Improve Windows threading performance scaling #4359
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thank you, looking great so far - including the msys2 runners with the LAPACK testsuite that was giving you grief the last time. |
|
Thank you, I've spent a fair amount of time working to better understand the code, both the win32 and *nix servers. I wrote my own test bed so that I could both iterate more quickly and test under stress. I am hopeful that I've got it sorted properly this time. |
|
Please see #4361 |
martin-frbg
reviewed
Dec 7, 2023
|
@mseminatore could you take a look at scipy/scipy#20294, where another library is also working with threads (maybe OpenMP?) and there seems to be a regression due to this PR |
This was referenced Aug 2, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I am making another attempt at improving the threading model for the Windows server, (see #4063). This PR passes the CTEST collateral included in the repo. Unfortunately, with changes to the GitHub workflows I can no longer test against the range of runners without submitting a PR.