(j3.2006) (SC22WG5.5562) LCPC conference in Raleigh

[Bill Long]

On Sep 15, 2015, at 3:43 PM, Van Snyder <Van.Snyder at jpl.nasa.gov> wrote:

> To address unstructured problems (graph, mesh, sparse matrix), where parallelism opportunities depend more upon the data presented than upon the properties of the algorithm, we need two more parallelism constructs between DO CONCURRENT and coarray images: a fork-join construct, which one can fake with a SELECT CASE inside DO CONCURRENT, and either a "spawn" construct or a task unit a la ada.


I don?t see a ?need? for either of these unless that is the only way you can think about parallelism.  Plasma codes with very dynamic grids have been written using coarrays without either of these.  You can always make work queues and shift work (particles in the plasma)  between images for load balancing. 

> 
> One of the presenters (it might have been Hadia Ahmed) described persistent MPI transactions.  Does anybody's coarray implementation use this (or its equivalent in a different transport mechanism)?


I don?t understand what you mean by a ?persistent? ?transaction?.  

Cheers,
Bill



Bill Long                                                                       longb at cray.com
Fortran Technical Support  &                                  voice:  651-605-9024
Bioinformatics Software Development                     fax:  651-605-9142
Cray Inc./ Cray Plaza, Suite 210/ 380 Jackson St./ St. Paul, MN 55101