ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-19 20:40:07 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,978 Commits 748 Branches 38 Tags
6111449cd61a0343595a9779b54ec1168e950dbd
Commit Graph

9 Commits

Author SHA1 Message Date
Khushbu Agarwal
7afee6c536 fix flatmm kernel for bigger size for fp16 datatype (#2302) 
[ROCm/composable_kernel commit: bd270fe4bc]
 2025-06-10 11:13:40 -07:00
Khushbu Agarwal
2b6621fba8 Rotating buffer PR CI fix (#2257) 
* Revert "Revert "[CK_tile] Add rotating buffer feature for universal gemm (#2200)" (#2256)"

This reverts commit 7baac527a1.

* fix regression

[ROCm/composable_kernel commit: 2e38eb4f1c]
 2025-06-02 10:25:01 -07:00
Illia Silin
7baac527a1 Revert "[CK_tile] Add rotating buffer feature for universal gemm (#2200)" (#2256) 
This reverts commit 0f77aa335d.

[ROCm/composable_kernel commit: bbdaf79a52]
 2025-05-28 09:46:52 -06:00
Khushbu Agarwal
0f77aa335d [CK_tile] Add rotating buffer feature for universal gemm (#2200) 
* Add rotating buffer feature for universal gemm

* adding changes in tile_engine

* Updated code to merge kernel_launch

* removing comments

* Enable rotating buffer changes to flatmm

* Created diff launch_kernel function for rotating buffer

* Simplfied calculation using macros

* merge code with new changes in tile_engine

* clang formatted

* Redefine macros

[ROCm/composable_kernel commit: 99857e10e6]
 2025-05-27 23:00:58 -07:00
Illia Silin
24057b3662 fix the buffer intrinsic names for clang >=20 (#2228) 
[ROCm/composable_kernel commit: 8146e471f1]
 2025-05-23 14:58:25 -07:00
Illia Silin
9c7b0a65f9 Revert "Update the buffer load/store intrinsic names for clang>=20. (#2192)" (#2227) 
This reverts commit 7d92e48278.

[ROCm/composable_kernel commit: 1b846143c6]
 2025-05-22 15:41:17 -07:00
Illia Silin
7d92e48278 Update the buffer load/store intrinsic names for clang>=20. (#2192) 
* fix the buffer load/store intrinsic names

* fix clang format

[ROCm/composable_kernel commit: 58f9e9ffbc]
 2025-05-13 10:18:14 -07:00
BingYuan.Zhou
977b7d0928 Flatmm merge (#2168) 
* sync with function interface of cshuffleepiloge,fix flatmm build fail

* move code from solin/flatmm which add mfma16*16*32fp8 and optimize flatmm

---------

Co-authored-by: solin <bingzhou@amd.com>

[ROCm/composable_kernel commit: 6a3960c1e1]
 2025-05-08 12:59:57 +08:00
BingYuan.Zhou
4ec293cb4b [flatmm] implement basic fp16 flatmm (#2089) 
* [flatmm] implement basic fp16 flatmm

* fix CI build fail

---------

Co-authored-by: root <root@hjbog-srdc-50.amd.com>
Co-authored-by: solin <bingzhou@amd.com>

[ROCm/composable_kernel commit: eaf1f0bf3b]
 2025-04-16 16:51:17 +08:00