[Cplex] Another Parallel API

Jeff Hammond jeff.science at gmail.com
Wed Jun 26 13:28:16 CEST 2013


If this group wants to take a serious look at PGAS, read the UPC spec.
 There's also some work on "Co-Array C++" that provides an alternative
view for those who don't like the UPC memory model or related
concepts.

As Bronis suggested, what is said about GPI on the Internet has little
basis in reality.  If requested, I will waste yet another hour of my
life listing all of the reasons that this project is an insult to the
programming models community.

Jeff

On Tue, Jun 25, 2013 at 10:37 PM, Bronis R. de Supinski <bronis at llnl.gov> wrote:
>
> I have a bridge in Brooklyn available cheap if you are interested...
>
> On Tue, 25 Jun 2013, Lawrence Crowl wrote:
>
>> FYI, http://www.gpi-site.com/gpi2/ is supposed to provide better
>> performance than MPI on modern systems.  It is also based on a
>> global address space, which may be easier to incorporate into
>> existing language standards.
>>
>> --
>> Lawrence Crowl
>> _______________________________________________
>> Cplex mailing list
>> Cplex at open-std.org
>> http://www.open-std.org/mailman/listinfo/cplex
>>
> _______________________________________________
> Cplex mailing list
> Cplex at open-std.org
> http://www.open-std.org/mailman/listinfo/cplex



-- 
Jeff Hammond
jeff.science at gmail.com


More information about the Cplex mailing list