You might want to play with process binding to see if your problem is
related to bad memory affinity.
Try to launch pingpong on two CPUs of the same socket, then on different
sockets (i.e. bind each process to a core, and try different
De : Matthias Jurenz <matthias.jurenz_at_[hidden]>
A : Open MPI Developers <devel_at_[hidden]>
Date : 13/02/2012 12:12
Objet : [OMPI devel] poor btl sm latency
Envoyé par : devel-bounces_at_[hidden]
on our new AMD cluster (AMD Opteron 6274, 2,2GHz) we get very bad
(~1.5us) when performing 0-byte p2p communication on one single node using
Open MPI sm BTL. When using Platform MPI we get ~0.5us latencies which is
pretty good. The bandwidth results are similar for both MPI
(~3,3GB/s) - this is okay.
One node has 64 cores and 64Gb RAM where it doesn't matter how many ranks
allocated by the application. We get similar results with different number
We are using Open MPI 1.5.4 which is built by gcc 4.3.4 without any
configure options except the installation prefix and the location of the
As mentioned at http://www.open-mpi.org/faq/?category=sm we tried to use
/dev/shm instead of /tmp for the session directory, but it had no effect.
Furthermore, we tried the current release candidate 1.5.5rc1 of Open MPI
provides an option to use the SysV shared memory (-mca shmem sysv) - also
results in similar poor latencies.
Do you have any idea? Please help!
devel mailing list