So, we should define it as not defined? OpenSHMEM itself does not define what should happen if you poll on a location that is the target of an RMA update. The "proper" way to poll in SHMEM is to call one of the built-in polling functions (e.g. shmem_int_wait(location, value)), which can deal with the data consistency problem. ~Jim. On Tue, Aug 27, 2013 at 1:16 PM, Pavan Balaji <[email protected]> wrote:

On 08/27/2013 11:39 AM, Jeff Hammond wrote:

...

I agree with Keith. Losing SHMEM as a client of MPI-3 is not worth symmetry or other esoteric properties.

It's entirely reasonable to say the standard leaves no-sync unified as undefined = implementation-defined. This would not be the first time.

Your statements are inconsistent. You said you agree with Keith, but then said that the no-sync unified option should be undefined. That's not what Keith is saying; he wants that to have *defined* behavior, i.e., it is valid for the client to do platform-specific memory consistency.

-- Pavan

-- Pavan Balaji http://www.mcs.anl.gov/~balaji ______________________________**_________________ mpiwg-rma mailing list [email protected] http://lists.mpi-forum.org/**mailman/listinfo.cgi/mpiwg-rma<http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-rma>