Hi. I think you are right about the synchronisation. I tried outputting the field after the harminv, that does make it better. I get the problem less often. Perhaps I should do something computationally expensive. Or does anyone what the all_wait call is in the scheme interface?
Best, Dries -------- Original message -------- From: Filip Dominec <filip.domi...@gmail.com> Date: 13/03/2014 09:01 (GMT+01:00) To: "Oosten, D. van (Dries)" <d.vanoos...@uu.nl>,meep-discuss <meep-discuss@ab-initio.mit.edu> Subject: Re: [Meep-discuss] meep mpi harminv problem Hi, it appears to me that harminv may not use the MPI synchronisation at its end. If this is the case, it could result inĀ a race condition, when one instance of harminv ends the multithreaded program, while the second one is still running. I suggest to add some field-manipulating function at the very end of your program, so that all threads have to wait for each other and finish simultaneously. My python-meep scripts have meep.all_wait() at their last line, and probably a similar function exists in scheme. Does it help? Regards, Filip 2014-03-12 20:32 GMT+01:00, Oosten, D. van (Dries) <d.vanoos...@uu.nl>: > Sorry guys, but just to clarify, mpirun often says things like > > -------------------------------------------------------------------------- > mpirun has exited due to process rank 5 with PID 8389 on > node workstation exiting without calling "finalize". This may > have caused other processes in the application to be > terminated by signals sent by mpirun (as reported here). > -------------------------------------------------------------------------- > > does that clarify things for anyone? > > > ________________________________________ > From: Oosten, D. van (Dries) > Sent: Wednesday, March 12, 2014 8:20 PM > To: meep-discuss@ab-initio.mit.edu > Subject: meep mpi harminv problem > > Hi guys, > > I have been struggling with the following issue. When I use harminv to find > eigenmodes in meep, it is often unreliable when I use it through mpirun. > This is especially the case when the workstation we run meep on is under > heavy load. It seems to me that the process get killed by mpirun before they > can give their results. Could this be the case and if so, what tests can I > run to track this problem down? > > Thanks in advance! > > best, > Dries > > _______________________________________________ > meep-discuss mailing list > meep-discuss@ab-initio.mit.edu > http://ab-initio.mit.edu/cgi-bin/mailman/listinfo/meep-discuss >
_______________________________________________ meep-discuss mailing list meep-discuss@ab-initio.mit.edu http://ab-initio.mit.edu/cgi-bin/mailman/listinfo/meep-discuss