[Beowulf] Nehalem and Shanghai code performance for our rzf example

Joe Landman landman at scalableinformatics.com
Sat Jan 17 10:16:28 PST 2009


Kevin Abbey wrote:
> Hi Joe,
> Can that 9% difference be due to the Intel capability to overclock one 
> core and turn the others off?

Hi Kevin:

   Not sure.  May investigate at some point, but we should see a marked 
decrease in speedup over 4 threads on 4 cores if this is the case.

> Or is does this Intel feature require manual switch somewhere?

   No 'switches'.  Pure gcc, using -O3 flag, nothing "funky" in the code.

Joe


-- 
Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics LLC,
email: landman at scalableinformatics.com
web  : http://www.scalableinformatics.com
        http://jackrabbit.scalableinformatics.com
phone: +1 734 786 8423 x121
fax  : +1 866 888 3112
cell : +1 734 612 4615



More information about the Beowulf mailing list