Some of the rationales do not apply. In particular, I don’t believe these are important for Accept: 1) Low overhead (justifies Isend/Irecv etc.) 2) Scarcity of threads (e.g., the BlueGene/L rationale) There are some interactions with multiple-competion routines and limitations in the generalized requests, but fixing generalized requests would be a more general solution. Bill William Gropp Director, Parallel Computing Institute Thomas M. Siebel Chair in Computer Science Chief Scientist, NCSA University of Illinois Urbana-Champaign On Feb 25, 2016, at 2:40 PM, Jeff Squyres (jsquyres) <[email protected]> wrote:
On Feb 25, 2016, at 2:01 PM, William Gropp <[email protected]> wrote:
Part of that proposal must explain why using Accept in a separate thread (as suggested by this very post) isn’t sufficient.
Is it different than the rationale for other non-blocking MPI operations?
-- Jeff Squyres [email protected] For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
_______________________________________________ mpi-forum mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi-forum