[Mpi3-hybridpm] [MPI Forum] #212: MPI3 Hybrid Programming: multiple endpoints per collective, option 5
MPI Forum
mpi-22 at lists.mpi-forum.org
Thu Jan 7 07:45:47 CST 2010
#212: MPI3 Hybrid Programming: multiple endpoints per collective, option 5
----------------------------------------------------------+-----------------
Reporter: dougmill@… | Owner: dougmill@…
Type: Enhancements to standard | Status: new
Priority: Not ready / author rework | Milestone: 2010/01/19 Atlanta, USA
Version: MPI 3.0 | Keywords:
Implementation: Unnecessary | Author_bill_gropp: 0
Author_rich_graham: 0 | Author_adam_moody: 0
Author_torsten_hoefler: 0 | Author_dick_treumann: 0
Author_jesper_larsson_traeff: 0 | Author_george_bosilca: 0
Author_david_solt: 0 | Author_bronis_de_supinski: 0
Author_rajeev_thakur: 0 | Author_jeff_squyres: 0
Author_alexander_supalov: 0 | Author_rolf_rabenseifner: 0
----------------------------------------------------------+-----------------
We declare that all endpoints must be "progressed" whenever any
communication is done. This way, the implementation can use whatever
endpoints internally to perform the communications. It does require that
there be some new interface by which an endpoint may make progress without
having explicit requests.
Since the overall "endpoints" proposal is a departure/extension of the
MPI2 "single endpoint" model, it may be reasonable to attach these
additional requirements on programs that wish to use multiple endpoints.
--
Ticket URL: <https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/212>
MPI Forum <https://svn.mpi-forum.org/>
MPI Forum
More information about the mpiwg-hybridpm
mailing list