James Cuff wrote: > It's a really nice paper. I have one tiny little observation. > > The L3 cache of the 6MB Madison has always made a huge difference. That and linking against MKL on the Itanium, and using icc on the Opteron w/o ACML/MKL, and using the wrong version of PGI so that only 4 threads could be tested on an 8 way system. ... -- Joseph Landman, Ph.D Founder and CEO Scalable Informatics LLC, email: landman at scalableinformatics.com web : http://www.scalableinformatics.com phone: +1 734 786 8423 fax : +1 734 786 8452 cell : +1 734 612 4615