On Jan 23, 2009, at 7:45 AM, N.M. Maclaren wrote:
MPI_COMM_WORLD is set to a large integer (1140850688) in MPICH2 so
I wonder if there is something in HDF5 and/or NetCDF4 that
doesn't like 0 for the communicator handle. At any rate, you have
given me some ideas of things to check in the debugger tomorrow.
Is there a safe way to change what MPI_COMM_WORLD is set to in
OpenMPI?
No. Open MPI's Fortran MPI_COMM_WORLD is pretty much hard-wired to
0.
That's a mistake. But probably non-trivial to fix.
Could you explain what you meant by that? There is no "fix"; Open
MPI's Fortran MPI_COMM_WORLD has always been 0. More specifically,
there is no coordination of the value of MPI_COMM_WORLD between MPI
implementations, unless some choose to emulate MPICH (or MPICH2 --
because they're different).
I'm assuming what you're really referring to is the fact that there is
no currently binary compatibility between different MPI
implementations (forgive me if my assumption is wrong). There's some
debate about this in the MPI Forum right now, but there is a large
impasse about creating an ABI. Every time we ask, there's a small
handful of vocal users who say "yes, we want it," but the vast
majority of users (in my experience) either don't care or are
vehemently against the idea of an MPI ABI.
--
Jeff Squyres
Cisco Systems