---------- Forwarded message ----------
From: Daniel Ibanez <firstname.lastname@example.org>
Date: Thu, Mar 22, 2012 at 6:06 PM
Subject: Re: [hwloc-devel] BGQ empty topology with MPI
To: Samuel Thibault <email@example.com
I suspected this might be the reason, so I called "nm"
with the static versions of the libraries their compiler wrappers
link against and I could not find the term "hwloc" in the output.
Is this a valid test?
On Thu, Mar 22, 2012 at 6:35 AM, Samuel Thibault <firstname.lastname@example.org>
Brice Goglin, le Thu 22 Mar 2012 10:58:46 +0100, a écrit :
> I don't see anything bad in your outputs.There might be symbol conflicts then, indeed. That's the usual problem
> So there's something strange going on when MPI is added. Which MPI are using?
> Is this a derivative of MPICH that embeds hwloc? (MPICH >= 1.2.1 if I remember
with embedding instead of using an installed library. Doesn't its
configure use the installed library if one exists?