(j3.2006) (SC22WG5.3914) [ukfortran] [MPI3 Fortran] [MPI3 Fortran] MPI non-blocking transfers

N.M. Maclaren nmm1
Fri Jan 23 15:13:53 EST 2009


On Jan 23 2009, Bill Long wrote:
>
>While I agree that we should make the effort to find a solution for MPI 
>users (Cray probably has the highest representation of them),  I would 
>not go as far as saying that the lack thereof makes Fortran an 
>"inadequate language".  After all, Fortran 2008 has a much better way of 
>doing parallel programming than MPI.  In that sense, it is a "superior 
>language". 

That is a matter of opinion, and only time will tell whether you are
correct.

However, this issue applies to ANY form of asynchronous I/O (transfer if
you like), including POSIX asynchronous I/O.  I don't know how many are
currently important (except for MPI), but there have been hundreds and
are likely to be more in the future.


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