Thanks Jeff and Andrew, those responses were well thought out and very
informative.
I'll run the same test explicitly using TCP for a couple runs and then
mvapi a couple times. The results should give the users a warm fuzzy
that OpenMPI is in fact using the expensive faster network (rather than
c
Howdy, I'm new to cluster administration, MPI and high speed networks.
I've compiled my OpenMPI using these settings:
./configure CC='icc' CXX='icpc' FC='ifort' F77='ifort'
--with-mvapi=/usr/local/topspin
--with-mvapi-libdir=/usr/local/topspin/lib64 --enable-static
--prefix=/share/apps/openmpi/1.
Never mind, I found it in the FAQ, need version 1.2 of OpenMPI. I'll
give that a go.
-Original Message-
From: users-boun...@open-mpi.org [mailto:users-boun...@open-mpi.org] On
Behalf Of Michael John Hanby
Sent: Tuesday, December 19, 2006 2:28 PM
To: Open MPI Users
Subject: [OMPI
Howdy,
I'm compiling OpenMPI 1.1.2 on a Rocks Cluster 4.2.1. The cluster has
sge installed which is what the users will use to submit their MPI jobs
(i.e. using qsub).
I'm not having any luck finding the correct parameters to provide
./configure in order to include support for SGE.
Here's the co
