Skip to content

Conversation

@rhc54
Copy link
Contributor

@rhc54 rhc54 commented Aug 22, 2016

We previously counted each cpu against the #slots. However, IBM has pointed out that "slot" is equated to the number of processes allowed to run on each node, and not the number of cpus on the node. This has been a continuing source of confusion, so make the distinction a "hard" one.

Each process occupies a "slot". We automatically set #slots = #cpus if nothing else is told to us. If you want to run more procs than slots, you must tell us to allow oversubscription.

A process can utilize multiple pe's if that option is given. If you try to bind more than one proc to a given pe, then we will error out unless you tell us to allow overloading.

@markalle Please see if this matches your expectations.

…against the #slots. However, IBM has pointed out that "slot" is equated to the number of processes allowed to run on each node, and not the number of cpus on the node. This has been a continuing source of confusion, so make the distinction a "hard" one.

Each process occupies a "slot". We automatically set #slots = #cpus if nothing else is told to us. If you want to run more procs and slots, you must tell us to allow oversubscription.

A process can utilize multiple pe's if that option is given. If you try to bind more than one proc to a given pe, then we will error out unless you tell us to allow overloading.
@jjhursey
Copy link
Member

Our of curiosity, if the user passes --use-hwthread-cpus then #slots = #hwthreads without the need for oversubscription, right? I just wanted to confirm that this case is still covered with this change.

@rhc54
Copy link
Contributor Author

rhc54 commented Aug 23, 2016

I didn't change anything about how the number of pe's is computed, so this shouldn't be impacted.

@markalle
Copy link
Contributor

I haven't checked out and built the change, but I think the description matches what I would expect. Thanks.

@rhc54 rhc54 merged commit 19b0f4d into open-mpi:master Aug 25, 2016
@rhc54 rhc54 deleted the topic/pe-per-rank branch August 25, 2016 19:38
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants