mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
236f946292
* convnd_fwd fp16 example
* update example
* update example
* update instance
* updating refernce conv
* update reference conv
* update conv fwd profiler
* update conv 1d and 3d instance
* update include path
* clean
* update profiler for conv bwd data and weight
* update conv bwd weight
* clean
* update conv example
* update profiler for conv bwd weight
* update ckprofiler for conv bwd data
* fix reference conv bwd data bug; update conv bwd data test
* update examples
* fix initialization issue
* update test for conv fwd
* clean
* clean
* remove test case too sensitive to error threshhold
* fix test
* clean
* fix build
* adding conv multiple d
* adding conv multiple D
* add matrix padder
* add gemm padding to convnd
* adding group conv
* update gemm multi-d
* refactor
* refactor
* refactor
* clean
* clean
* refactor
* refactor
* reorg
* add ds
* add bias
* clean
* add G
* adding group
* adding group
* adding group
* update Tensor
* clean
* update example
* update DeviceGemmMultipleD_Xdl_CShuffle
* update conv bwd-data and bwd-weight
* upate contraction example
* update gemm and batch gemm with e permute
* fix example build
* instance for grouped conv1d
* update example
* adding group conv instance
* update gemm bilinear instance
* update gemm+add+add+fastgelu instance
* update profiler
* update profiler
* update test
* update test and client example
* clean
* add grouped conv into profiler
* update profiler
* clean
* add test grouped conv, update all conv test to gtest
* update test
[ROCm/composable_kernel commit: 500fa99512]
80 lines
3.1 KiB
C++
80 lines
3.1 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"
|
|
|
|
int main()
|
|
{
|
|
using ADataType = ck::half_t;
|
|
using BDataType = ck::half_t;
|
|
using CDataType = ck::half_t;
|
|
using AccDataType = float;
|
|
|
|
using Row = ck::tensor_layout::gemm::RowMajor;
|
|
using Col = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
|
|
|
auto test = [&](auto a_layout, auto b_layout, auto c_layout) {
|
|
bool pass = true;
|
|
|
|
using DeviceOp = ck::tensor_operation::device::DeviceGemm<decltype(a_layout),
|
|
decltype(b_layout),
|
|
decltype(c_layout),
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
PassThrough,
|
|
PassThrough,
|
|
PassThrough>;
|
|
|
|
const auto gemmPtrs =
|
|
ck::tensor_operation::device::instance::DeviceOperationInstanceFactory<
|
|
DeviceOp>::GetInstances();
|
|
|
|
for(auto& gemmPtr : gemmPtrs)
|
|
{
|
|
pass &= ck::gemm_util::TestGemm<std::unique_ptr<DeviceOp>,
|
|
ADataType,
|
|
BDataType,
|
|
CDataType,
|
|
AccDataType,
|
|
decltype(a_layout),
|
|
decltype(b_layout),
|
|
decltype(c_layout),
|
|
PassThrough,
|
|
PassThrough,
|
|
PassThrough>{}(gemmPtr);
|
|
}
|
|
|
|
return pass;
|
|
};
|
|
|
|
bool pass = test(Row{}, Row{}, Row{}) && test(Row{}, Col{}, Row{}) &&
|
|
test(Col{}, Row{}, Row{}) && test(Col{}, Col{}, Row{});
|
|
|
|
std::cout << "TestGemm ..... " << (pass ? "SUCCESS" : "FAILURE") << std::endl;
|
|
return pass ? 0 : 1;
|
|
}
|