Paper showing Linpack scalability of mainstream clusters

Alan Ward award at
Fri Sep 28 08:42:03 PDT 2001

In many (european) countries, the "efficiency factor" -- or "cos(phi)"
as we call it -- must be over 0.9 . A transformer, or computer power supply,
must be designed to comply with this, at least under normal working
conditions. An overloaded transformer won't.

I would have to check this, but get the impression that with many power
supplies cos(phi) goes way down during power on, when they tend to
suck in current.

Alan Ward

Greg Lindahl ha escrit:

> On Thu, Sep 27, 2001 at 09:24:18PM -0400, Carlos O'Donell Jr. wrote:
> > And if the supply is _good_enough_ then it will approach 1 and give
> > you the worst case GFlops/kW ;)
> I don't believe that modern power supplies actually have an
> "efficiency factor" that close to 1. I'll have to ask my business guy
> (David Rhoades), he used to specialize in weird trivia like building
> machine rooms, something that most computer people tend to avoid...
> greg
> _______________________________________________
> Beowulf mailing list, Beowulf at
> To change your subscription (digest mode or unsubscribe) visit

More information about the Beowulf mailing list