Files
composable_kernel/test/gemm/gemm_bf16.cpp
Anthony Chang 57106048ae Gemm standalone bench executable (#480)
* prototype

4 layouts

fix default stride

all problem sizes

tidy

move file

update build script

restore old file

fix build

* refactor standalone test to use gemm test harness

* simplify gemm test

* update build script

* remove redundant

* early return when cmd arg doesn't match

* tidy

* report failure when result not validated

* tidy

* Apply suggestions from code review

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>

Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
2022-10-27 12:25:12 -06:00

35 lines
1.0 KiB
C++

// SPDX-License-Identifier: MIT
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
#include <algorithm>
#include <cstdlib>
#include <iostream>
#include <numeric>
#include <tuple>
#include <vector>
#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.hpp"
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
#include "ck/library/tensor_operation_instance/gpu/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/reference_tensor_operation/cpu/reference_gemm.hpp"
#include "test/gemm/gemm_util.hpp"
using ADataType = ck::bhalf_t;
using BDataType = ck::bhalf_t;
using CDataType = ck::bhalf_t;
using AccDataType = float;
#include "run_gemm_test.inc"
int main() { return run_gemm_test(); }