[MITgcm-support] MITGCM on dual-dual-core Opteron
Constantinos Evangelinos
ce107 at ocean.mit.edu
Thu Jun 15 18:02:32 EDT 2006
On Thu 15 Jun 2006 17:00, Jason Goodman wrote:
> I'd like to be able to use the quad-core nodes as dual-core nodes
> sometimes, but MITGCM's performance using 2 cores per node is
> terrible. The 275 chip has the same clock speed as the 248, so you
> would think that each MITGCM process would run on a separate chip,
> each with its separate memory, and performance would be equal to the
> 248. That's exactly what happens with CAM. But with MITGCM on my
> system, the processes hop around from CPU to CPU. Sometimes both
> processes will be on the same chip, sometimes they'll be on different
> chips, the scheduler moves them around like crazy. And of course,
> when they're on the same chip, you get a memory bottleneck.
>
> Why does this happen? Why MITGCM and not CAM? Is there anything I
> can change in my OS configuration or MITGCM configuration to stop it?
For MPI codes you need a NUMA-aware MPI to do this using the numactl utility
or numa library calls. There are patched versions of MPICH and MPICH2 around
(there's a report somewhere from Phil Mucci) and OpenMPI has a numa module.
That should work.
Constantinos
--
Dr. Constantinos Evangelinos
Department of Earth, Atmospheric and Planetary Sciences
Massachusetts Institute of Technology
More information about the MITgcm-support
mailing list