Hi Martin,
We read the various tools tickets today and so far, everything seems to look good. Here is the minor feedback we got:
Ticket 378: the "OUT" is in the wrong font
Fixed.
For MQD:
Section 3.2.4: of the MPI process -> of an MPI process
Also, there were questions on the definition of a "unique image" - at the end people seemed to be OK with it, but would like to see a cleaner definition for the next forward looking version of MQD. In particular, it should cover the case where multiple MPI processes are in one OS process.
Straw votes: 377: 12 yes, 0 no, 5 abstain 378: 13 yes, 0 no, 2 abstain
Looks like they will pass then!
Also, someone commented on the example on page 16 of the tools3.pdf document:
The loop terminates when it hits a non MPI_SUCCESS return from get_info - this is not quite as intended. The loop should jump over holes in the index space (e.g., caused by unloading). I.e., it should test for SUCCESS or INVALID_INDEX and in both cases continue, abort otherwise.
Bill suggested to fix this as ticket 0.
Okay, I'll fix it as ticket 0. Thanks for the summary! Kathryn
Martin
_______________________________________________ mpiwg-tools mailing list [email protected] http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-tools
______________________________________________________________ Kathryn Mohror, [email protected], http://people.llnl.gov/mohror1 CASC @ Lawrence Livermore National Laboratory, Livermore, CA, USA