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][ARM] Enable fast math in ACL deconvolution executor #26615

Merged

Conversation

alvoron
Copy link
Contributor

@alvoron alvoron commented Sep 16, 2024

Details:

  • ACL deconvolution fast_math option is enabled on PERFORMANCE mode.
  • This option enables fast math computation in ACL. In case this flag were set, ACL could dispatch the fastest implementation available which may introduce a drop of accuracy as well.
  • Accuracy testing on dataset subset highlights some deviations from reference values. Results are attached to the ticket.

Tickets:

@alvoron alvoron added the platform: arm OpenVINO on ARM / ARM64 label Sep 16, 2024
@alvoron alvoron requested review from a team as code owners September 16, 2024 13:14
@github-actions github-actions bot added the category: CPU OpenVINO CPU plugin label Sep 16, 2024
@@ -22,6 +22,9 @@ struct DeconvAttrs {
std::vector<ptrdiff_t> paddingR;
ov::CoordinateDiff outputPadding;
bool withBiasesParam = false;
#if defined(OV_CPU_WITH_ACL)
bool aclFastMath = false;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I would prefer to avoid backend specific params in common attributes structure.
Doesn't ACL Deconv Executor have direct access to GraphConfig?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It doesn't.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ok, I think we can merge this as temp solution, but in general it should be refactored.
I would expect to have some backend related properties inside ExecutorContext. @EgorDuplensky what is your opinion?

@dmitry-gorokhov dmitry-gorokhov added this to the 2024.5 milestone Oct 21, 2024
@dmitry-gorokhov dmitry-gorokhov added this pull request to the merge queue Oct 21, 2024
Merged via the queue into openvinotoolkit:master with commit d0056bd Oct 21, 2024
155 checks passed
@alvoron alvoron deleted the alvoron_enable_deconv_fast_math branch October 21, 2024 06:41
CuriousPanCake pushed a commit to CuriousPanCake/openvino that referenced this pull request Nov 6, 2024
…olkit#26615)

### Details:
- ACL deconvolution `fast_math` option is enabled on `PERFORMANCE` mode.
- This option enables fast math computation in ACL. In case this flag
were set, ACL could dispatch the fastest implementation available which
may introduce a drop of accuracy as well.
- Accuracy testing on dataset subset highlights some deviations from
reference values. Results are attached to the ticket.

### Tickets:
 - CVS-152534
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: CPU OpenVINO CPU plugin platform: arm OpenVINO on ARM / ARM64
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants