mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-16 02:54:21 +00:00
867bc90509
* Rename folder
* Add layernorm 4d fwd example
* Rename original layernorm example
* Add layernorm 4d f16 test
* Add layernorm4d_fwd client example
* Support layernorm4D in ckProfiler
* Rename groupnorm to groupnorm fwd in example
* Rename layernorm and group fwd in test
* Rename normalization to normalization_fwd (instances)
* Add fwd to DeviceNormalization
* Rename external api header
* Rename folder, because we can also add bwd in this folder
* Add fwd in layernorm and groupnorm (profiler
* Fix compile error
---------
Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
[ROCm/composable_kernel commit: a3d9a2cd42]
25 lines
899 B
C++
25 lines
899 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include <iostream>
|
|
#include <numeric>
|
|
#include <initializer_list>
|
|
#include <cstdlib>
|
|
#include <getopt.h>
|
|
|
|
#include "ck/ck.hpp"
|
|
#include "ck/utility/reduction_enums.hpp"
|
|
#include "ck/tensor_operation/gpu/device/impl/device_normalization_fwd_impl.hpp"
|
|
#include "ck/tensor_operation/gpu/device/impl/device_normalization_fwd_splitk_impl.hpp"
|
|
#include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
|
|
|
|
#include "ck/library/utility/fill.hpp"
|
|
#include "ck/library/utility/check_err.hpp"
|
|
#include "ck/library/utility/device_memory.hpp"
|
|
#include "ck/library/utility/host_common_util.hpp"
|
|
#include "ck/library/utility/host_tensor.hpp"
|
|
#include "ck/library/utility/host_tensor_generator.hpp"
|
|
#include "ck/library/reference_tensor_operation/cpu/reference_groupnorm.hpp"
|