(j3.2006) (SC22WG5.3908) [ukfortran] [MPI3 Fortran] [MPI3 Fortran] MPI non-blocking transfers

N.M. Maclaren nmm1
Fri Jan 23 06:46:39 EST 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