Andrea,
On top of what Ralph just wrote, you might want to upgrade OpenMPI to
the latest stable version (1.10.3)
1.6.5 is pretty antique and is no more maintained.
the message indicates that one process died, and so many things could
cause a process crash.
(since the crash occurs only with N > 25, the root cause could be an out
of memory (just run dmesg and grep OOM),
a division by zero, your application calling exit(...) instead of
MPI_Finalize()/MPI_Abort(...) or a bug in your application)
Cheers,
Gilles
On 7/8/2016 7:12 AM, Ralph Castain wrote:
Try running one of the OMPI example codes and verify that things run
correctly if N > 25. I suspect you have an error in your code that
causes it to fail if its rank is > 25.
On Jul 7, 2016, at 2:49 PM, Alberti, Andrea <alber...@illinois.edu
<mailto:alber...@illinois.edu>> wrote:
Hi,
my name is Andrea and I am a new openMPI user.
I have a code compiled with:
intel/16.0.3
openmpi/1.6.5
--> When I try to run my code with: mpirun -n N ./code.exe
a) the code correctly runs and gives results if N<=25
b) the code gives the following error if N>25:
mpirun has exited due to process rank X with PID ...
--> This seems to be a pretty common problem when not all the
processes are initialized or finalized.
However, I do init and finalize the processors.
And, moreover, I do not understand why the problem is not there
when N<=25
Could someone, please, help me out with that or point me to some
pages where the same problem is discussed/solved?
Thank you very much in advance for the help.
Andrea
_______________________________________________
users mailing list
us...@open-mpi.org <mailto:us...@open-mpi.org>
Subscription:https://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this
post:http://www.open-mpi.org/community/lists/users/2016/07/29596.php
_______________________________________________
users mailing list
us...@open-mpi.org
Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http://www.open-mpi.org/community/lists/users/2016/07/29597.php