mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 01:10:17 +00:00
9e95d54cd2
* initial * Cmake file * successfull compilation but validation failed * Cmake * update * gpu validation * gemm universal * gemm universal sk update * sk bf16 universal instance * gemm_universal_streamk.hpp * only build for gfx94 * Cmakelist * profiler update, bf16 sk only works at gfx42 * clang * clang * clang all * no need flags * cmake script * delete comment * gemm universal sk fix * clang * profiler fix * clang * update * update * delete comment * code formatting * cmake * fix instance * clang * argument supported * argument supported and clang * update * fix * removing unnecessary comments * clang formatting * Update library/src/tensor_operation_instance/gpu/CMakeLists.txt Co-authored-by: afagaj <john.afaganis@gmail.com> * CopyRight Comment 2025 * clang reformatting * copy right 2025 --------- Co-authored-by: Emin Ozturk <ozturk.27@osu.edu> Co-authored-by: root <root@ctr-ubbsmc16.amd.com> Co-authored-by: Muhammed Emin Ozturk <meozturk@t004-008.hpcfund> Co-authored-by: root <root@splinter-126-wr-d3.amd.com> Co-authored-by: Muhammed Emin Ozturk <meozturk@t006-001.hpcfund> Co-authored-by: Muhammed Emin Ozturk <meozturk@login1.hpcfund> Co-authored-by: Muhammed Emin Ozturk <meozturk@t004-004.hpcfund> Co-authored-by: Emin Ozturk <emin.ozturk@utah.edu> Co-authored-by: Muhammed Emin Ozturk <meozturk@t008-001.hpcfund> Co-authored-by: afagaj <john.afaganis@gmail.com>
60 lines
5.5 KiB
C++
Executable File
60 lines
5.5 KiB
C++
Executable File
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#include "common.hpp"
|
|
|
|
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_streamk.hpp"
|
|
|
|
using ADataType = ck::half_t;
|
|
using BDataType = ck::half_t;
|
|
using AccDataType = float;
|
|
using CShuffleDataType = float;
|
|
using CDataType = ck::half_t;
|
|
|
|
using F16 = ck::half_t;
|
|
|
|
using ALayout = Row;
|
|
using BLayout = Row;
|
|
using CLayout = Row;
|
|
|
|
using AElementOp = PassThrough;
|
|
using BElementOp = PassThrough;
|
|
using CElementOp = PassThrough;
|
|
|
|
// clang-format off
|
|
using DeviceGemmStreamK = ck::tensor_operation::device::DeviceGemmXdlStreamK
|
|
// ######| AData| BData| CData| AccData| ALayout| BLayout| CLayout| A| B| C| Block| MPer| NPer| K0Per| 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| 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| | | | | | | | Wave| Wave| Lengths_K0_M_K1| ArrangeOrder| | | PerVector| PerVector_K1| | Lengths_K0_N_K1| ArrangeOrder| | | PerVector| PerVector_K1| | PerShuffle| PerShuffle| _NBlock_NWaveNPerXdl| _NWaveNPerXdl|
|
|
// ######| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
< ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementOp, BElementOp, CElementOp, 256, 128, 128, 4, 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>;
|
|
|
|
// < ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementOp, BElementOp, CElementOp, 256, 256, 128, 4, 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, 2, 1, 1, 1, S<1, 32, 1, 8>, 8>;
|
|
// < ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementOp, BElementOp, CElementOp, 128, 32, 64, 4, 8, 32, 32, 1, 1, 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, 16, 1, 8>, 8>;
|
|
// < ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout, AElementOp, BElementOp, CElementOp, 128, 32, 128, 4, 8, 32, 32, 1, 1, S<8, 16, 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, 2, 2, 1, 1, 1, S<1, 32, 1, 4>, 8>;
|
|
|
|
|
|
|
|
// // clang-format on
|
|
// clang-format on
|
|
|
|
using DeviceGemmInstance = DeviceGemmStreamK;
|
|
|
|
using ReferenceGemmInstance = ck::tensor_operation::host::
|
|
ReferenceGemm<ADataType, BDataType, CDataType, AccDataType, AElementOp, BElementOp, CElementOp>;
|
|
|
|
using ReferenceGemmInstanceGPU = ck::tensor_operation::device::ReferenceGemm<ALayout,
|
|
BLayout,
|
|
CLayout,
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
AccDataType,
|
|
AElementOp,
|
|
BElementOp,
|
|
CElementOp>;
|
|
|
|
#include "run_gemm_example.inc"
|
|
|
|
int main(int argc, char* argv[]) { return !run_gemm_streamk_example(argc, argv); }
|