ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 06:49:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

[CK_TILE] Split-K autodeduction (#3351)

Browse Source 
* 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 <>
This commit is contained in:
Ville Pietilä
2025-12-10 09:30:30 +02:00
committed by GitHub
parent 1aa93ef551
commit fc22320d78
11 changed files with 485 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/ck_tile/ops/grouped_convolution.hpp
View File

@@ -8,6 +8,7 @@
#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"