On Sat, Dec 8, 2012 at 11:12 AM, Torsten Hoefler <[email protected]> wrote:
Hi all,
We discussed the neighborhood reductions at the last Forum and the straw vote if we should include them in the next revision was:
- yes: 18 - no: 0 - abstain: 3
I addressed all the issues in the draft that were brought up at the Forum. The new draft is now at http://www.unixer.de/sec/topol.pdf . Look for ticket "XXX".
The other interfaces for MPI_Ineighbor_reduce do not contain the "I" (page 40, line 25 and 30); MPI_Ineighbor_reducev does not have the "v" (page 41, line 26 and 31).
One open question remains: would a single send buffer for neighbor_reduce suffice or do we need one buffer per destination process? The second case could always be done with neighbor_reducev (with small additional costs). This questions is more to the potential users (Jed etc.).
My understanding of Neighbor_reducev is that I send different sizes to each neighbor, but receive the same size from every neighbor (reducing into exactly one buffer). That isn't really a useful operation in domain decomposed methods. The useful operation is that I reduce different sized received buffers into different (but sometimes overlapping) parts of my local buffer. The single send buffer (with different datatype arguments) imposes no restriction and is natural.