Haocong WANG

[GEMM] Set enable-post-misched=0 as default compile option

5

This PR set "-mllvm -enable-post-misched=0" as default compile option of CK. This option will improve gemm_universal performance and ensure the correctness.

Fix set_slice_tile API and sequence hisogram function

1

## Proposed changes Please describe the motivation behind the pull request, whether it enables a new feature or fixes a bug. If there are associated pull requests or issues, please...

Update a8w8 kernel library Update flush cache timing api

Implement new data movement and mma layout inside universal gemm.

[CK_TILE] FMHA FWD Add TileSize kM0=64

2

## Proposed changes Add TileSize kM0=64 in fmha fwd kernel, for xformer medium size shape consuming ## Checklist Please put an `x` into the boxes that apply. You can also...

enable testing for all hdim supported in fmha_fwd

4

## Proposed changes Enable hdim=96/160/192 instances in fmha fwd and turn on tests for them. ## Checklist Please put an `x` into the boxes that apply. You can also fill...