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

MPI-aware threading defaults #198

Merged
merged 1 commit into from
Apr 20, 2023
Merged

MPI-aware threading defaults #198

merged 1 commit into from
Apr 20, 2023

Conversation

siboehm
Copy link
Member

@siboehm siboehm commented Apr 20, 2023

No description provided.

@siboehm siboehm enabled auto-merge April 20, 2023 16:46
@siboehm siboehm requested a review from rcoreilly April 20, 2023 17:00
@siboehm
Copy link
Member Author

siboehm commented Apr 20, 2023

Closes #197

Copy link
Member

@rcoreilly rcoreilly left a comment

Choose a reason for hiding this comment

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

This is only applicable for same-node mpi case.. better to not bake it in but rather set GOMAXPROCS externally based on the actual runtime configuration.

@siboehm
Copy link
Member Author

siboehm commented Apr 20, 2023

Related: emer/empi#11

@rcoreilly
Copy link
Member

the job submission script should know this.. Also, under SLURM used on many clusters, it automatically sets GOMAXPROCS based on actual allocated number of cores, so this calculation would be off there.

Overall, I think it is better to keep it simple in the axon code and leave this to the submission script.

@siboehm siboehm merged commit 1c1726b into master Apr 20, 2023
@siboehm siboehm deleted the siboehm/MPIHeuristics branch April 20, 2023 23:16
@etuleu
Copy link
Contributor

etuleu commented Apr 21, 2023

Sorry I wasn't aware there was a conversation still going on and I just approved the PR. Please decide what you want and do it! It's confusing as hell like this!

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