On Jul 1, 2013, at 1:24 PM, "David Goodell (dgoodell)" <dgoodell(a)cisco.com> wrote:
> ----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)?
Today's attribute calls give you a callback when MPI_*_FREE is invoked -- when is potentially not when the object is actually destroyed.
The Fab+Jeff idea was wondering if anyone cares about the difference between these two; are there any useful use cases where someone could benefit from knowing when the object was actually destroyed?
--
Jeff Squyres
jsquyres(a)cisco.com
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
On Jun 27, 2013, at 1:23 PM, Jeff Squyres (jsquyres) <jsquyres(a)cisco.com> wrote:
> 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
Quoting from those notes:
----8<----
> Marc-Andre asks: because of the Fortran debacle, and because tools will now have Fortran wrappers, should we do MPI_T for Fortran?
> � PRO: be able to call MPI_T directly from Fortran wrapper functions
> � CON: Jeff thinks we (tools WG) should stay out of Fortran
----8<----
I agree with Jeff here. Anyone who is savvy enough to understand that a tools interface exists can also write their tool code in C. Getting a Fortran binding right will take a lot of work for very little benefit to anyone.
----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)?
-Dave
