mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 21:21:22 +00:00
bba085d2b5
* refactor cmake files for the tests * refactor cmake files for examples * fix cmake for gemm example * fix the cmake file for all examples * add splitting by data types in gemm_splitk instance header * rename test to reflect only dl instances are used * clean up CI workspace, update cmake for instances * change the jenkinsfile syntax * build all instances except DL on gfx11 * move workspace cleanup after stages * clean up workspace after every stage * isolate data types in grouped_conv_fwd header * isolate dl instances for grouped_conv2d_fwd * fix syntax * fix cmake and batchnorm instances * fix typo * fix reduction instances * fix grouped_conv headers * fix syntax * replace parsing logic for instances, replace bfp16 with bf16 * fix the client examples build * clean up DTYPES from instances cmake files * update the parsing logic in cmake files * make an exception for reduction kernels * update few remaining cmake files to handle DTYPES * fix syntax * fix cmake conflicts * replace f8 with fp8 test name * resolve conflicts for dpp instances
60 lines
4.3 KiB
C++
60 lines
4.3 KiB
C++
#include <iostream>
|
|
#include <numeric>
|
|
#include <initializer_list>
|
|
#include <cstdlib>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
|
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
|
|
#include "ck/tensor_operation/gpu/device/impl/device_batched_gemm_multi_d_xdl.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
|
|
#include "ck/library/utility/check_err.hpp"
|
|
#include "ck/library/utility/device_memory.hpp"
|
|
#include "ck/library/utility/host_tensor.hpp"
|
|
#include "ck/library/utility/host_tensor_generator.hpp"
|
|
#include "ck/library/reference_tensor_operation/cpu/reference_batched_gemm.hpp"
|
|
#include "ck/library/utility/literals.hpp"
|
|
|
|
template <ck::index_t... Is>
|
|
using S = ck::Sequence<Is...>;
|
|
|
|
using BF16 = ck::bhalf_t;
|
|
using F32 = float;
|
|
|
|
using Row = ck::tensor_layout::gemm::RowMajor;
|
|
using Col = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
|
|
|
using ADataType = BF16;
|
|
using BDataType = BF16;
|
|
using AccDataType = F32;
|
|
using CShuffleDataType = BF16;
|
|
using DsDataType = ck::Tuple<>;
|
|
using EDataType = BF16;
|
|
|
|
using ALayout = Row;
|
|
using BLayout = Col;
|
|
using DsLayout = ck::Tuple<>;
|
|
using ELayout = Row;
|
|
|
|
using AElementOp = PassThrough;
|
|
using BElementOp = PassThrough;
|
|
using CDEElementOp = PassThrough;
|
|
|
|
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
|
|
|
|
// clang-format off
|
|
using DeviceGemmInstance = ck::tensor_operation::device::DeviceBatchedGemmMultiD_Xdl
|
|
//######| ALayout| BLayout| DsLayout| ELayout| 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|
|
|
//######| | | | | Type| Type| Type| DataType| 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| 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, DsLayout, ELayout, ADataType, BDataType, AccDataType, CShuffleDataType, DsDataType, EDataType, AElementOp, BElementOp, CDEElementOp, 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
|
|
|
|
#include "run_batched_gemm_example.inc"
|
|
|
|
int main(int argc, char* argv[]) { return !run_batched_gemm_example(argc, argv); }
|