RE: [mpi-21] Proposal EH2: add const keyword to the C bindings

["Bronis R. de Supinski" <bronis@xxxxxxxx>]

Dick:

Re:
> I think it is likely the forum will conclude that the send buffer access
> rules should be relaxed but there should be more to the discussion than
> "Do you care about users or don't you?"

I have been silent on this question up to now. I have
taken the opinion that if some want to spend their
time creating solutions to non-problems that will
eventually be discarded then then let them. However,
it is quickly proving that alot of other people's time
will be consumed by this.

I have implemented a lot of MPI code. I work with many
serious MPI application and library programmers. I have
implemented tools that detect MPI programming errors.
I have several people who use that tool and find it
helpful. I have read many papers on the subject of MPI
coding errors. I have seen some pretty bizarre MPI errors.

Not ONCE have I heard that "Restricted access to buffers
of non-blocking MPI send operations was the source of my
problem." Not only do implementations not take advantage
of the opportunity, the restriction is NOT violated. This
issue is not worth the time it is being given until someone
can do more than state that it must be causing problems for
"many applications and commercial applications." I see no
reason to sacrifice any potential performance for something
no one slips on.

As a representative of the user committee, I intend to
vote AGAINST these proposed changes.

Bronis