Daniel Kidger Daniel.Kidger at
Wed Feb 19 06:30:18 PST 2003


   Superscaling is seen most often when you run the old-fashioned style of
scalability test: one is which the overall problem size stays constant even
though you are increasing the number of CPUs you are running on.
In this case the problem size per node falls as the node count increases
such that more and more of the data will reside in cache.
Such problems are considered 'memory-bandwidth'-bound rather than CPU or


Dr. Dan Kidger, Quadrics Ltd.      daniel.kidger at
One Bridewell St., Bristol, BS1 2AA, UK         0117 915 5505
----------------------- --------------------

-----Original Message-----
From: Simon Hogg [mailto:seth at]
Sent: 19 February 2003 13:30
To: Beowulf mailing list
Subject: Super-scaling

Is there a rough rule of thumb which dictates when a program (if ever) 
shows superscaling with number of nodes.  Of course, I would not expect 
this to carry on ad infinitum, but does anyone see superscalar behaviour up 
to, a certain number of nodes.

What would be the conditions for this to occur?


Beowulf mailing list, Beowulf at
To change your subscription (digest mode or unsubscribe) visit

More information about the Beowulf mailing list