Hi all, I have uploaded a new draft version of MPI_T, hopefully addressing all/most of the comments from last time, to the Wiki at: https://svn.mpi-forum.org/trac/mpi-forum-web/wiki/MPI3Tools/mpit I have also attached the document. The color markings are now relative to the approved and current version of MPI. The following issues are still open or at least should be discussed by the group and it would be great if we could get through those next Monday during our TelCon: - Rolf requested to sort the arguments for each function to first IN then OUT - this causes problems with string returns (would split buffer and length) - unclear what the right label for Recv is - I added types to each prototype definition, but it was unclear to me what to put for the character array. - Should we make integers unsigned in the interface? - Should we ad const where appropriate? - Are we still OK with the text on the associating MPI objects with variables? I am not sure anymore what the result of the discussion was last time. - What other changes in the rest of the standard document do we still need to make - so far we only touched Init and Finalize, as well as the language appendix. Anything else? Also, it would be great if as many of you as possible could read the document for correctness and consistency. Feel free to send me corrections or, if you have too many, let me know and I'll send you the TeX file to edit. We have about two weeks now to get the document to a state so it can pass the reading and I hope this is achievable. If I missed any issue, please speak up. Thanks, Martin ________________________________________________________________________ Martin Schulz, [email protected], http://people.llnl.gov/schulzm CASC @ Lawrence Livermore National Laboratory, Livermore, USA