[Mpi3-rma] Updated MPI-3 RMA proposal 1

[Torsten Hoefler]

Hi all,
> I think it's semantically ugly, doesn't fit with the spirit of the
> standard, and is unnecessary.  I understand others disagree.  I also
> don't care enough to fight about it not being proposed (in the general
> case).  However, since I believe that others in the general forum will
> have a strong reaction to it and I'd really prefer not have proposal 1
> (which is already going to be difficult to get done) tainted with
> something that is not strictly necessary to fixing obviously broken
> pieces of the existing standard and that will invoke strong reactions
> in the greater community.
> 
> But like I said, I dont' care enough to argue something without data.
Brian has a good point. Proposal 1 was supposed to be the uncontentious
one. We have made the decision to include it in absence of the two main
opponents. Pushing this forward feels incorrect, thus, I removed it for
now from the proposal.

Attached to
https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/RmaWikiPage

I am actually in favor of the semantics (I am convinced that there could
be a performance advantage due to the higher abstraction). I am not sure
whether to put it in proposal 2/3 or make it a separate ticket :-).

All the Best,
  Torsten

-- 
 bash$ :(){ :|:&};: --------------------- http://www.unixer.de/ -----
Torsten Hoefler         | Modeling and Simulation Lead
Blue Waters Directorate | University of Illinois
1205 W Clark Street     | Urbana, IL, 61801
NCSA Building           | +01 (217) 244-7736