Hi All, We discovered a series of issues in the RMA chapter the last weeks. However, the document was closed for edits before we could fix all of them. Some of us think that it would be advisable to have an errata draft *before* the meeting in Vienna next week (there may be a negligible chance of fixing the issues in MPI-3.0 this way). Nevertheless, we need to get together and discuss the issues. Thus, I'd propose to have a one-hour telecon to discuss those issues on either Monday or Tuesday next week (I know, short notice ... but the time is getting shorter). It would be great if the individuals who raised the issues could be there! I created a doodle at: http://www.doodle.com/29bg7iew6ik427fm . Please complete it by *** Sunday (tomorrow) ***. We will see of we get a reasonable number of people together to discuss this. The agenda would be: 0) Discuss a strategy for those issues/changes. 1) The win_free deallocation issue (I think we agree on a solution, this just needs to be implemented) 2) MPI_AINT issues (that may require a discussion) 3) Fortran issues with create_dynamic (as raised by Hubert) 4) Explicit definition of lock vs. lock_exclusive (I would vote against it at this point but we should discuss) Anything else? Please feel free to add! Thanks & Best, Torsten -- ### qreharg rug ebs fv crryF ------------- http://www.unixer.de/ ----- Torsten Hoefler | Assistant Professor Dept. of Computer Science | ETH Z�rich Universit�tsstrasse 6 | Zurich-8092, Switzerland CAB E 64.1 | Phone: +41 76 309 79 29