Skip to content

perf(linalg): run SiLU through the fused FMA kernel on AVX-512 hosts - #2567

Draft
cverrier wants to merge 2 commits into
sonos:mainfrom
cverrier:perf/run-silu-through-fused-fma-on-avx512
Draft

perf(linalg): run SiLU through the fused FMA kernel on AVX-512 hosts#2567
cverrier wants to merge 2 commits into
sonos:mainfrom
cverrier:perf/run-silu-through-fused-fma-on-avx512

Conversation

@cverrier

@cverrier cverrier commented Aug 3, 2026

Copy link
Copy Markdown
Contributor

No description provided.

x86 hosts with AVX2+FMA but no AVX-512 ran SiLU through the generic
scalar kernel; they now get a vectorized one, which improves the
throughput. Accuracy follows the FMA sigmoid.
AVX-512 hosts ran silu_f32 and silu_f16 through a kernel composed over
the zmm sigmoid, which pays a scratch copy and an extra traversal that
the fused FMA kernel avoids. They now use the fused kernel at both
widths. The composed kernel has no remaining users, and is removed.
@cverrier
cverrier force-pushed the perf/run-silu-through-fused-fma-on-avx512 branch from 44655f7 to 94b0657 Compare August 4, 2026 15:53
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