[mvapich-discuss] CPU affinity and binding check

[Davide Vanzo]

Hi all,
I'm learning how to optimize MPI codes running on heterogeneous
architectures with GPUs. I compiled MVAPICH 2.1 with hwloc support and
I know how to instruct mpirun_rsh to allocate threads according to the
desired topology. Now I would like to find (or write, if it doesn't
exist) an MPI program that returns as output what cores each thread has
been assigned to. I started looking into the hwloc library and the
numalib, but why reinventing the wheel?
Thank you in advance for your help.

Davide

-- 
Davide Vanzo, PhD
Application Developer
Advanced Computing Center for Research and Education (ACCRE)
Vanderbilt University - Hill Center 201
www.accre.vanderbilt.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cse.ohio-state.edu/pipermail/mvapich-discuss/attachments/20151105/618651ac/attachment.html>