> I was hoping that someone might have some examples of real application
> behaviour rather than micro benchmarks. It can be crazy hard to get that
> information from users.
[Tom]
I don't have direct performance information on knem, but with Intel's (formerly
QLogic's) PSM layer as delivered in o
On Jul 15, 2013, at 3:43 AM, Paul Kapinos wrote:
> Jeff, I would turn the question the other way around:
>
> - are there any penalties when using KNEM?
Good question. I can't think of any, but then again, I haven't tried this at
really large scale.
If you guys try it, we'd like to hear your
On 07/12/13 12:55, Jeff Squyres (jsquyres) wrote:
FWIW: a long time ago (read: many Open MPI / knem versions ago),
I did a few benchmarks with knem vs. no knem Open MPI installations.
IIRC, I used the typical suspects like NetPIPE, the NPBs, etc.
There was a modest performance improvement (I don'