My program is failing in MPI_Comm_spawn, but it seems to simply terminate the
job rather than throwing an exception that I can catch. Here is the
abbreviated error message:
[n001:32127] *** An error occurred in MPI_Comm_spawn
[n001:32127] *** reported by process [1679884289,1]
[n001:32127] ***
On Nov 7, 2019, at 3:02 PM, Mccall, Kurt E. (MSFC-EV41) via users
mailto:users@lists.open-mpi.org>> wrote:
My program is failing in MPI_Comm_spawn, but it seems to simply terminate the
job rather than throwing an exception that I can catch. Here is the
abbreviated error message:
[n001:32127]
Ø You need to also set the MPI::ERRORS_THROW_EXCEPTIONS error handler in your
MPI application.
Thanks Jeff. I double-checked, and yes, I’m calling
MPI_Comm_set_errhandler(com , MPI::ERRORS_THROW_EXCEPTIONS) for every intra-
and inter-communicator in the parent and child processes. Could it
On Nov 7, 2019, at 4:18 PM, Mccall, Kurt E. (MSFC-EV41) via users
wrote:
>
> Ø You need to also set the MPI::ERRORS_THROW_EXCEPTIONS error handler in
> your MPI application.
>
> Thanks Jeff. I double-checked, and yes, I’m calling
> MPI_Comm_set_errhandler(com , MPI::ERRORS_THROW_EXCEPTION
Just to double check, does ompi_info show that you have C++ exception support?
-
$ ompi_info --all | grep exceptions
C++ exceptions: yes
-
Indeed it does:
$ ompi_info --all | grep exceptions
Configure command line: '--prefix=/opt/openmpi_pgc' '--enable-mpi-cxx'
'--enable-cx
> Something is odd here, though -- I have two separately compiled OpenMpi
> directories, one with and one without Torque support
> (via the -with-tm configure flag). >Ompi_info chose the one without Torque
> support. Why would it choose one over the other?
> The one with Torque support is w
On Nov 7, 2019, at 4:37 PM, Mccall, Kurt E. (MSFC-EV41) via users
wrote:
>
> Something is odd here, though -- I have two separately compiled OpenMpi
> directories, one with and one without Torque support (via the -with-tm
> configure flag). Ompi_info chose the one without Torque support. Wh
