Fritz Chess Benchmark

Our last benchmark is a chess benchmark which scales very well with both cores and clock speed.

Fritz Chess


Chess programs are branch intensive integer applications, and although the Opteron 2350 is a bit better (clock for clock) than the previous generation of Opterons, it is the Xeon "Clovertown" that comes out on top. The quad-core Xeon is 30% faster.

WinRAR 3.62 Power Requirements
Comments Locked

46 Comments

View All Comments

  • JohanAnandtech - Monday, September 10, 2007 - link

    well said. I don't think AMD will have that advantage for a long time in 2P space :-)
  • JackPack - Monday, September 10, 2007 - link

    The problem is, 45nm Harpertown and 1600 MHz FSB will be rolling in soon.

    Barcelona would have looked great 6 or 9 months ago. But today, it's a little weak unless they can raise the frequency fast.
  • Viditor - Monday, September 10, 2007 - link

    quote:

    45nm Harpertown and 1600 MHz FSB will be rolling in soon


    True, but so will HT 3.0 and the newer mem controller for the Barcelonas...
  • jones377 - Monday, September 10, 2007 - link

    You got your work cut out for you now :)
  • IntelUser2000 - Monday, September 10, 2007 - link

    AMD won't compete against Intel's Tulsa chips anymore. They will have to compete against Tigerton Xeon MP and the newly introduced Clarksbro chipset.

    On the DP server platform, Intel will introduce Harpertown and Seaburg chipset. Seaburg chipset features 1600MHz bus with significantly improved memory controller performance. We'll see how it all turns out but as of now, Barcelona is a bit late to be competitive.
  • wegra - Monday, September 10, 2007 - link

    You should not forget the Penryn. 2.5Ghz Barcelona will face to 3.1+Ghz Penryn. According to result from this article, I expect the performance of 2.5Ghz Barcelona will reach between 2.8 ~ 2.9Ghz Penryn. So wait till (hopefully) next year to see that AMD becomes the performance king. BTW, talking about the multi-processor servers, AMD will lead w/o much difficulties, I expect, thanks to the scalable architecture.

Log in

Don't have an account? Sign up now