mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 01:10:17 +00:00
75e622f02f
* universal streamk with atomics with ckprofiler support. grid_size and streamk strategy are tunable. grid_size of -1 leads to #WGs = maximum occupancy X num_CUs. implementation supports many different streamk policies: 1-tile, 2-tile, 3-tile and 4-tile. streamk strategy of -1 leads to default streamk policy (4-tile). * Update README.md * fixing clang-format issues * removed conflicts in struct members between streamk and universal streamk * corrected arg parsing for streamk and universal streamk * added stream-k policies for 3 tile and 4 tile * fixed argument type issue with parsing cmd args * changes suggested in PR review are made- removing comments and correcting copyright * file permissions updated * added default value support for grid_size and streamk-policy selection set to -1 * print messages for arguments * print messages for arguments * print messages for arguments1
49 lines
1.6 KiB
C++
49 lines
1.6 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2024, 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::half_t;
|
|
using BDataType = ck::half_t;
|
|
using AccDataType = float;
|
|
using CShuffleDataType = ck::half_t;
|
|
using CDataType = ck::half_t;
|
|
|
|
using ALayout = Row;
|
|
using BLayout = Row;
|
|
using CLayout = Row;
|
|
|
|
using AElementOp = PassThrough;
|
|
using BElementOp = PassThrough;
|
|
using CElementOp = PassThrough;
|
|
|
|
static constexpr auto GemmDefault = ck::tensor_operation::device::GemmSpecialization::MNPadding;
|
|
|
|
// 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,
|
|
224, 256,
|
|
64, 8, 2,
|
|
16, 16,
|
|
7, 8,
|
|
S<8, 32, 1>, S<1, 0, 2>, S<1, 0, 2>,
|
|
2, 8, 8, 0,
|
|
S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>,
|
|
1, 8, 2, 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>;
|
|
|
|
#include "run_gemm_example_streamk_v2.inc"
|
|
|
|
int main(int argc, char* argv[]) { return !run_gemm_universal_streamk_example(argc, argv); }
|