Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |  

This web mail archive is frozen.

This page is part of a frozen web archive of this mailing list.

You can still navigate around this archive, but know that no new mails have been added to it since July of 2016.

Click here to be taken to the new web archives of this list; it includes all the mails that are in this frozen archive plus all new mails that have been sent to the list since it was migrated to the new archives.

Subject: Re: [OMPI users] Running on two nodes slower than running on one node
From: Ralph Castain (rhc_at_[hidden])
Date: 2014-01-30 06:09:56


On Jan 30, 2014, at 12:38 AM, Victor <victor.major_at_[hidden]> wrote:

> I use htop and top....and until now I did not make the connection that each listed process is actually a thread...
>
> Thus the application that I am running is single threaded. How does that affect the CPU affinity and rank settings?

It affects it very much - there is no value in running a rank on multiple cores in that case. Just do "mpirun --bind-to-core"

Threading the app is a mixed bag - it might help, but there is a penalty as well since you have to do all that thread locking. For now, just bind-to-core

> <-- as mentioned earlier I am a novice, and very easily confused :-)
>
>
>
> On 30 January 2014 15:59, John Hearns <hearnsj_at_[hidden]> wrote:
> Ps. 'htop' is a good tool for looking at where processes are running.
>
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users
>
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users