Open MPI logo

Hardware Locality Users' Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Hardware Locality Users mailing list

Subject: Re: [hwloc-users] Understanding hwloc-ps output
From: Youri LACAN-BARTLEY (youri.lacan-bartley_at_[hidden])
Date: 2012-05-30 10:34:19

Brice, Jeff,

Thank you for your swift reply.
I will try out openmpi 1.6 as soon as I can and see if this produces the expected results.
The benchmarking results I've obtained seem to confirm that openmpi is indeed reporting the wrong bindings.

It would indeed be great if openmpi 1.6 could display hwloc bitmasks to avoid confusion.


-----Message d'origine-----
De : hwloc-users-bounces_at_[hidden] [mailto:hwloc-users-bounces_at_[hidden]] De la part de Brice Goglin
Envoyé : mercredi 30 mai 2012 16:07
À : Hardware locality user list
Objet : Re: [hwloc-users] Understanding hwloc-ps output

What is the displayed bitmask in OMPI 1.6? Is it the hwloc bitmask? Or the OMPI bitmask made of OMPI indexes?

Le 30/05/2012 16:01, Jeff Squyres a écrit :
> You might want to try the OMPI tarball that is about to become OMPI v1.6.1 -- we made a bunch of affinity-related fixes, and it should be much more predictable / stable in what it does in terms of process binding:
> (these affinity fixes are not yet in a nightly 1.6 tarball because
> we're testing them before they get committed to the OMPI v1.6 SVN
> branch)
> On May 30, 2012, at 9:54 AM, Brice Goglin wrote:
>> Hello Youri,
>> When using openmpi 1.4.4 with --np 2 --bind-to-core --bycore" it reports the following:
>>> [hostname:03339] [[17125,0],0] odls:default:fork binding child
>>> [[17125,1],0] to cpus 0001
>>> [hostname:03339] [[17125,0],0] odls:default:fork binding child
>>> [[17125,1],1] to cpus 0002
>> Bitmask 0001 and 0002 mean CPUs with physical indexes 0 and 1 in OMPI 1.4. So that corresponds to the first core of each socket, and that matches what hwloc-ps says. Try "hwloc-ps -c" should show the same bitmask.
>> However, I agree that these are not adjacent cores, but I don't know enough of OMPI binding options to understand what it was supposed to do in your case.
>> Brice
>> _______________________________________________
>> hwloc-users mailing list
>> hwloc-users_at_[hidden]

hwloc-users mailing list