mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-19 22:39:03 +00:00
57106048ae
* 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>
42 lines
1.3 KiB
C++
42 lines
1.3 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#include <cstdlib>
|
|
|
|
#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/impl/device_gemm_xdl_cshuffle.hpp"
|
|
#include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
|
|
|
|
#include "ck/library/tensor_operation_instance/add_device_operation_instance.hpp"
|
|
|
|
namespace ck {
|
|
namespace tensor_operation {
|
|
namespace device {
|
|
namespace instance {
|
|
|
|
using F16 = ck::half_t;
|
|
using F32 = float;
|
|
|
|
using Row = ck::tensor_layout::gemm::RowMajor;
|
|
using Col = ck::tensor_layout::gemm::ColumnMajor;
|
|
|
|
template <ck::index_t... Is>
|
|
using S = ck::Sequence<Is...>;
|
|
|
|
using PassThrough = ck::tensor_operation::element_wise::PassThrough;
|
|
|
|
void add_gemm_f16_tn_256x256(std::vector<std::unique_ptr<BaseOperator>>& instances);
|
|
|
|
void add_gemm_f16_tn_256x128(std::vector<std::unique_ptr<BaseOperator>>& instances);
|
|
|
|
void add_gemm_f16_tn_128x128(std::vector<std::unique_ptr<BaseOperator>>& instances);
|
|
|
|
void add_gemm_f16_tn_128x64(std::vector<std::unique_ptr<BaseOperator>>& instances);
|
|
|
|
} // namespace instance
|
|
} // namespace device
|
|
} // namespace tensor_operation
|
|
} // namespace ck
|