[Mpi3-hybridpm] new proposal on MPI + OpenMP,TBB,UPC, CAF

[Cownie, James H]

The discussions on binding to PGAS languages seem to be missing discussion of one of the significant issues, the UPC version of which is "Can an MPI call be passed a pointer-to-shared ?"

I think it's fairly clear that the answer should be "No"; all MPI functions require local data and can only accept pointers to local data. (In effect this is saying that MPI provides a C interface, rather than a UPC interface; the only types which cross the boundary into the MPI library are native C types).

Assuming we all agree that this is the intent, we should say it somewhere.

-- Jim

James Cownie <james.h.cownie at intel.com>
SSG/DPD/PAT
Tel: +44 117 9071438





---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ
VAT No: 860 2173 47

This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpi-forum.org/pipermail/mpiwg-hybridpm/attachments/20091019/7dd5e6b0/attachment-0001.html>