On Oct 1, 2010, at 4:02 AM CDT, Brice Goglin wrote: > Le 01/10/2010 10:56, Ondrej Marsalek a écrit : >> Hi again, >> >> I have a question regarding parallelization using both MPI and threads >> in a NUMA setup. I would like to be able to use one MPI process per >> socket or NUMA node and use threads within each MPI process to use all >> the cores. Can I use hwloc to put and keep all of these in the right >> places? >> >> Thanks, >> Ondrej >> > > It mostly depends on the MPI implementation. Several of them are > switching to hwloc for binding, so you will likely have a mpiexec option > to do so.
FWIW, MPICH2 supports this when using the hydra process manager: http://wiki.mcs.anl.gov/mpich2/index.php/Using_the_Hydra_Process_Manager#Process-core_Binding Open MPI has similar functionality documented somewhere on their website, but I don't have the link handy. -Dave
