Optimizing CNS

Kay Diederichs Kay.Diederichs at uni-konstanz.de
Mon Mar 1 03:20:56 EST 1999


Steffen Graether wrote:
> 
> Could someone suggest how I could optimize cns on a linux pc running
> redhat 5.2? I find the three-fold execution time difference between our
> overused R10000-250 MHz Octane and underused PentiumII-333 Mhz PC rather
> large.
> 
> Steffen
> 

Why do you think the 333MHz P-II should be much faster than that? 

I just checked
http://www.spec.org/osg/cpu95/results/res98q1/cpu95-980206-02407.html
versus
http://www.spec.org/osg/cpu95/results/res98q1/cpu95-980302-02523.html
and it appears to me that the Octane has 20.3 SPECfp95, versus 9.25 of
the P-II. So using the Intel compiler (which I heard is optimized for
SPEC and won't necessarily give good real-world performance) you could
get at most 46% of the SGI's performance.  

Has anybody tried the 21264 Alpha workstations for CNS (they are rated
at 52.2 SPECfp95)?

Kay
-- 
Kay Diederichs         http://strucbio.biologie.uni-konstanz.de/~kay 
email: Kay.Diederichs at uni-konstanz.de  Tel +49 7531 88 4049 Fax 3183
Fakultaet fuer Biologie, Universitaet Konstanz 
Box M656, D-78457 Konstanz, Germany



More information about the X-plor mailing list