mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 14:11:29 +00:00
2327f1a640
* Add custom target to bundle examples together
* Add int4 example conditionally (just copy from int8 example)
* Extract common code into common.hpp
* Move ref gemm type alias into data-type-specific sources
* Add #error directive to prevent compile with wrong setting
* Let AddAddFastGelu support int4 parameter type
* Let check_err() support int4 parameter type
* Add wrapper function to hide value conversion while copying memory
* Finish int4 example for GEMM + AddAddFastGelu
* Add new DeviceMem API to copy memory
* Use new DeviceMem API to implement examples
* Fix wrongly use of macro 'CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4'
* Revert "Add new DeviceMem API to copy memory"
This reverts commit e26e7af71e.
* Add conversion ctor for Tensor<>
* Add 'const' specifier to Tensor<>::CopyAsType()
* Convert Tensor<> values before/after transfer between host & device
107 lines
3.1 KiB
C++
107 lines
3.1 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <algorithm>
|
|
#include <cstddef>
|
|
#include <iostream>
|
|
#include <stdexcept>
|
|
#include <string>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
|
#include "ck/tensor_operation/gpu/device/gemm_specialization.hpp"
|
|
#include "ck/tensor_operation/gpu/device/device_gemm_multiple_d_xdl_cshuffle.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
#include "ck/utility/data_type.hpp"
|
|
|
|
#include "ck/library/reference_tensor_operation/cpu/reference_gemm.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/utility/literals.hpp"
|
|
|
|
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 AddAddFastGelu = ck::tensor_operation::element_wise::AddAddFastGelu;
|
|
|
|
using BF16 = ck::bhalf_t;
|
|
using F16 = ck::half_t;
|
|
using F32 = float;
|
|
#ifdef CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4
|
|
using I4 = ck::int4_t;
|
|
#endif
|
|
using I8 = int8_t;
|
|
using I32 = int32_t;
|
|
|
|
struct ProblemSize final
|
|
{
|
|
ck::index_t M = 3840;
|
|
ck::index_t N = 4096;
|
|
ck::index_t K = 4096;
|
|
|
|
ck::index_t StrideA = 4096;
|
|
ck::index_t StrideB = 4096;
|
|
ck::index_t StrideD0 = 0;
|
|
ck::index_t StrideD1 = 4096;
|
|
ck::index_t StrideE = 4096;
|
|
};
|
|
|
|
struct ExecutionConfig final
|
|
{
|
|
bool do_verification = true;
|
|
int init_method = 1;
|
|
bool time_kernel = false;
|
|
};
|
|
|
|
inline bool
|
|
parse_cmd_args(int argc, char* argv[], ProblemSize& 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 == 12)
|
|
{
|
|
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.StrideD0 = std::stoi(argv[9]);
|
|
problem_size.StrideD1 = std::stoi(argv[10]);
|
|
problem_size.StrideE = std::stoi(argv[11]);
|
|
}
|
|
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 10: M (256x), N(128x), K(32x), StrideA, StrideB, StrideD0, StrideD1, "
|
|
"StrideE"
|
|
<< std::endl;
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|