Skip to content

Conversation

usamoi
Copy link
Contributor

@usamoi usamoi commented Feb 19, 2025

  1. only check simd-related features when dispatching
  2. choose SVE implementation only if SVE bits >= 256
  3. choose SVE f16 sum_of_d2 and sum_of_xy implementation only if SVE bits >= 512

Signed-off-by: usamoi <usamoi@outlook.com>
Signed-off-by: usamoi <usamoi@outlook.com>
@usamoi usamoi merged commit 6309bf0 into tensorchord:main Feb 19, 2025
15 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant