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: improve memory management safety for aarch64 kernels #2038

Merged
merged 4 commits into from
Sep 3, 2024

Conversation

Permanence-AI-Coder
Copy link
Contributor

Description

The code changes in this PR were generated automatically by the Permanence AI Coder and reviewed by @fwph & @jweese. This PR updates memory allocation across several objects in the aarch64 implementation. Note that the bot is configured to add the DNNL_DISALLOW_COPY_AND_ASSIGN where it is missing; while this is redundant with the use of unique_ptr, it provides more consistency with existing code.

on-behalf-of: @permanence-ai github-ai@permanence.ai

General

  • Do all unit and benchdnn tests (make test and make test_benchdnn_*) pass locally for each commit?*
  • Have you formatted the code using clang-format?
  • note that on our build system (AWS graviton instance) the test 172 - test_benchdnn_modeC_brgemm_ci_cpu (Subprocess aborted) is failing both on this branch AND on the main branch.

@Permanence-AI-Coder Permanence-AI-Coder requested a review from a team as a code owner August 14, 2024 16:58
@vpirogov vpirogov added the platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64 label Aug 14, 2024
@vpirogov vpirogov added this to the v3.6 milestone Aug 14, 2024
Copy link
Contributor

@theComputeKid theComputeKid left a comment

Choose a reason for hiding this comment

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

I see some JIT failures that I did not expect to see (considering the contents of this change) - will look into this more.

Copy link
Contributor

@theComputeKid theComputeKid left a comment

Choose a reason for hiding this comment

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

Issue was unrelated. LGTM. Approved.

@theComputeKid
Copy link
Contributor

@vpirogov I don't know what is wrong with the bot, I approved the changes but it still shows as At least 2 approving reviews are required.

@dzarukin dzarukin merged commit 606c064 into uxlfoundation:main Sep 3, 2024
11 checks passed
@vpirogov
Copy link
Contributor

vpirogov commented Sep 3, 2024

@theComputeKid, nothing is wrong with the bot. The repo is configured to require 2 approvals for any PR per OpenSSF recommendation.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
platform:cpu-aarch64 Codeowner: @oneapi-src/onednn-cpu-aarch64
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants