Thanks for your answer.yes. I have two processor in
one node.
If I said there is posible two processors run slower
than one processor because one become master and just
send the data and recv data only and another one is
just recv data and do calculation,then send back to
master. No parallel processing happen here.
I assume that the adition time is for sending and
recving data. Am I right?
p/s:compare with distributed memory, generally, witch
one is more faster?
thanks.
--- Jeff Squyres <jsquyres_at_[hidden]> wrote:
> With your references to shared memory, you imply
> that you're only running
> on one node. Do you actually have two processors on
> your machine?
>
> If you only have one processor, then your 2
> processes are likely to be
> thrashing while trying to run on your one processor.
> If this is so, then
> the 167 seconds is likely to be mostly thrashing
> time, not communication
> time.
>
>
> On Wed, 9 Apr 2003, choy hau yan wrote:
>
> > I use 2 processor for parallel in shared memory.
> >
> > When I run in one processor (no parallel) the time
> of
> > calculation is 5157 seconds.
> >
> > when run in 2 processor,(one master, one slave)
> the
> > time is 5324 seconds.
> > So, the time communications is 167 seconds. As I
> know
> > there is nearly no communication in shared memory.
> So
> > what is the reason that contribute the time (167
> > seconds.) Thanks.
>
> --
> {+} Jeff Squyres
> {+} jsquyres_at_[hidden]
> {+} http://www.lam-mpi.org/
> _______________________________________________
> This list is archived at
http://www.lam-mpi.org/MailArchives/lam/
__________________________________________________
Do you Yahoo!?
Yahoo! Tax Center - File online, calculators, forms, and more
http://tax.yahoo.com
|
