Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

cpu: aarch64: fp16 postops: disable ACL post ops for fp16 #1506

Merged
merged 1 commit into from
Nov 23, 2022

Conversation

fadara01
Copy link
Contributor

Description

The oneDNN API specifies that post ops need to (always) be executed in fp32, but ACL executes them in f16 (when running in fp16 mode) which caused a lot of conv+relu benchdnn tests to fail.

Fixes # (#1499)

Checklist

General

  • [ YES ] Do all unit and benchdnn tests (make test and make test_benchdnn_*) pass locally for each commit?
  • [ YES ] Have you formatted the code using clang-format?

Performance improvements

  • [ N/A] Have you submitted performance data that demonstrates performance improvements?

New features

  • [ N/A] Have you published an RFC for the new feature?
  • [ N/A] Was the RFC approved?
  • [ N/A] Have you added relevant tests?

Bug fixes

  • [ YES] Have you included information on how to reproduce the issue (either in a github issue or in this PR)?
  • [ N/A] Have you added relevant regression tests?

The oneDNN API specifies that post ops need to (always)
be executed in fp32, but ACL executes them in f16
(when running in fp16 mode) which caused a lot of
conv+relu benchdnn tests to fail.
@vpirogov vpirogov added this to the v3.0 milestone Nov 23, 2022
@igorsafo igorsafo self-assigned this Nov 23, 2022
@igorsafo igorsafo merged commit 669e488 into oneapi-src:master Nov 23, 2022
@igorsafo
Copy link
Contributor

igorsafo commented Nov 23, 2022

Hi @fadara01 ,
The changes landed into rls-v2.7, rls-v3.0 and master. Thank you for your contribution!

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.

3 participants