Mailing List Archives
Authenticated access
|
|
|
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Condor-users] MPICH application
- Date: Thu, 12 Jul 2007 12:41:43 +0200
- From: Nicolas GUIOT <nicolas.guiot@xxxxxxx>
- Subject: Re: [Condor-users] MPICH application
Mark,
I don't understand when you're creating your "machfile" file : is it created on the fly ? how ? I can't see anyhting related to it, only when you want to use it : "mpiexec -l -machinefile $MPDIR/etc/machfile -envall -n $_CONDOR_NPROCS $EXECUTABLE $@"
Does this mean that you create it manually ? before submitting the jobs ? in this case, it's static, and you can't know on which machine you're running your job ??
I'd be glad to have a bit some explanation...
Nicolas
----------------
On Wed, 11 Jul 2007 17:12:03 +0100
Mark Calleja wrote:
> Nicolas, if you're going to use MPICH2 on the same SMP machine then the
> mp2script and the machfile that it uses take on a particularly simple
> form. I've written some notes on how to do it at:
>
> http://www.escience.cam.ac.uk/projects/camgrid/mpi.html
>
> Good luck,
> Mark
>
> Nicolas GUIOT wrote:
> > Hi,
> >
> > I'm trying (again..) to make some MPI application work with condor.
> >
> > Right now, the problem is when I try to run some parallel jobs on the same machine (dual-core) : basically, mpich2 asks for a file mpd.hosts that contains this :
> > node1:2
> > --> so that it starts 2 process on the same box.
> >
> > But mp2script creates a file that contains this :
> > node1
> > node1
> > --> this doesn't work (at least by me..)
> >
> > Did someone find a workaround ?
> >
> > Tnaks in advance
> > Nicolas
> >
> >
> > ----------------------------------------------------
> > CNRS - UPR 9080 : Laboratoire de Biochimie Theorique
> >
> > Institut de Biologie Physico-Chimique
> > 13 rue Pierre et Marie Curie
> > 75005 PARIS - FRANCE
> >
> > Tel : +33 158 41 51 70
> > Fax : +33 158 41 50 26
> > ----------------------------------------------------
> > _______________________________________________
> > Condor-users mailing list
> > To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> > subject: Unsubscribe
> > You can also unsubscribe by visiting
> > https://lists.cs.wisc.edu/mailman/listinfo/condor-users
> >
> > The archives can be found at:
> > https://lists.cs.wisc.edu/archive/condor-users/
> >
>
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
>
> The archives can be found at:
> https://lists.cs.wisc.edu/archive/condor-users/
>
----------
----------------------------------------------------
CNRS - UPR 9080 : Laboratoire de Biochimie Theorique
Institut de Biologie Physico-Chimique
13 rue Pierre et Marie Curie
75005 PARIS - FRANCE
Tel : +33 158 41 51 70
Fax : +33 158 41 50 26
----------------------------------------------------