mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 05:01:25 +00:00
60 lines
2.4 KiB
C++
60 lines
2.4 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved
|
|
|
|
#include "common.hpp"
|
|
|
|
#include "ck/tensor_operation/gpu/device/impl/device_gemm_xdl_cshuffle_streamk_v3.hpp"
|
|
|
|
using ADataType = ck::bhalf_t;
|
|
using BDataType = ck::bhalf_t;
|
|
using CDataType = ck::bhalf_t;
|
|
using AccDataType = float;
|
|
using CShuffleDataType = ck::bhalf_t;
|
|
|
|
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;
|
|
|
|
// clang-format off
|
|
using DeviceGemmV2_Streamk_Instance =
|
|
ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle_Streamk_V3<
|
|
ALayout, BLayout, CLayout,
|
|
ADataType, BDataType, CDataType, AccDataType, CShuffleDataType,
|
|
PassThrough, PassThrough, PassThrough, GemmDefault,
|
|
256,
|
|
128, 128,
|
|
64, 8, 8,
|
|
16, 16,
|
|
4, 4,
|
|
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
|
|
2, 8, 8, 0,
|
|
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
|
|
2, 8, 8, 0,
|
|
1, 2, S<1, 32, 1, 8>, 8,
|
|
ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3>;
|
|
// clang-format on
|
|
|
|
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_streamk_v2.inc"
|
|
|
|
int main(int argc, char* argv[]) { return !run_gemm_universal_streamk_example(argc, argv); }
|