mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-03-31 13:52:40 +00:00
4216d43da8
* WIP * Add Unit tests for the Multi Reduction Kernel * clang format * Rename multiblock to threadwise * Multiblock WIP * Fix multi reduce multi block unit tests * Multi Reduce Tile Engine: WIP * refactoring + try addressing precision error * Fix multiops examples * Cleanup * Clean up tile engine's reduce op * Update changelog * Fix remod/clang * Fix dates * Fix documentation & missing file * Fix comments * Use the update_tile api in the multi-block kernel * Unify threadwise/multiblock into a single kernel + default multiblock output to float in tests * Add TileParitioner * Cleanup * Add warning when no data to process, in the example * Refactoring Reduce kernel Tile Partioner + cleanup * Move the tile partioner to its own file * Add missing includes * Fix copyright header with update_amd_copyright_headers.py * Fix change of interface in Reduce2dProblem --------- Co-authored-by: Damien Lejeune <damien.lejeune@amd.com> Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
21 lines
1.0 KiB
C++
21 lines
1.0 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
#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/reduce/kernel/multi_reduce2d_kernel.hpp"
|
|
#include "ck_tile/ops/reduce/kernel/multi_reduce2d_multiblock_kernel.hpp"
|
|
#include "ck_tile/ops/reduce/kernel/multi_reduce2d_threadwise_kernel.hpp"
|
|
#include "ck_tile/ops/reduce/kernel/multi_reduce2d_tile_partitioner.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"
|
|
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
|
|
#include "ck_tile/ops/common/load_interleaved_pk_type.hpp"
|
|
#include "ck_tile/ops/common/streamk_common.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|
|
#include "ck_tile/ops/common/utils.hpp"
|