> Still, if that is indeed the cause, as i suspected, i thought that > putting in a bunch of MPI_Barrier()'s leading up to the offending call > or calls might solve the problem?
No, the barrier actually does nothing good in your case. If all processes come up to the barrier at the same time, everything is fine and you pass. If one of the processes has skipped an earlier call and gets to the barrier while the other processes are still waiting for it to respond to another MPI call, your program locks up -- just as if instead of the barrier you would have had any other MPI call. I've found that barriers actually have very few useful uses. W. ------------------------------------------------------------------------- Wolfgang Bangerth email: [email protected] www: http://www.math.tamu.edu/~bangerth/ _______________________________________________ dealii mailing list http://poisson.dealii.org/mailman/listinfo/dealii
