mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 10:09:41 +00:00
d719c09343
* First version of split-K autodeduction.
* Fix circular dependency and kernel construction.
* Fix tolerance calculation for bwd weight example.
* Simplify kernel construction.
* Fix kernel launching bug for split-K autodeduce.
* Add split-K autodeduction support for the two stage example.
* Fix a corner case.
* Fix clang-format.
* Fix clang-format for inc files.
* Add missing header.
* Prevent too large split-K values.
* Fix formatting.
* Add unit tests for IsSupportedArgument in grouped bwd conv.
* clang-format.
* Fix merge conflicts.
* Address feedback from code review.
* clang-format
* Fix new tests after merge.
---------
Co-authored-by: Ville Pietilä <>
[ROCm/composable_kernel commit: fc22320d78]
20 lines
1.1 KiB
C++
20 lines
1.1 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/ops/grouped_convolution/kernel/grouped_convolution_backward_data_kernel.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/kernel/grouped_convolution_backward_weight_kernel.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/kernel/grouped_convolution_forward_kernel.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/utils/convolution_specialization.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/utils/grouped_convolution_utils.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/utils/split_k_utils.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/utils/transform_conv_bwd_data_to_gemm.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/utils/transform_conv_bwd_weight_to_gemm.hpp"
|
|
#include "ck_tile/ops/grouped_convolution/utils/transform_conv_fwd_to_gemm.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"
|