[Mpi3-tools] Current Version of the MPIR document

[Ashley Pittman]

On 29 Jun 2010, at 01:25, John DelSignore wrote:
> "
> Totalview also needs the debug information for the MPIR_PROCDESC type,
> since it uses that to work out the size and fields in the procedesc
> array. 
> "

I could argue that that's an implementation detail about the debugger and not part of the "specification" but I don't believe that would get me very far.  The existing documentation as it is is clearly contradictory on this point and given what we are trying to do with this effort I think it's fair to take the more permissive (from the MPI implementors perspective that is) of the two interpretations so I'm happy with the text as you propose it.

> And if you don't believe me, ask your father-in-law! ;-)

I'll mention it to him but we should not be discussing what the intention was but rather what an implementor might have thought was reasonable behaviour for an MPI library based on the documentation as it stands.

Ashley.

-- 

Ashley Pittman, Bath, UK.

Padb - A parallel job inspection tool for cluster computing
http://padb.pittman.org.uk