On Nov 2, 2011, at 10:34 AM, Durga Choudhury wrote:
> 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.)
I honestly don't rememb
yes i call MPI_init after MPI_finalise ,because i use mpi in function and i
call it lot of time .
thank you for ur help ,now i call mpi_init and finalize out of funtion and
it work .
thank you
Le 2 novembre 2011 13:29, Jeff Squyres (jsquyres) a
écrit :
> Did you call MPI-INIT after you called
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 re
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" wrote:
> hey
>
> i'm new in mpi , i try tu use mpi inside of function and
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 kill
