mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 09:16:52 +00:00
3af8c81a72
* added working example for 5D input using 1D kernel * example with 5D input tensor and 2d kernel - not working: issues with arguments * added updated version of 3d device op - changed descriptors/dims * added example file to check kernel * fixed descriptor and isSupportedArgument stride problem * added and modified kernel for 3d - updated tids/loop * adding some more 5d example files * fixed some issues * changes made for testing * working version: fixed error in stride for A, still a bit inefficient * cleaned up formatting/comments * updating formatting * more formatting fixes * fixing cmake, adding back gpu targets in cmake script * adding client example * added instances for client example * fixed errors in client example * implemented client ex with device_elementwise.hpp and device_elementwise_3d_impl.hpp * removed extra files * minor formatting and naming fixes * adding test files and profiler * fixing minor error * minor fix * removed unneccesary comments, renamed files * updated instance list for client example, added different layout example * removing instances * fixed error in instance generation * remove comments * update profiler and client example tensor layouts * fixed errors in test/profiler * updated vector dim access to enable vector load * updated test/profiler files * updated example with 1d kernel * updating profiler * renamed files --------- Co-authored-by: Jing Zhang <jizha@amd.com>
55 lines
1.5 KiB
C++
55 lines
1.5 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <string>
|
|
#include <sstream>
|
|
#include <tuple>
|
|
#include <vector>
|
|
#include <gtest/gtest.h>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
#include "ck/tensor_operation/gpu/device/tensor_layout.hpp"
|
|
#include "include/ck/utility/data_type.hpp"
|
|
#include "profiler/profile_transpose_impl.hpp"
|
|
|
|
namespace ck {
|
|
namespace test {
|
|
|
|
template <typename Tuple>
|
|
class TestTranspose : public testing::Test
|
|
{
|
|
using F32 = float;
|
|
|
|
protected:
|
|
using ADataType = std::tuple_element_t<0, Tuple>;
|
|
using BDataType = std::tuple_element_t<1, Tuple>;
|
|
|
|
public:
|
|
static constexpr bool verify_ = true;
|
|
static constexpr int init_method_ = 1; // decimal value initialization
|
|
static constexpr bool log_ = false;
|
|
static constexpr bool bench_ = false; // measure kernel performance
|
|
std::vector<std::vector<index_t>> lengths_ = {{16, 32, 16, 32, 16}, {16, 8, 16, 32, 8}};
|
|
|
|
void Run()
|
|
{
|
|
for(auto length : this->lengths_)
|
|
{
|
|
this->RunSingle(length);
|
|
}
|
|
}
|
|
|
|
void RunSingle()
|
|
{
|
|
bool pass = ck::profiler::profile_transpose_impl<ADataType, BDataType, 5>(
|
|
verify_, init_method_, log_, bench_, lengths_);
|
|
EXPECT_TRUE(pass);
|
|
}
|
|
};
|
|
|
|
} // namespace test
|
|
} // namespace ck
|