Ummm....I'll let you guys work this out on PLPA. However, just to
clarify, OMPI currently binds to cores, not logical cpus. It is the
PLPA that is "dumb" and provides the plumbing to do what OMPI tells it.
:-)
On Jul 24, 2009, at 2:18 AM, Chris Samuel wrote:
----- "Jeff Squyres" <jsquy...@cisco.com> wrote:
PLPA does not currently deal with cpusets.
I think it can get close enough if it assumes that
its initial affinity list is the subset of cores that
it can choose from when setting CPU affinity.
As for whether OMPI or PLPA should choose, I suspect
it's better if OMPI continues to be dumb and say "bind
me to CPU n" and PLPA works out what CPU 'n' works
out to be in terms of actual cores it can access.
But I'll take the rest of this to the PLPA list. :-)
cheers,
Chris
--
Christopher Samuel - (03) 9925 4751 - Systems Manager
The Victorian Partnership for Advanced Computing
P.O. Box 201, Carlton South, VIC 3053, Australia
VPAC is a not-for-profit Registered Research Agency
_______________________________________________
devel mailing list
de...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/devel
