Skip to content

D3D12 Swin kernels: weight staging stores the last chunk from several threads #118

Open

Description

@phantoslayer21

In the D3D12 Swin block template (clean/dx12/kernels/swin_block.hlsl, weight staging), when the number of 16-byte chunks is smaller than the thread count of the group, the threads past the last chunk all store that last chunk to the same groupshared addresses. The stored values are identical, and no wrong output has been observed, but the HIP version has exactly one writer per address and the D3D12 version should match it instead of relying on how the driver treats overlapping stores.

Applies to every channel count, including Model M's shipped kernels and the C = 32 block of Model L (#117).

Fix: in the partial row, store only when the thread's chunk index is below the chunk count; keep the barrier. Because this changes Model M's shader binaries, the change needs the bit-exact checks and the DXIL hash record redone for all kernels built from the template.

Found in review of #117. Refs #89

Activity

  1. added this to the 0.7.0 milestone on Nov 14, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions