Qianfeng 3e0b77670e [CK_TILE] Improve headdim96 performance for fmha-bwd (#1573) ...

* Add kQKHeaddimForGemmN and kVHeaddimForGemmN in order to support headdim 96

* Remove the using of MakeKRegBlockDescriptor and MakeVRegBlockDescriptor

* Fix in bwd_piple_default_policy

* Remove kQKHeaddim and rename kQKHeaddimForGemmN to kQKHeaddim in the bwd kernel and pipelines

* Replace kVHeaddimForGemmN by kVHeaddim and kDoDvHeaddim

* Update to hd96 tile settings

* Add smoke test scripts for fmha-bwd hd96

* Revert "Add smoke test scripts for fmha-bwd hd96"

This reverts commit 7ca7e1a93d.

* Remove hd96 tile settings in fmha_bwd codegen to save compiling

* Fix lost code line in bwd_pipeline_default_policy

* Merge kDoDvHeaddim/kPadHeadDimDoDv to kVHeaddim/kPadHeadDimV and remove TileFmhaBwdTraits

* Rename KRegSliceBlockDescriptor/VRegSliceBlockDescriptor to KRegBlockDescriptor/VRegBlockDescriptor

* tiny adjustments

---------

Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com>
Co-authored-by: danyao12 <Dan.Yao@amd.com>

[ROCm/composable_kernel commit: 14c3cfb1c6]

2024-10-16 18:14:32 +08:00

..

ck

Add custom type vector support (#1333)

2024-10-14 11:56:45 -05:00

ck_tile

[CK_TILE] Improve headdim96 performance for fmha-bwd (#1573)

2024-10-16 18:14:32 +08:00