I'm trying to build OpenMPI 1.6.1 with Intel Cluster Studio 2012 for use
on our cluster however I'm running into a bit of a problem. The OpenMPI
itself builds fine as does the code I'm testing with. However when I try
to run on more than about 16 processors the run seg faults and when I
turn on traceback it seems to point to this call:
CALL MPI_INIT_THREAD(MPI_THREAD_FUNNELED, provided, ierr)
This is a pretty standard call. Even stranger when I use a different
version of the Intel Compiler 12.0.3 20110309 it doesn't have any problems.
The version of the Intel compiler in Intel Cluster Studio 2012 is 12.1.0
20110811.
Does any one have any thoughts about this error? I've tried turning off
any optimization to no avail. I even tried turned on debug mode for
OpenMPI but I can't get any thing more specific as to why it is
failing. I even tried compiling Intel MPI Benchmark, which failed in a
similar way, which indicates that its a problem specifically with the
interaction of MPI and the intel compiler and not the code I was working
with.
Thanks.
-Paul Edmon-