[Beowulf] Woodcrest Memory bandwidth

[Greg Lindahl]

On Tue, Aug 15, 2006 at 07:16:59AM -0700, Bill Broadley wrote:

> Interesting, the woodcrest latencies are much higher than I've seen
> elsewhere.  It's been awhile since I looked at the lmbench source,
> I seem to recall it used to do a negative stride, but then one of the
> the architectures detected it and successfully prefetched it.

Yes, and after I complained about HP publishing lmbench numbers that
were broken, it turned out that the next version of lmbench already
used a random stride instead of negative.

So you're OK if you use a recent version.

> I'm guessing the best woodcrest stream numbers will be:
> * Pathscale's compiler with -mp -O3 or possibly -mp -Ofast

Those options are a good start, but generally you can get a few % more
by playing around. Our pathopt2 tool can be used, or you can look at
recent stream submissions from us (none for Woodcrest yet, I think.)

-- greg