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

Running htex/exex with TorqueProvider hardcodes ppn=1 #669

Open
annawoodard opened this issue Dec 2, 2018 · 3 comments
Open

Running htex/exex with TorqueProvider hardcodes ppn=1 #669

annawoodard opened this issue Dec 2, 2018 · 3 comments

Comments

@annawoodard
Copy link
Collaborator

This is related to #557 and #660.

We set it here. I'm not sure how to get around this without asking for the number of cores/node ahead of time. Maybe there is some PBS magic we can do to avoid setting it at all or set it to # of cores?

@annawoodard annawoodard changed the title Running htex with TorqueProvider sets ppn=1 Running htex/exex with TorqueProvider hardcodes ppn=1 Dec 11, 2018
@annawoodard
Copy link
Collaborator Author

Note that I think the main difficulty here stems from the fact that we use one parameter (tasks_per_node) to describe two things: 1) the number of loops the launcher executes and 2) the number of processes we plan to run on the node. I don't see an alternative except to add a second parameter to provider.submit. As a quick hack for the exex case, we can just set tasks_per_node=ranks_per_node-- this breaks the launcher, but that won't affect most configs, as we're currently recommending you usually use the SimpleLauncher with exex anyways.

@annawoodard
Copy link
Collaborator Author

Note this issue is critical to have exex work out-of-the-box on BW.

@benclifford
Copy link
Collaborator

crossref #3616

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants