mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 12:41:26 +00:00
* Update include path to break the cyclic dep issue * Use ck_tile::permute_vectors_i4x4_b in tile engine --------- Co-authored-by: Damien Lejeune <damien.lejeune@amd.com> Co-authored-by: Adam Osewski <19374865+aosewski@users.noreply.github.com>
14 lines
573 B
C++
14 lines
573 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/ops/norm_reduce/block/block_norm_reduce.hpp"
|
|
#include "ck_tile/ops/norm_reduce/block/block_norm_reduce_problem.hpp"
|
|
#include "ck_tile/ops/norm_reduce/thread/thread_welford.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"
|