Skip to content

Remove AVX file from aarch64 compilation#5458

Closed
Nicoshev wants to merge 1 commit into
pytorch:mainfrom
Nicoshev:export-D95431713
Closed

Remove AVX file from aarch64 compilation#5458
Nicoshev wants to merge 1 commit into
pytorch:mainfrom
Nicoshev:export-D95431713

Conversation

@Nicoshev

@Nicoshev Nicoshev commented Mar 6, 2026

Copy link
Copy Markdown
Contributor

Summary:
We are removing QuantUtilsAvx2.cc from fbgemm SVE compilation.

QuantUtilsAvx2.cc currently compiles for aarch64 using translation layers, which increase build times and can hide performance optimization opportunities.

Reviewed By: YifanYuan3

Differential Revision: D95431713

@meta-cla meta-cla Bot added the cla signed label Mar 6, 2026
@meta-codesync

meta-codesync Bot commented Mar 6, 2026

Copy link
Copy Markdown
Contributor

@Nicoshev has exported this pull request. If you are a Meta employee, you can view the originating Diff in D95431713.

Summary:
X-link: facebookresearch/FBGEMM#2430


We are removing QuantUtilsAvx2.cc from fbgemm SVE compilation.

QuantUtilsAvx2.cc currently compiles for aarch64 using translation layers, which increase build times and can hide performance optimization opportunities.

Reviewed By: YifanYuan3

Differential Revision: D95431713
@meta-codesync

meta-codesync Bot commented Mar 7, 2026

Copy link
Copy Markdown
Contributor

This pull request has been merged in 8d08cc1.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants