[MPI3 Fortran] Sample implementation

[Lionel, Steve]

I'm sorry I missed it - I didn't see the emails about the time and
number until after the call ended.


Steve Lionel
Developer Products Division
Intel Corporation
Nashua, NH 



> -----Original Message-----
> From: mpi3-fortran-bounces at lists.mpi-forum.org [mailto:mpi3-fortran-
> bounces at lists.mpi-forum.org] On Behalf Of Jeff Squyres
> Sent: Tuesday, April 22, 2008 10:24 AM
> To: MPI-3 Fortran working group
> Subject: [MPI3 Fortran] Sample implementation
> Importance: Low
> 
> We had a short call because it was just Torsten, Jeff, and Craig
> (i.e., one Fortran guy and 2 guys who are interested but not experts).
> 
> Craig's going to reach out to the other Fortran experts and ensure
> that we're moving forward.  He's also going to work on a small sample
> implementation to ensure that we're moving in the right direction --
> some small wrappers around a handful of functions the ensure that the
> concepts are right, it works, etc.  With a small enough number of
> functions, keeping them updated with the current ideas and discussion
> shouldn't be too hard.  Additionally, although Craig is likely to do
> this work in Open MPI, the code should be more-or-less portable (i.e.,
> likely with a little bit of work) to other MPI's to test with.
> 
> Here's a list of functions that I suggest (others can be included of
> course):
> 
> 6-function MPI
> - MPI_INIT
> - MPI_FINALIZE
> - MPI_SEND
> - MPI_RECV
> - MPI_COMM_RANK
> - MPI_COMM_SIZE
> Some non-blocking functions
> - MPI_ISEND
> - MPI_IRECV
> - MPI_WAITALL
> A function with a string
> - MPI_GET_PROCESSOR_NAME
> Memory pointers
> - MPI_ALLOC_MEM
> - MPI_FREE_MEM
> Varargs
> - MPI_PCONTROL
> Functions dealing with function pointers
> - MPI_COMM_ERRHANDLER_SET
> - MPI_COMM_ERRHANDLER_GET
> 
> Along with at least the following pre-defined MPI handles (others can
> be included of course):
> 
> Basic handles
> - MPI_INTEGER
> - MPI_COMM_WORLD
> "Weird" handles
> - MPI_BOTTOM
> - MPI_STATUSES_IGNORE
> Function pointer handle
> - MPI_ERRORS_ARE_FATAL
> 
> These should be representative enough of the different kinds of types
> that we need to deal with.
> 
> Did I miss anything?
> 
> --
> Jeff Squyres
> Cisco Systems
> 
> _______________________________________________
> mpi3-fortran mailing list
> mpi3-fortran at lists.mpi-forum.org
> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-fortran