Being on this list should be good. If you create an account on the trac page, you can also add yourself to the cc list for the ticket. You're also welcome to join meetings; right now we are focused on the March face-to-face meeting deadlines so we won't be able to work in any new business until after that. Changing the standard is a long process, so this could take a while, but staying involved to provide motivating use cases would be very helpful. :) On Tue, Feb 11, 2014 at 11:53 AM, Thomas Jahns <[email protected]> wrote:

Hello Jim,

On 02/11/14 16:59, Jim Dinan wrote:

...

This sounds like a reasonable proposal to me; it should be possible to create a sane definition for windows on intercommunicators. The RMA interface has focused on intracommunicators, so it could require several additions to e.g. make it possible to query both local and remote groups from the window. I think the main argument against adding this would be the increased complexity in the standard and to implementations. Given that there is a workaround (flattening the communicator to make the window, and using post/start/complete/wait to restrict the set of communication peers in active target), we would need to motivate such a change.

I captured your proposal in a ticket, https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/412, so we remember to discuss this further in the RMA working group.

thank you. Will remaining subscribed to this list be sufficient to receive notice of updates or should I poll above issue every few weeks?

Regards, Thomas -- Thomas Jahns DKRZ GmbH, Department: Application software

Deutsches Klimarechenzentrum Bundesstraße 45a D-20146 Hamburg

Phone: +49-40-460094-151 Fax: +49-40-460094-270 Email: Thomas Jahns <[email protected]>

_______________________________________________ mpiwg-rma mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-rma