(j3.2006) IEEE modules and NORM2

Aleksandar Donev donev1
Thu Oct 9 13:56:57 EDT 2008


On Thursday 09 October 2008 10:51, Van Snyder wrote:
> always going to be a lot slower than simply scaling. ?This is
> because there is overhead in the calls to get and set flags.
One of the goals of a proper exception handling mechanism is to avoid the 
overhead of always checking flags, even when all goes well. Rather, do extra 
work only when something does go wrong. Isn't that what interrupts are 
designed for: interrupting the computational stream when something happens?
Aleks

-- 
Aleksandar Donev, Ph.D.
Lawrence Postdoctoral Fellow @ Lawrence Livermore National Laboratory
High Performance Computational Materials Science and Chemistry
E-mail: donev1 at llnl.gov
Phone: (925) 424-6816  Fax: (925) 423-0785
Address: P.O.Box 808, L-367, Livermore, CA 94551-9900
Web: http://cherrypit.princeton.edu/donev




More information about the J3 mailing list