[mpiwg-rma] FW: [Mpi3-rma] [EXTERNAL] Re: MPI-3 UNIFIED model updates

Jeff Hammond jeff.science at gmail.com
Tue Aug 27 12:57:29 CDT 2013

The MPI standard will not define by what mechanism the SHMEM implementation
will establish the necessary consistency.  This is what I mean by undefined
= implementation-defined.  I do not think that Keith is proposing to
enumerate all processor memory models and the appropriate fences required
to achieve the affect of win_sync but at lower cost.  Thus, it is the
implementation - or perhaps more accurately, the platform on which the
implementation resides - that will define these semantics.


On Tue, Aug 27, 2013 at 10:16 AM, Pavan Balaji <balaji at mcs.anl.gov> 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

Jeff Hammond
jeff.science at gmail.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpi-forum.org/pipermail/mpiwg-rma/attachments/20130827/31d80616/attachment-0001.html>

More information about the mpiwg-rma mailing list