Skip to content

Optimize _batched_lu_factor for dpnp.linalg.det/slogdet #2572

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 10 commits into from
Sep 18, 2025
Merged

Optimize _batched_lu_factor for dpnp.linalg.det/slogdet #2572

merged 10 commits into from
Sep 18, 2025

Conversation

vlad-perevezentsev
Copy link
Contributor

This PR suggests optimizing and simplifying _batched_lu_factor logic by replacing per-iteration allocations with a single preallocated buffer and batch-axis views which improves performance in dpnp.linalg.det and dpnp.linalg.slogdet

Results on pvc:
image

  • Have you provided a meaningful PR description?
  • Have you added a test, reproducer or referred to an issue with a reproducer?
  • Have you tested your changes locally for CPU and GPU devices?
  • Have you made sure that new changes do not introduce compiler warnings?
  • Have you checked performance impact of proposed changes?
  • Have you added documentation for your changes, if necessary?
  • Have you added your changes to the changelog?

@vlad-perevezentsev vlad-perevezentsev added this to the 0.19.0 release milestone Sep 2, 2025
@vlad-perevezentsev vlad-perevezentsev self-assigned this Sep 2, 2025
@github-actions GitHub Actions
Copy link
Contributor

github-actions bot commented Sep 2, 2025 •
edited
Loading

View rendered docs @ https://intelpython.github.io/dpnp/index.html

@github-actions GitHub Actions
Copy link
Contributor

github-actions bot commented Sep 2, 2025 •
edited
Loading

Array API standard conformance tests for dpnp=0.19.0dev4=py313h509198e_11 ran successfully.
Passed: 1227
Failed: 0
Skipped: 9

@coveralls
Copy link
Collaborator

coveralls commented Sep 2, 2025 •
edited
Loading

Coverage Status

coverage: 71.78% (+0.03%) from 71.755%
when pulling 2713230 on improve_perf_det_slogdet
into d289709 on master.

antonwolfy
antonwolfy reviewed Sep 4, 2025
View reviewed changes
antonwolfy
antonwolfy approved these changes Sep 8, 2025
View reviewed changes
Copy link
Contributor

@antonwolfy antonwolfy left a comment

Choose a reason for hiding this comment

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

LGTM! Thank you @vlad-perevezentsev

@vlad-perevezentsev vlad-perevezentsev merged commit 879a629 into master Sep 18, 2025
92 of 97 checks passed
@vlad-perevezentsev vlad-perevezentsev deleted the improve_perf_det_slogdet branch September 18, 2025 10:52
github-actions bot added a commit that referenced this pull request Sep 18, 2025
@github-actions
Optimize _batched_lu_factor for dpnp.linalg.det/slogdet (#2572)
ed4aa5d 
This PR suggests optimizing and simplifying `_batched_lu_factor` logic
by replacing per-iteration allocations with a single preallocated buffer
and batch-axis views which improves performance in `dpnp.linalg.det` and
`dpnp.linalg.slogdet` 879a629
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@antonwolfy antonwolfy antonwolfy approved these changes

@AlexanderKalistratov AlexanderKalistratov Awaiting requested review from AlexanderKalistratov

@vtavana vtavana Awaiting requested review from vtavana

@ndgrigorian ndgrigorian Awaiting requested review from ndgrigorian ndgrigorian is a code owner

Assignees

@vlad-perevezentsev vlad-perevezentsev

Labels
None yet
Projects
None yet
Milestone
0.19.0 release
Development

Successfully merging this pull request may close these issues.
3 participants
@vlad-perevezentsev @coveralls @antonwolfy