mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
c544eb4da0
* init for reduce_threadwise multi_d * add reduce_threadwise_multi_d * add reduce_multi_d * clean * start add an other splitk device op * add reduce template parameter to SplitKBatchOffset * add reduce c matrix * clean up code * change example data type to bf16 * add bf16Ai8B example * remove reduce template parameter * add splitk atomic status to v4 * example add multi d parameters * device op add multi-d parameters * add multi-d to reduce * fix kbach=1 bug * change B layout to col in bf16Ai8B example * remove float adding struct * change multi-d interface * change file and class name * remove multi-d of bf16Ai8B example * change IsReduce function to IsReduceAdd * change example layout to RRR from RCR * according layout to set ds stride * reset parameter layout * add gemm universal reduce instance * add reduce factory * add profile_gemm_universal_reduce * add reduce to profiler * fix reduce instance * fix profiler reduce compiling bug * format * format library instance code * add mem instance for reduce library * fix call instance names * add workspace for reduce in ckProfiler * format * add mnpading to reduce library instance * add fp16 instance to reduce of profiler * change copyright time * restore profiler cmake file * add reduce text to instances * add DsLayout and DsDataType to instances template parameter * fixed gemm_reduce_multi_d * add an example without multi_d * Update common.hpp * Update gtest.cmake * Update gemm_xdl_splitk_reduce_bf16.cpp * clean * Update gtest.cmake * format * fixe api * format * default parameter change to RRR * add vector_len for multi_d * format * Update gtest.cmake * fix bf16A iBB elementwiseop * add ReduceDataType * move ReduceDataType to end position * format * remove googletest git method address * fix copyright time * update init data --------- Co-authored-by: root <jizhan@amd.com> Co-authored-by: letaoqin <letaoqin@amd.com> Co-authored-by: Jing Zhang <jizhan@meta.com> Co-authored-by: zjing14 <zhangjing14@gmail.com>
102 lines
3.0 KiB
C++
102 lines
3.0 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <cstdlib>
|
|
#include <iostream>
|
|
#include <initializer_list>
|
|
#include <numeric>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
|
|
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
#include "ck/utility/data_type.hpp"
|
|
|
|
#include "ck/library/utility/check_err.hpp"
|
|
#include "ck/library/utility/device_memory.hpp"
|
|
#include "ck/library/utility/fill.hpp"
|
|
#include "ck/library/utility/host_tensor.hpp"
|
|
#include "ck/library/utility/host_tensor_generator.hpp"
|
|
#include "ck/library/utility/literals.hpp"
|
|
#include "ck/library/reference_tensor_operation/cpu/reference_gemm.hpp"
|
|
#include "ck/library/reference_tensor_operation/cpu/reference_gemm_multiple_d.hpp"
|
|
|
|
struct ProblemSizeSplitK final
|
|
{
|
|
ck::index_t M = 256;
|
|
ck::index_t N = 1024;
|
|
ck::index_t K = 512;
|
|
|
|
ck::index_t StrideA = K;
|
|
ck::index_t StrideB = N;
|
|
ck::index_t StrideC = N;
|
|
|
|
ck::index_t KBatch = 2;
|
|
};
|
|
|
|
struct ExecutionConfig final
|
|
{
|
|
bool do_verification = true;
|
|
int init_method = 2;
|
|
bool time_kernel = true;
|
|
};
|
|
|
|
template <ck::index_t... Is>
|
|
using S = ck::Sequence<Is...>;
|
|
|
|
using Row = ck::tensor_layout::gemm::RowMajor;
|
|
using Col = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
|
using Add = ck::tensor_operation::element_wise::Add;
|
|
|
|
bool parse_cmd_args(int argc,
|
|
char* argv[],
|
|
ProblemSizeSplitK& problem_size,
|
|
ExecutionConfig& config)
|
|
{
|
|
if(argc == 1)
|
|
{
|
|
// use default case
|
|
}
|
|
else if(argc == 4)
|
|
{
|
|
config.do_verification = std::stoi(argv[1]);
|
|
config.init_method = std::stoi(argv[2]);
|
|
config.time_kernel = std::stoi(argv[3]);
|
|
}
|
|
else if(argc >= 10)
|
|
{
|
|
config.do_verification = std::stoi(argv[1]);
|
|
config.init_method = std::stoi(argv[2]);
|
|
config.time_kernel = std::stoi(argv[3]);
|
|
|
|
problem_size.M = std::stoi(argv[4]);
|
|
problem_size.N = std::stoi(argv[5]);
|
|
problem_size.K = std::stoi(argv[6]);
|
|
|
|
problem_size.StrideA = std::stoi(argv[7]);
|
|
problem_size.StrideB = std::stoi(argv[8]);
|
|
problem_size.StrideC = std::stoi(argv[9]);
|
|
|
|
if(argc >= 11)
|
|
{
|
|
problem_size.KBatch = std::stoi(argv[10]);
|
|
}
|
|
}
|
|
else
|
|
{
|
|
std::cerr << "arg1: verification (0=no, 1=yes)" << std::endl
|
|
<< "arg2: initialization (0=no init, 1=integer value, 2=decimal value)"
|
|
<< std::endl
|
|
<< "arg3: time kernel (0=no, 1=yes)" << std::endl
|
|
<< "arg4 to 9: M (256x), N(128x), K(32x), StrideA, StrideB, StrideC" << std::endl
|
|
<< "arg10: KBatch" << std::endl;
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|