[Mpi3-rma] [Mpi-forum] MPI 3.0 overview

[William Gropp]

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 <dinan at mcs.anl.gov> 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 <richardg at mellanox.com
>>>> <mailto:richardg at mellanox.com>>
>>>> *Subject: **[Mpi-forum] MPI 3.0 overview*
>>>> *Date: *September 4, 2012 2:17:29 AM GMT+02:00
>>>> *To: *"mpi-forum at lists.mpi-forum.org
>>>> <mailto:mpi-forum at lists.mpi-forum.org>" <mpi-forum at lists.mpi-forum.org
>>>> <mailto:mpi-forum at lists.mpi-forum.org>>
>>>> *Reply-To: *Main MPI Forum mailing list <mpi-forum at lists.mpi-forum.org
>>>> <mailto:mpi-forum at lists.mpi-forum.org>>
>>>> 
>>>> 
>>>> 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
>>>> mpi-forum at lists.mpi-forum.org <mailto:mpi-forum at lists.mpi-forum.org>
>>>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum
>>> 
>>> 
>>> 
>>> 
>>> _______________________________________________
>>> mpi3-rma mailing list
>>> mpi3-rma at lists.mpi-forum.org
>>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
>>> 
>> 
>> _______________________________________________
>> mpi3-rma mailing list
>> mpi3-rma at lists.mpi-forum.org
>> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma
> 
> 
> 
> -- 
> Jeff Hammond
> Argonne Leadership Computing Facility
> University of Chicago Computation Institute
> jhammond at alcf.anl.gov / (630) 252-5381
> http://www.linkedin.com/in/jeffhammond
> https://wiki.alcf.anl.gov/parts/index.php/User:Jhammond
> _______________________________________________
> mpi3-rma mailing list
> mpi3-rma at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-rma