User: Password:
|
|
Subscribe / Log in / New account

Memory part 5: What programmers can do

Memory part 5: What programmers can do

Posted Oct 27, 2007 14:15 UTC (Sat) by bartoldeman (subscriber, #4205)
In reply to: Memory part 5: What programmers can do by Coren
Parent article: Memory part 5: What programmers can do

It is even 20 times faster if you use ATLAS 3.8:
http://math-atlas.sourceforge.net/
Its DGEMM routine does the job in around 708,000,000 cycles, another factor of 2 faster (my
other numbers, also on a Core 2 (a Duo, but single threaded), were very similar to Ulrich's so
I can state this with some confidence). Of course there's been a lot of research and tweaking
to obtain this score.

ATLAS' SUMMARY.LOG reports for DGEMM:
 Performance: 4846.05MFLOPS (302.88 percent of of detected clock rate)
and this is on a 1.6GHz Core 2 Duo, not 2.66GHz!

GOTOBLAS may also be worth looking at, for comparison. It looks more into TLB misses than
ATLAS does.


(Log in to post comments)


Copyright © 2018, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds