You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
The text was updated successfully, but these errors were encountered:
annawoodard
changed the title
Running htex with TorqueProvider sets ppn=1
Running htex/exex with TorqueProvider hardcodes ppn=1
Dec 11, 2018
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.
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?
The text was updated successfully, but these errors were encountered: