WHAT: Move hwloc up to be a first-class citizen in OPAL (while still making it
possible to compile it out for platforms that don't need it)
WHY: I previously sent a similar RFC to this one, but it got shot down in favor
of hiding hwloc's functionality under abstraction. After playing with this
Dear all:
I met a performance issue of Open MPI Reduce on infiniband cluster.
I have two clusters, each has 32 nodes. Only difference between these two
clusters is their interconnect:
one gigabyte ethernet cluster and one 20 g infiniband. I configure Open MPI
1.5.3 on both clusters as follo
Perhaps it would help if you had clearly stated your concern. From this
description, I gather your concern is -not- that remote processes don't see the
setting, but that the remote -orteds- don't see it.
Yes, I'm aware of that issue for rsh-based launches. It stems from rsh not
allowing one to
On 8/30/2011 7:34 PM, Ralph Castain wrote:
On Aug 29, 2011, at 11:18 PM, Eugene Loh wrote:
Maybe someone can help me from having to think too hard.
Let's say I want to max my system limits. I can say this:
% mpirun --mca opal_set_max_sys_limits 1 ...
Cool.
Meanwhile, if I do this:
