mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-12 09:16:52 +00:00
ed3a2e5226
* Rename to proper naming * Add example of groupnorm + swish * Extract duplicate code in example * Add groupnorm + swish instances * Ractor instance generation, split into multiple cpp file * Add external api and client example * Refine profiler message * Use ck math version of exp * Refine problem size in example * Add host version of exp
24 lines
807 B
C++
24 lines
807 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2022, 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_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"
|