[mpich-discuss] mpich from the MCS Ubuntu linux build

[Gustavo Correa]

Maybe increasing the OMP_STACKSIZE will help?
The defaults tend to be too small for most applications.

My two cents
Gus Correa

On Sep 23, 2011, at 12:15 AM, Jeff Hammond wrote:

> What happens if you build an OpenMP program with no MPI using CC=mpicc?
> 
> Does gdb tell you anything about where the code dies?
> 
> Jeff
> 
> On Thu, Sep 22, 2011 at 5:47 PM, Nichols A. Romero
> <naromero at alcf.anl.gov> wrote:
>> Hi,
>> 
>> I am using the MPICH that comes with the MCS Ubuntu Linux build (accesible through
>> the softenv). I am launching the application with mpiexec.gforker. If I run
>> with MPI only, the code starts. But if I run with MPI + OpenMP threads, it seg. faults
>> immediately.
>> 
>> Am I doing something wrong, or should just rebuild MPICH myself and not use what's
>> available through softenv?
>> 
>> Nichols A. Romero, Ph.D.
>> Argonne Leadership Computing Facility
>> Argonne National Laboratory
>> Building 240 Room 2-127
>> 9700 South Cass Avenue
>> Argonne, IL 60490
>> (630) 252-3441
>> 
>> 
>> _______________________________________________
>> 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
>> 
> 
> 
> 
> -- 
> Jeff Hammond
> Argonne Leadership Computing Facility
> University of Chicago Computation Institute
> jhammond at alcf.anl.gov / (630) 252-5381
> http://www.linkedin.com/in/jeffhammond
> https://wiki.alcf.anl.gov/index.php/User:Jhammond
> _______________________________________________
> 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