On Aug 27, 2008, at 8:55 AM, Robert Kubrick wrote:
However from an application point of view I see an odd result here.
On the sender side I can use a buffered send to "queue" messages for
delivery and decide how many messages my buffer should contain
before the MPI_Bsend blocks if it's running out of space.
On the receiving side I have no control over the number of messages
that MPI can buffer. This is basically left to the implementation
details as you very well described. Shouldn't the user be allowed to
specify a memory space to buffer messages on the receiving side,
just like on the send?
It's worth pointing out that the MPI Forum is again meeting to work on
MPI-2.1 (small bug fixes over MPI-2.0), MPI-2.1 (bigger bug fixes over
MPI 2.0/2.1) and MPI-3.0 (entirely new stuff).
If you'd like to make a proposal to the Forum (e.g., to allow the
receive side to control buffering), I encourage you to do so. The
more specific your proposal, the better. It strikes me that such a
proposal fits within the scope of MPI-3.0.
--
Jeff Squyres
Cisco Systems