Perhaps often it is more useful to use MPI_WAIT rather than MPI_TEST type fucntions, because at MPI_WAIT point it will be taken care of communication completion, automatically, which may be necessary before going ahead. with MPI_TEST it would become the responsibility of the programmer to handle the situation if the test is FALSE/FAILED.

On Wed, Feb 2, 2011 at 7:50 AM, Jeff Squyres <jsquyres@cisco.com> wrote:
Yes; you can use any of the various flavors of the MPI_TEST* functions.

On Feb 2, 2011, at 7:03 AM, Bibrak Qamar wrote:

> Hello All,
>
> Is there any way to find whether a non blocking communication has finished without calling the wait( ) function.
>
>
> Thanks
> Bibrak Qamar
> Undergraduate Student BIT-9
> Member Center for High Performance Scientific Computing
> NUST-School of Electrical Engineering and Computer Science.
> _______________________________________________
> users mailing list
> users@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users


--
Jeff Squyres
jsquyres@cisco.com
For corporate legal information go to:
http://www.cisco.com/web/about/doing_business/legal/cri/


_______________________________________________
users mailing list
users@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users