[mvapich-discuss] one-sided passive communications
Jim Dinan
dinan at mcs.anl.gov
Wed Dec 5 17:28:00 EST 2012
Hi All,
Here's an easy way for to poke the MPI progress engine:
{
int flag;
MPI_Iprobe(MPI_ANY_SOURCE, MPI_ANY_TAG, MPI_COMM_WORLD,
&flag, MPI_STATUS_IGNORE);
}
Best,
~Jim.
On 12/5/12 1:17 PM, sreeram potluri wrote:
> Jeff, thats true with MVAPICH2 as well. Thanks.
>
> Sreeram Potluri
>
> On Wed, Dec 5, 2012 at 1:57 PM, Jeff Hammond <jhammond at alcf.anl.gov
> <mailto:jhammond at alcf.anl.gov>> wrote:
>
> >> If helper threads are not used, what is needed to get progress
> in the
> >> lock/unlock calls? Is it necessary to enter in any specific MPI
> call in the
> >> target process?
> >
> > Any of the MPI Test/Probe/Wait calls on the target will ensure
> progress.
>
> To add to this, I ~think~ that any other MPI calls that internally
> call the progress engine will also drive progress, including blocking
> send/recv and collectives. I could be wrong though; my understanding
> here is based upon MPICH, not MVAPICH2.
>
> Jeff
>
> --
> Jeff Hammond
> Argonne Leadership Computing Facility
> University of Chicago Computation Institute
> jhammond at alcf.anl.gov <mailto:jhammond at alcf.anl.gov> / (630)
> 252-5381 <tel:%28630%29%20252-5381>
> http://www.linkedin.com/in/jeffhammond
> https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond
>
>
>
>
> _______________________________________________
> mvapich-discuss mailing list
> mvapich-discuss at cse.ohio-state.edu
> http://mail.cse.ohio-state.edu/mailman/listinfo/mvapich-discuss
>
More information about the mvapich-discuss
mailing list