Re: caching on MPI handles

Rajeev Thakur (thakur@mcs.anl.gov)
Fri, 18 Oct 1996 16:55:42 -0500

> From: "Eric Salo" <salo@mrjones.engr.sgi.com>
>
> I didn't think this would work, but now I can't remember why...
>
> Are there any cases for which a non-null copy_fn would even be useful? If I
> understand you correctly, all you really care about is the delete_fn, right?

Yes, I mainly care about the delete function. I don't intend to use
the copy function. So, if we say "when a new datatype is created
from an old one, the attribute does not get propagated to the new
one", that would be fine with me.

Rajeev