[mpiwg-ft] FTWG Call Topics?
lagunaperalt1 at llnl.gov
Wed Jun 21 12:17:14 CDT 2017
I'm okay if we cancel.
On a different note, I wanted to ask the group about the error handler
for MPI_Init. As I look into the problem of MPI re-initialization, I
came across some questions, which I'm not been able to answer myself by
reading the standard:
- Since one cannot set an error handler before MPI_Init, is is expected
that MPI_ERRORS_ARE_FATAL is enabled when MPI_Init is called? If that is
the case, one can assume that if an error occurs the first time MPI_Init
is called (let's assume in the future we can call MPI_Init several
times), MPI will abort?
- Is there any situation, in which MPI_Init could return an error code
if a failure occurs?
- Is there a way to set MPI_ERROR_RETURN in COMM_WORLD before calling
I realize this was discussed in 2010, but I'm not sure if the forum
found a solution:
Center for Applied Scientific Computing (CASC)
Lawrence Livermore National Laboratory
Phone: 925-422-7308, Fax: 925-422-6287
On 6/21/17 9:40 AM, Bland, Wesley wrote:
> I don't have any topics for today's FTWG con call. Does anyone have anything they want to discuss?
> Should we cancel?
> mpiwg-ft mailing list
> mpiwg-ft at lists.mpi-forum.org
More information about the mpiwg-ft