Re: forall and do loop

Ian Bush wrote:

As if by magic, Walter Spector appeared !

highegg wrote:
...
One probblem with HPF is that few real-life parallel computations can
be neatly expressed by a sequence of parallelized array expressions
and assignments (like FORALL). That's why even Fortran parallel CFD
codes use MPI.

Not really. MPI is used because of the Sirens call of cheap computing
by "hooking a bunch of PCs together".

I suspect it is at least as often due to the codes encountering the
message passing paradigm on such machines as the IPSC/2.

And the IPSC/2 is a "distributed memory MIMD" computer.

In other words, distributed memory
MIMD computing. And MPI happens to work ok on shared memory machines.
However most who have used MPI would admit that it is a huge pain compared
to other forms of shared memory parallelism.


Hmmm, therefore I'm in the minority, as are most people around here.
Personally I suspect it is much more to do with familiarity and what
kind of architectures you have to support. Personally I find OpenMP
more confusing than MPI,

With OpenMP one can often place a few directives in front of a few key
loops and get very nice speedups. With MPI one often has to restructure
entire programs to accomodate the division of data between threads...

and also that the latter allows you to run
on a wider range of architectures,

Right. As I said, MPI programs can also run on shared memory systems.
However, on a shared memory system, why copy messages around when you can
simply and directly access the data you need? Thus the message passing
piece introduces overhead that need not be there. (Note that in MPI-2,
the "one-sided" message passing calls were introduced to mitigate, but not
eliminate, this problem.)

W.
.

Quantcast