1 slide would be helpful (Rich has a lot of material to cover, so we need to be concise). Thanks! Bill William Gropp Director, Parallel Computing Institute Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign On Sep 7, 2012, at 4:08 PM, Jeff Hammond wrote:

I can provide a slide or two on my pet, request-based local completion RMA, and why it is _enormously useful_ :-) if encouraged to do so.

It might make sense for someone to say something about MPI-3 in relation to PGAS, SHMEM and/or ARMCI, since at least some fraction of the one-sided people in the world are going to measure us in that way.

Jeff

On Fri, Sep 7, 2012 at 1:26 PM, Jim Dinan <[email protected]> wrote:

...

Hi Bill,

I've attached a few MPI-3 RMA summary slides that Dave and I presented at a recent tutorial. We could use these as a starting point.

~Jim.

On 9/7/12 2:52 PM, William Gropp wrote:

...

One of us needs to provide this. There are the slides that we've used for the forum itself, and abbreviated versions of these. I'm working on the standard updates - is someone able to prepare these slides for Rich?

Bill

William Gropp Director, Parallel Computing Institute Deputy Director for Research Institute for Advanced Computing Applications and Technologies Paul and Cynthia Saylor Professor of Computer Science University of Illinois Urbana-Champaign

Begin forwarded message:

...

*From: *Richard Graham <[email protected] <mailto:[email protected]>> *Subject: **[Mpi-forum] MPI 3.0 overview* *Date: *September 4, 2012 2:17:29 AM GMT+02:00 *To: *"[email protected] <mailto:[email protected]>" <[email protected] <mailto:[email protected]>> *Reply-To: *Main MPI Forum mailing list <[email protected] <mailto:[email protected]>>

In preparation for presentations on the MPI 3.0 standard, I would like to ask that the working groups send a few slides on the following new additions to the MPI standard: - Nonblocking collectives - RMA enhancements - MPI Tool Interface - New Fortran bindings - Sparse collectives - Enhanced Datatype support - Distributed Graph - Noncollective communicator creation Also, if your working group had items that did not make it into MPI-3.0, and would like these mentioned in the same talk, please provide me with some slides. It is good to let folks know why some items did not make it into the standard. It would be very helpful if I could get these slides by Sept the 12^th .

Thanks, Rich _______________________________________________ mpi-forum mailing list [email protected] <mailto:[email protected]> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum

_______________________________________________ mpi3-rma mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma

_______________________________________________ mpi3-rma mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma

-- Jeff Hammond Argonne Leadership Computing Facility University of Chicago Computation Institute [email protected] / (630) 252-5381 http://www.linkedin.com/in/jeffhammond https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond _______________________________________________ mpi3-rma mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma