composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 18:17:44 +00:00

Files

Bartłomiej Kocot f14ee90152 [CK][CK Tile] Force padding for atomic_add bf16 C tensor (#5842 )

## Motivation

Force padding for atomic_add bf16 C tensor to avoid memfaults.

## Technical Details

- add global atomic add for bf16 and enable them
- add padding for atomic add bf16 due to the lack of oob
- remove padding for not continous dims in conv for other cases
- minor bwd data conv fixes

## Test Plan

test_grouped_conv_*_tile

## Test Result

pending

## Submission Checklist

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

2026-03-31 10:02:24 +02:00

mma

[CK_Tile] Refactor amdgcn_mma policy structs (#5272 )

2026-03-20 09:07:00 -06:00

amd_buffer_addressing_builtins.hpp

[CK][CK Tile] Force padding for atomic_add bf16 C tensor (#5842 )

2026-03-31 10:02:24 +02:00

amd_buffer_addressing.hpp

[CK][CK Tile] Force padding for atomic_add bf16 C tensor (#5842 )

2026-03-31 10:02:24 +02:00

amd_buffer_coherence.hpp

Update AMD buffer coherency (#3403 )