This is a very good example! Thanks for the clarification! Thanks, Raghu --On Saturday, June 29, 2013 3:08 PM -0500 Rajeev Thakur <[email protected]> wrote:

Yes.

On Jun 29, 2013, at 3:05 PM, Jed Brown wrote:

...

Rajeev Thakur <[email protected]> writes:

...

It doesn't have to be a matching Wait. The implementation is required to make progress on other pending communication while it is blocked in a Wait.

Or blocked in any of a number of other places, if non-blocking collective requests have the same completion semantics as point-to-point requests. E.g., this shouldn't deadlock:

MPI_Iallreduce(...,COMM_WORLD,&req); if (!rank) MPI_Wait(&req); MPI_Allgather(...,COMM_WORLD); if (rank) MPI_Wait(&req);

_______________________________________________ discuss mailing list [email protected] To manage subscription options or unsubscribe: https://lists.mpich.org/mailman/listinfo/discuss