Re: [OMPI users] 1.8.1 query [SEC=UNCLASSIFIED]

2015-02-16 Thread Ralph Castain
Yo Greg Is this still an issue for you? If so, could you please provide me with the requested info? I'm getting ready to start the release cycle on 1.8.5, so now would be the time to address this > On Jan 28, 2015, at 1:55 PM, Ralph Castain wrote: > > Ah, indeed - sounds like we are not corr

Re: [OMPI users] 1.8.1 query [SEC=UNCLASSIFIED]

2015-01-28 Thread Ralph Castain
Ah, indeed - sounds like we are not correctly picking up the cpuset. Can you pass me the environ from the procs, and the contents of the $PBS_HOSTFILE? IIRC, Torque isn't going to bind us to those cores, but instead sets something into the environ or the allocation that we need to correctly parse.

[OMPI users] 1.8.1 query [SEC=UNCLASSIFIED]

2015-01-28 Thread DOHERTY, Greg
Thank you Ralph for the advice. I will move on to try 1.8.4 as soon as I can. The first torque job asks for nodes=1:ppn=16:whatever The second job asks for nodes=1:ppn=16:whatever Both jobs happen to finish up on the same 64 core node. Each is running on its own set of 16 cores 0-15, and 16-31 res