Open MPI logo

Hardware Locality Development Mailing List Archives

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

Subject: Re: [hwloc-devel] dplace
From: Michael Raymond (mraymond_at_[hidden])
Date: 2010-04-20 11:54:32


  As of SGI ProPack 7 dplace uses hwloc internally to specify stride
patterns. For example:

mpirun -np 8 dplace -c SC a.out

  means to pin ranks to every core inside a socket before jumping to the
next socket and doing the same.

  From the man page:

         For striding patterns any
              subset of the characters (B)lade, (S)ocket, (C)ore,
(T)hread may
              be used and their ordering specifies the nesting of the
itera-
              tion. For example "SC" means to iterate all the
cores in a
              socket before moving to the next CPU socket, while "CB"
means to
              pin to the first core of each blade, then the second
core of
              every blade, etc.

  I've been trying to evangelize more hwloc usage with mixed results.

Brice Goglin wrote:
> I discovered "dplace" today. I don't know how many people install/use it
> on their cluster, but it's something that looks interesting when you
> don't have advanced binding capabilities in the MPI implementation. For
> instance, you could do:
> $ mpirun -np 8 dplace 0,4,2,6,1,5,3,7 myprogram
> to bind process ranks according to the machine topology.
>
> hwloc-calc can easily generate such list of physical processors, for
> instance:
> $ hwloc-calc --physical proc:all --pulist
> 0,4,2,6,1,5,3,7
> or even restrict of one PU per socket with:
> $ hwloc-calc --physical socket:all.core:0 --pulist
> 0,1
>
> So hwloc-calc could help dplace significantly. Maybe we should put such
> examples somewhere in the doc.
>
> Brice
>
> _______________________________________________
> hwloc-devel mailing list
> hwloc-devel_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-devel

-- 
Michael A. Raymond
Message Passing Toolkit Team
Silicon Graphics Inc
(651) 683-3434