mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
6091458300
* add examples into grouped/batched_gemm * adding splitK examples * fixed splitK * add bfp16 int8 example into splitK * formatting * use static_cast * added common for batched_gemm * add commons for examples of splitK/batched/grouped_gemm * return true * adjust splitK check tol * update example Co-authored-by: Chao Liu <lc.roy86@gmail.com>
59 lines
4.0 KiB
C++
59 lines
4.0 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#include <iostream>
|
|
#include <numeric>
|
|
#include <initializer_list>
|
|
#include <cstdlib>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
|
|
#include "ck/tensor_operation/gpu/device/device_gemm_xdl_splitk_c_shuffle.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_gemm.hpp"
|
|
#include "ck/library/utility/literals.hpp"
|
|
|
|
template <ck::index_t... Is>
|
|
using S = ck::Sequence<Is...>;
|
|
|
|
using F16 = ck::half_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 = F32;
|
|
using BDataType = F32;
|
|
using AccDataType = F32;
|
|
using CDataType = F32;
|
|
|
|
using ALayout = Row;
|
|
using BLayout = Col;
|
|
using CLayout = Row;
|
|
|
|
using AElementOp = PassThrough;
|
|
using BElementOp = PassThrough;
|
|
using CElementOp = PassThrough;
|
|
|
|
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::Default;
|
|
|
|
using DeviceGemmInstance = ck::tensor_operation::device::DeviceGemmXdlSplitKCShuffle
|
|
// clang-format off
|
|
//######| AData| BData| CData| AccData| ALayout| BLayout| CLayout| A| B| C| GEMM| Block| MPer| NPer| KPer| K1| 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| Type| | | | Elementwise| Elementwise| Elementwise| Spacialization| Size| Block| Block| Block| | XDL| XDL| Per| Per| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraM| ThreadCluster| ThreadCluster| SrcAccessOrder| SrcVectorDim| SrcScalar| DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave| _MBlock_MXdlPerWave_MWaveMPerXdl| ScalarPerVector|
|
|
//######| | | | | | | | Operation| Operation| Operation| | | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NXdlPerWave_NWaveNPerXdl| _NWaveNPerXdl|
|
|
//######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementOp, BElementOp, CElementOp, GemmDefault, 256, 256, 128, 4, 4, 32, 32, 4, 2, S<1, 4, 64, 1>, S<0, 2, 1, 3>, S<0, 2, 1, 3>, 3, 4, 4, true, S<1, 4, 64, 1>, S<0, 1, 3, 2>, S<0, 1, 3, 2>, 3, 4, 4, true, 1, 1, S<1, 32, 1, 8>, 4>;
|
|
// clang-format on
|
|
|
|
#include "run_splitK_gemm_example.inc"
|
|
|
|
int main(int argc, char* argv[]) { return !run_splitK_gemm_example(argc, argv); }
|