Jeff and Craig, does the Tools Fortran wrapper include calls to the C f2c (and c2f) function through a Fortran BIND(C) interface definition that makes these functions callable from the Fortran written tools wrappers? If yes, then we should continue to think about including these Fortran callable f2c (and c2f) functions as official Fortran Interfaces into the MPI library, because the BIND(C) Fortran interface for these functions seems to me not portable if these C functions are implemented as macros. And for portable programming of calling the f2c functions, we also Need types in Fortran that correspond to the C types MPI_Comm, etc., i.e., the concept of the standardized constants MPI_C_COMM_KIND, etc., to get the type definition INTEGER(KIND=MPI_C_COMM_KIND) in Fortran as equivalent to MPI_Comm in C. To minimize the tools' instrumentation overhead, such conversions should be possible as macros, especially if the conversion is the identity. Implementing such in Fortran functions inside of a Fortran module (i.e., with CONTAINS), allows that the Compiler is inlining the conversion and removing it in the case of the identity function. Best regards Rolf ----- Original Message -----
From: "Jeff Squyres (jsquyres)" <[email protected]> To: "MPI-3 WG" <[email protected]> Sent: Thursday, June 27, 2013 8:23:30 PM Subject: Re: [Mpi3-tools] Tools WG webex: tomorrow! The notes from todays meeting are now posted on the wiki:
https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/MPI3Tools/notes-2013-06-27
Enjoy!
On Jun 26, 2013, at 4:54 PM, Jeff Squyres <[email protected]> wrote:
This is your friendly neighborhood MPI-3 Tools Working Group teleconf reminder for tomorrow:
Thursday, June 27, 2013, 11am US Eastern time Webex link: https://cisco.webex.com/ciscosales/j.php?ED=217124297&UID=0&PW=NMDEyN2UwZmM3... Webex password: tools
Wiki link: https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/MPI3Tools
Agenda:
MPI meeting results - Formal reading of MPI queue side document: went well https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/375 Anh to discuss details - Voted on MPI_T constants erroneously listed for Fortran: passed https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/354 Need to commit to latex and get PDF reviews - Fortran debacle: you've all been doing it wrong (for ~15 years) - Thoughts on new profiling interface for MPI-4 - ...anything else?
-- Jeff Squyres [email protected] For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
-- Jeff Squyres [email protected] For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
_______________________________________________ Mpi3-tools mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-tools
-- Dr. Rolf Rabenseifner . . . . . . . . . .. email [email protected] High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530 University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832 Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner Nobelstr. 19, D-70550 Stuttgart, Germany . . . . (Office: Room 1.307)