mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 06:01:23 +00:00
fa2d894be1
* Add GEMM examples for int4 Currently the source files are just copied from int8 examples * Re-use pre-defined alias in int4 exmples * Distinguish user-side type from kernel-side type * Add int4_t support for check_err() * Allow conversion between Tensor<> specializations * Re-format source files * Use different type for host tensors * Re-use CopyAsType<>() to implement copy ctor * Re-use element-wise operation type alias * Fix typo in alias names * Complete the int4 examples * Add constraint to Tensor<> templated methods * Add type traits 'is_signed_integral<>' * Add type constraints for integer version check_err<>() * Allow comparing different-sized integral types in check_err() * Check converted Tensor<int4_t> with golden Tensor<int8_t> * Remove constraint of Tensor<>::CopyAsType() * Avoid compilation error while disabling ck::int4_t support * Remove debug messages * Add #error directive to prevent compile sources with wrong setting * Simplify tensor usages in examples * Add constraint to check_err() input reference type * Align design with other PR * Use ""_uz to simplify example code * Avoid too much generalizing check_err() * Re-format GEMM instance template arguments * Extract int4 example common codes * Sort include directives * Move #include directives into new header * Move common codes together * Re-format template argument in example code * Reuse same implementation code for most of GEMM examples * Re-format common.hpp * Unify structured comment in examples * Use reinterpret_cast<>() for cross-type pointer conversion * Revert "Add type traits 'is_signed_integral<>'" This reverts commitf2c148efae. * Allow unsigned integer arguments for check_err() * Fix compilation error in check_err() * Remove unnecessary copy ctor for Tensor<> * Mark Tensor<> special member functions as 'default' * Use more strict condition to add code in examples * Fix wrong program return value of GEMM examples * Handle the case while user specify all the strides * Fix never-ran examples * Exit successfully if GEMM instance does not support given problem * Add missing 'else' keyword * Re-format CMakeLists.txt * Add wrapper function to hide value conversion while copying memory * Add new DeviceMem API to copy memory * Use new DeviceMem API to implement examples * Revert "Add new DeviceMem API to copy memory" This reverts commit3f190b0779. * Add conversion ctor for Tensor<> * Write Tensor<> conversion logics explicitly in example code * Convert Tensor<> values after transfer data to host
90 lines
2.6 KiB
C++
90 lines
2.6 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, 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"
|
|
|
|
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 StrideC = 4096;
|
|
};
|
|
|
|
struct ExecutionConfig final
|
|
{
|
|
bool do_verification = true;
|
|
int init_method = 1;
|
|
bool time_kernel = false;
|
|
};
|
|
|
|
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;
|
|
|
|
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 == 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]);
|
|
}
|
|
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;
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|