Jeff Squyres wrote:
> If you're exchanging data at the end of an iteration, then you
> effectively have a synchronization anyway -- no need for an extra
> barrier synchronization.
Ralph Castain wrote:
> Ummm....not to put gasoline on the fire, but...if the data exchange
> is blocking, why do you need to call a barrier op first? Just use an
> appropriate blocking data exchange call (collective or whatever) and
> it will "barrier" anyway.
I could also imagine processes interacting/communicating/whatever via
some other mechanism than MPI calls. Heck, OMPI itself is an example.
Maybe they interact via a file system or something.
Anyhow, I agree with the majority sentiment: single raised eyebrow if
there's an app that beats heavily on Barrier.
|
![[Flag]](../../../../../community/mirrors/flag-us.gif){kind=small}