[MPI3 Fortran] Request for a straw vote.
jsquyres at cisco.com
Tue Jun 23 07:23:22 CDT 2009
On Jun 22, 2009, at 12:08 PM, Lionel, Steve wrote:
> >But I can also see that it would be a PITA for programmers to have to
> >specify *every* argument to MPI functions, and potentially have to
> >translate between their MPI-argument-variables and non-MPI-argument-
> >variables. Shrug.
> No - programmers do NOT have to do this just because kinds are
> specified. If default integer happens to match the declared kind, it
> will just work without coding changes. If programmers want to use
> the kinds, they can, and would be encouraged to, but it is not
If an MPI implementation uses MPI_TAG_KIND for MPI message tags that
are 4 bytes and are the same as default INTEGERs, then I can
understand the logic here.
But what if a user compiles a code that uses INTEGERs where
INTEGER(MPI_TAG_KIND) parameters are expected with "ifort -
i8" (transmorgifying default INTEGERs to be 8 bytes)? Will their code
refuse to compile? If so, do users expect / compensate for this kind
More information about the mpiwg-fortran