Dave, all,
----8<----
� Jeff also brings up the idea of a callback (or some kind of MPI_T notification) to know when an MPI object is destroyed (per email conversation w/ Jeff, Kathryn, Martin). � Marc-Andre will think about whether it will be useful for any tools to know when MPI objects get destroyed. � Marc-Andre will also think about whether it would be useful for there to be an MPI_T mechanism to get some kind of unique ID for an MPI object (that will be durable after the handle is freed). This way, a tool can track the entire lifecycle of an object -- not just its handle. ----8<----
I was unable to attend the call, but why isn't attaching an attribute with a destructor callback to the object in question sufficient? Is it because we have MPI opaque objects which do not support attributes (e.g., MPI_Op)?
The fact that not all handles support attributes is afaik also part of Jeff's and Fab's proposal, but the specific question here is where there is a use-case for a tool knowing the difference between calling free and the actual destruction of the object. In other words: If we design a new attributes interface that supports _all_ handles, should this also include a callback for destruction, or is the callback on free sufficient. Cheers, Marc-Andre -- Marc-Andre Hermanns German Research School for Simulation Sciences GmbH c/o Laboratory for Parallel Programming 52062 Aachen | Germany Tel +49 241 80 99753 Fax +49 241 80 6 99753 Web www.grs-sim.de Members: Forschungszentrum J�lich GmbH | RWTH Aachen University Registered in the commercial register of the local court of D�ren (Amtsgericht D�ren) under registration number HRB 5268 Registered office: J�lich Executive board: Prof. Marek Behr, Ph.D | Prof. Dr. Sebastian M. Schmidt