Re: caching on MPI handles
Rajeev Thakur (thakur@mcs.anl.gov)
Fri, 18 Oct 1996 17:15:00 -0500
> With communicators, the copy_fn is only invoked for MPI_COMM_DUP,
> right? Since we don't have a MPI_TYPE_DUP function, we could at
> least claim that we're being consistent. So the next question to
> ask is, should there be a MPI_TYPE_DUP? I seem to recall someone
> asking for this a while back.
Well, I actually need an MPI_Type_dup function :-) to save a copy of
the "etype" and "filetype" for the file. The way I do it now is by
calling MPI_Type_contiguous with a count of 1.
Rajeev
PS: But it wasn't me who asked for it earlier :-)