[mpiwg-rma] same_op_no_op and SHMEM

[Jeff Hammond]

Indeed, I was thinking of asking for that to be added to the standard
one way or another.  However, I decided that it would be way more
useful to have window info arguments related to same_type and
no_floats since it is far more likely to have atomics in hardware for
fixed-point.

Jeff

On Thu, Oct 24, 2013 at 12:33 PM, Underwood, Keith D
<keith.d.underwood at intel.com> wrote:
> It is also possible that one person thought "NO_OP and REPLACE are really the same thing" and the other person didn't, but you are talking about conversations that have now been migrated off to tape ;-)
>
>> -----Original Message-----
>> From: mpiwg-rma [mailto:mpiwg-rma-bounces at lists.mpi-forum.org] On
>> Behalf Of Jeff Hammond
>> Sent: Thursday, October 24, 2013 1:24 PM
>> To: MPI Forum
>> Subject: [mpiwg-rma] same_op_no_op and SHMEM
>>
>> I recall that Brian and/or Keith wanted same_op_no_op because of SHMEM.
>> However, SHMEM requires the use of MPI_NO_OP (for atomic Get via
>> Get_accumulate), MPI_REPLACE (for atomic Put via Accumulate) and
>> MPI_SUM (for add, fadd, inc and finc).  So what is the benefit of
>> same_op_no_op to SHMEM?  Perhaps I remember completely wrong and
>> the motivation was something that does not use the latter atomics.  Or
>> perhaps it is common for SHMEM codes to not use these and thus the
>> assumption is MPI_SUM can be ignored.
>>
>> Jeff
>>
>> --
>> Jeff Hammond
>> jeff.science at gmail.com
>> _______________________________________________
>> mpiwg-rma mailing list
>> mpiwg-rma at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-rma
> _______________________________________________
> mpiwg-rma mailing list
> mpiwg-rma at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-rma



-- 
Jeff Hammond
jeff.science at gmail.com