[Beowulf] The Case for an MPI ABI

[Greg Lindahl]

Those of you who were at the Open IB conference last week saw me give
a talk entitled "The Case for an MPI ABI". It seems that Patrick and I
have been channeling each other AGAIN; see what happens when I move to
California?

The first question is: Does an ABI provide enough benefit for people
to care? To care enough to sit on a committee?

If the answer is "yes", then I think we'll have one. The minimum
technical issues revolve around the contents of <mpi.h> and the names
of shared libraries. The amount of work for MPICH or OpenMPI to
support that part of an ABI is modest.

If we wanted to go farther, I have a strawman proposal which addresses
a generic startup procedure which would allow user applications, MPI
implementations, and queue systems to all live in peace and harmony.

This talk:

http://www.openib.org/docs/oib_wkshp_022005/mpi-abi-pathscale-lindahl.pdf

mostly talks about why we need an ABI, who wins and loses as a result
of having one, and the pieces that could be in it. Please give it a
look.

-- greg