mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-15 10:37:44 +00:00
b6f0e98da6
* General 2D Reduction Kernel
* Move the reduction kernel from the example
* Split the code and add the necessary policy, problem, shape files as
per ck_tile convention
* Add/modify the headers
* Modified the example to work with the 'new' kernel
* Added tests for the kernel
* N-D refernce reduce
* Added support for N-D input with transform to 2D
* Added padding to support various input sized tensors
* Bug fix in the thread buffer constructor
* Some comments to explain the reduce2d block kernel
* comments resolution
* clang-format
* comments resolution
* clang-format
* clang-format
* comments resolution
* clang-format
[ROCm/composable_kernel commit: 4750b293fe]
16 lines
683 B
C++
16 lines
683 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/ops/reduce/block/block_reduce.hpp"
|
|
#include "ck_tile/ops/reduce/block/block_reduce2d.hpp"
|
|
#include "ck_tile/ops/reduce/block/block_reduce2d_problem.hpp"
|
|
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|
|
#include "ck_tile/ops/common/utils.hpp"
|
|
#include "ck_tile/ops/reduce/kernel/reduce2d_kernel.hpp"
|
|
#include "ck_tile/ops/reduce/pipeline/reduce2d_default_policy.hpp"
|
|
#include "ck_tile/ops/reduce/pipeline/reduce2d_problem.hpp"
|
|
#include "ck_tile/ops/reduce/pipeline/reduce2d_shape.hpp"
|