composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 02:02:46 +00:00

Files

Bartłomiej Kocot 9ad26943ac [CK][CK TILE] Improve oob check (#4791 )

## Motivation

Improve OOB checks. Remove permutes which have been generated by thread
buffer zero clear. at now in assembly there is only condmask instead of
permute + condmask.

Change number of KPack for generated instances

## Technical Details

Remove permute instructions from assembly

## Test Plan

test_grouped_convnd_fwd_tile

## Test Result

passed

## Submission Checklist

- [x] Look over the contributing guidelines at
https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.

---------

Co-authored-by: jakpiase <jakpia21@gmail.com>

2026-02-24 22:40:48 +01:00

mma

[CK_TILE] Fix MMA concepts compiler error (#4381 )

2026-02-06 16:26:57 -08:00

amd_buffer_addressing_builtins.hpp

[CK][CK TILE] Improve oob check (#4791 )

2026-02-24 22:40:48 +01:00

amd_buffer_addressing.hpp

[CK][CK TILE] Improve oob check (#4791 )

2026-02-24 22:40:48 +01:00

amd_buffer_coherence.hpp

Update AMD buffer coherency (#3403 )