[MPI3 Fortran] [Mpi-comments] MPI 3.0: Fortran 2008 interface - issue with the LOGICAL kind

[Hubert Ritzdorf]

> I believe the NEC Fortran MPI API may do similar things.

This is right.
The tool guys are mainly looking for a well-defined name.
I think that it is a bad idea to kill backward compatibility, Fortran profiling interface
and optimization possibilities of MPI implementers in order to get  this well-defined name.

It would be possibly simpler to add a specific BIND(Fortran, name="MPI_Test_f08") to Fortran
which sets the linker name instead of using BIND(C, name="MPI_Test_f08") and we could
avoid all the interoperability problems which were found till now (and in future).

MPI_Test is a relatively simple function. We have much more complex functions which
might increase scalability problems (for example additional memory
allocation for MPI_Alltoallw in order to transform datatypes, possibly counts, displacements)
for this requested approach. 

The upper routines/functions might become complex or
cpu-time relevant  (example: implementation of MPI_SUBARRAYS_SUPPORTED).
In this case, the usage of performance (or debugging) tools which ignore the work in
this upper functions (since these tools see only the C MPI  functions) might
become problematic.

Hubert
________________________________________
From: mpi3-fortran-bounces at lists.mpi-forum.org [mpi3-fortran-bounces at lists.mpi-forum.org] on behalf of Jeff Squyres (jsquyres) [jsquyres at cisco.com]
Sent: Thursday, March 21, 2013 4:38 PM
To: MPI-3 Fortran working group
Cc: Martin Schulz
Subject: Re: [MPI3 Fortran] [Mpi-comments] MPI 3.0: Fortran     2008 interface  -       issue with the  LOGICAL kind

On Mar 21, 2013, at 8:26 AM, Craig Rasmussen <rasmus at cas.uoregon.edu> wrote:

> I talked with Martin yesterday and he would be happy to have the requirement in the standard that the Fortran wrappers MUST call the MPI C interface.  This would much simplify things for the tools community.  (I had earlier thought he would object to this solution.)

No!  This is NOT a good idea to mandate.

Open MPI currently has a bunch of Fortran functions that do NOT call the corresponding MPI_<foo> C function.  Instead, they call some other back-end, internal function.

I believe the NEC Fortran MPI API may do similar things.

--
Jeff Squyres
jsquyres at cisco.com
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/


_______________________________________________
mpi3-fortran mailing list
mpi3-fortran at lists.mpi-forum.org
http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-fortran


 Click https://www.mailcontrol.com/sr/Geaaq1rkMOPGX2PQPOmvUpJBCTqJzJUeYtFmk42MgAlOvSHOzXVuO4Ep5Wd3HnToAzNTk47hsmGOdoKZwoXR0w==  to report this email as spam.