[Mpi-forum] Embiggenment: formal reading

Jeff Squyres (jsquyres) jsquyres at cisco.com
Mon Feb 3 16:25:32 CST 2020

The Embiggenment WG is ready for a formal reading at the Feb 2020 Portland MPI Forum physical meeting.

Issue: https://github.com/mpi-forum/mpi-issues/issues/137
PR:    https://github.com/mpi-forum/mpi-standard/pull/132
PDF:   attached to Feb 3, 2020 comments on the issue/PR
       (this PDF includes all relevant text changes *AND* all the Embiggened bindings)

Search for "ticket137" in the text to find all the text changes.
The Embiggened functions are not marked; they are simply evident throughout the entire document.


To be clear, the Embiggenment WG is *NOT* raising this PDF as a "no no" vote compared to the ABQ meeting.  This is a new PDF, and this will be its first formal reading.

The rationale is twofold:

1. A series of small items have come up (and been resolved) since the ABQ meeting that have not yet been presented to the Forum.  We will present these in Portland.
2. This PDF includes *ALL* the rendered Embiggened APIs (which were not presented at the ABQ meeting).

After much thought/discussion in the WG, it just didn't seem right to bring up such wide-ranging changes in a "no no" vote.  Yes, the Chapter Chairs/Committees have reviewed the Embiggened sections.  But it doesn't seem like this is within the intended scope of the "no no" vote.  A "no no" vote is supposed to be for "small" things.

We recognize that this "resets the clock" on this PR, and that it makes timing for MPI-4.0... awkward.  It still seemed like the responsible thing to do.

Jeff Squyres
jsquyres at cisco.com

More information about the mpi-forum mailing list