @@ using DeviceGemmInstance1 = ck::tensor_operation::device::DeviceGemm_Xdl_CShuffl
< 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, LoopSchedDefault, GemmPipeline>;
// clang-format on
using DeviceGemmInstance = DeviceGemmInstance;
using DeviceGemmInstance = DeviceGemmDirectCWriteOut;
using ReferenceGemmInstance = ck::tensor_operation::host::
ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
......
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