(j3.2006) (SC22WG5.3908) [ukfortran] [MPI3 Fortran] [MPI3 Fortran] MPI non-blocking transfers
N.M. Maclaren
nmm1
Fri Jan 23 11:46:39 UTC 2009
On Jan 22 2009, Jim Xia wrote:
>
>Sad to say, but true to some compiler writers: asynchronous alone will
>have no impact on how the procedure call is dealt with (or optimized).
>Asynchronous attribute will only take effect when there is a corresponding
>WAIT statement somewhere due to the "invisible hands" referred to by Bill.
> I think asynchronous approach to nonblocking transfer may lead to
>nowhere, at least not as easy as it appears.
I know that is is politically difficult, and finding out what people
believed was the purpose of starting this thread. But, if some people are
going to reject any technically possible solution, then there is a very big
problem. And, so far, nobody has proposed anything except that which has
any technical plausibility - all of the alternatives will work only if the
programmer uses MPI in a particular way.
Unless this one is resolved, the current situation will continue, and users
who have problems will quite rightly claim that the reason is that Fortran
is an inadequate language. That is a pity.
Regards,
Nick Maclaren,
University of Cambridge Computing Service,
New Museums Site, Pembroke Street, Cambridge CB2 3QH, England.
Email: nmm1 at cam.ac.uk
Tel.: +44 1223 334761 Fax: +44 1223 334679
More information about the J3
mailing list