[Mpi-forum] Fortran change for discussion
Jeff Squyres (jsquyres)
jsquyres at cisco.com
Tue Sep 11 05:24:47 CDT 2012
FWIW, we chose the copying language not because of the c language, but rather because we have to explain that the MPI data type is applied, and that seemed far easier to explain against a (virtual) contiguous buffer.
Sent from my phone. No type good.
On Sep 11, 2012, at 3:38 AM, "N.M. Maclaren" <nmm1 at cam.ac.uk> wrote:
> On Sep 11 2012, Jeff Squyres wrote:
>> You explain the situation in Fortran-eese, but the current text is an attempt to explain it in MPI-eese (i.e., in terms of copying). I think the MPI-reader-friendly text should be used.
> Sort-of, I agree. The problem with the current description is precisely
> that it uses copying rather than aliasing as a basis, but I assume that
> is for C programmers. There is definitely a problem in trying to explain
> something in C-friendly terms that is conceptually outside C's rudimentary
> array model.
>>> If the current text is kept, I think the clarification is important.
> The other possibility is to stress that the copying can occur at any
> time between the initial call and the Wait. That is, after, all precisely
> what asynchronous means in this context!
> mpi-forum mailing list
> mpi-forum at lists.mpi-forum.org
More information about the mpi-forum