Any particular reason these calls don't nest? In some other HPC-like paradigms (e.g. VSIPL) such calls are allowed to nest (i.e. only the finalize() that matches the first init() will destroy allocated resources.)
Just a curiosity question, doesn't really concern me in any particular way. Best regards Durga 2011/11/2 Jeff Squyres (jsquyres) <jsquy...@cisco.com>: > Did you call MPI-INIT after you called MPI-finalize? If so, you're not > allowed to do that. Call. MPI-INIT once and call MPI-finalize once. > > Sent from my phone. No type good. > > On Nov 1, 2011, at 2:45 PM, "amine mrabet" <amines...@gmail.com> wrote: > >> hey >> >> i'm new in mpi , i try tu use mpi inside of function and i have this error >> messag >> >> An error occurred in MPI_Init >> *** after MPI was finalized >> *** MPI_ERRORS_ARE_FATAL (goodbye) >> [dellam:16806] Abort before MPI_INIT completed successfully; not able to >> guarantee that all other processes were killed! >> >> maybe i cant use mpi inside of function ? >> >> -- >> amine mrabet >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> http://www.open-mpi.org/mailman/listinfo.cgi/users > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users >
