[mpich-discuss] Non-blocking collectives

[Rajeev Thakur]

Yes.

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

> Rajeev Thakur <thakur at mcs.anl.gov> 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);