Re: [OMPI users] NUMA interaction with Open MPI

2017-07-27 Thread Gilles Gouaillardet
Dave, On 7/28/2017 12:54 AM, Dave Love wrote: Gilles Gouaillardet writes: Adam, keep in mind that by default, recent Open MPI bind MPI tasks - to cores if -np 2 - to NUMA domain otherwise Not according to ompi_info from the latest release; it says socket.

Re: [OMPI users] NUMA interaction with Open MPI

2017-07-27 Thread Dave Love
Gilles Gouaillardet writes: > Adam, > > keep in mind that by default, recent Open MPI bind MPI tasks > - to cores if -np 2 > - to NUMA domain otherwise Not according to ompi_info from the latest release; it says socket. > (which is a socket in most cases, unless

Re: [OMPI users] NUMA interaction with Open MPI

2017-07-20 Thread Iliev, Hristo
Sent: Thursday, July 20, 2017 9:52 AM To: users@lists.open-mpi.org Subject: Re: [OMPI users] NUMA interaction with Open MPI Hello Mems_allowed_list is what your current cgroup/cpuset allows. It is different from what mbind/numactl/hwloc/... change. The former is a root-only restriction that cannot

Re: [OMPI users] NUMA interaction with Open MPI

2017-07-20 Thread Brice Goglin
6 > cpubind: 1 > nodebind: 1 > membind: 0 1 > > Cheers, > Hristo > > -Original Message----- > From: users [mailto:users-boun...@lists.open-mpi.org] On Behalf Of Gilles > Gouaillardet > Sent: Monday, July 17, 2017 5:43 AM > To: Open MPI Users <users@list

Re: [OMPI users] NUMA interaction with Open MPI

2017-07-19 Thread Iliev, Hristo
al Message- From: users [mailto:users-boun...@lists.open-mpi.org] On Behalf Of Gilles Gouaillardet Sent: Monday, July 17, 2017 5:43 AM To: Open MPI Users <users@lists.open-mpi.org> Subject: Re: [OMPI users] NUMA interaction with Open MPI Adam, keep in mind that by default, recent Open MP

Re: [OMPI users] NUMA interaction with Open MPI

2017-07-16 Thread Gilles Gouaillardet
Adam, keep in mind that by default, recent Open MPI bind MPI tasks - to cores if -np 2 - to NUMA domain otherwise (which is a socket in most cases, unless you are running on a Xeon Phi) so unless you specifically asked mpirun to do a binding consistent with your needs, you might simply try to

[OMPI users] NUMA interaction with Open MPI

2017-07-16 Thread Adam Sylvester
I'll start with my question upfront: Is there a way to do the equivalent of telling mpirun to do 'numactl --interleave=all' on the processes that it runs? Or if I want to control the memory placement of my applications run through MPI will I need to use libnuma for this? I tried doing "mpirun