[mpich-discuss] MPICH2 (or MPI_Init) limitation | scalability

Dave Goodell goodell at mcs.anl.gov
Mon Jan 9 17:52:57 CST 2012


Make sure you include a call to MPI_Finalize in your test program as  
well.

-Dave

On Jan 9, 2012, at 2:58 AM, Bernard Chambon wrote:

> Hello,
>
> Using, mpich2 1.4.1p1, running the smallest code (MPI_Init(NULL,  
> NULL) )
> I got Segmentation fault (signal 11),  with high numbers of tasks
>
> Someone ran into the same failure ?
> Best regards
>
>
> context :
>  mpich2 1.4.1 p1, compiled with gcc (4.1.2)
>  Linux SL5 (kernel 2.6.18-238.12cc.el5)
>
> code :
>   if (MPI_Init(NULL, NULL) != MPI_SUCCESS ) {
>    printf("Error calling MPI_Init !!, => exiting \n") ;  
> fflush(stdout);
>    return(1);
>   }
>
> run :
>   mpiexec -verbose -np 255 bin/mpiInit_test   >& mpiInit_test.log
>
> result :
>  APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault  
> (signal 11)
>
>
> mpiInit_test.log file :
>
> <mpiInit_test.log.txt>
>
>
> ---------------
> Bernard CHAMBON
> IN2P3 / CNRS
> 04 72 69 42 18
>
> _______________________________________________
> mpich-discuss mailing list     mpich-discuss at mcs.anl.gov
> To manage subscription options or unsubscribe:
> https://lists.mcs.anl.gov/mailman/listinfo/mpich-discuss



More information about the mpich-discuss mailing list