Hi Erik,

Thanks for the breakdown.

With regard to condor, I know Duncan Brown at Syracuse has a working script 'condor_mpirun' that's GPL'd.  I'm including a copy of a message that circulated to a LIGO software email list that describes how to run condor mpi jobs.

So you'd submit to a cluster with
     condor_submit  <name-of-script-text-file-included-below>
which would in turn call this script

See http://www.cs.wisc.edu/condor/manual/v7.4/2_9Parallel_Applications.html
for a description of the underlying issues.  I personally haven't used condor in parallel in a few years, but it was particularly convenient when I did.  And it's the submission system I'll likely be using in the future.

-Richard

From: Duncan Brown <dabrown@physics.syr.edu>
Date: October 6, 2010 8:35:36 AM CDT
To: daswg@gravity.phys.uwm.edu, Vivien Raymond <vivien@u.northwestern.edu>
Cc: Stuart Anderson <anderson@ligo.caltech.edu>, LDAS_ADMIN_ALL <ldas_admin_all@ligo.caltech.edu>
Subject: Re: [DASWG] MPI jobs on LDG clusters
Reply-To: daswg@gravity.phys.uwm.edu

Hi Vivien,