Compiling Benchmarks

We get a lot of requests to show some compiling benchmarks. We took the standard Linux 2.6.4 release from kernel.org and compiled it under our 32-bit test bed. We did not cross platform compile for simplicity, so we are only looking at the 32-bit vanilla kernel. We used the commands as below.

# yes "" | make config
# time make

32-bit Linux 2.6.4 Kernel Compile

Here, we see the largest deficiency of the Dothan yet.

The fact that the processor also utilizes much slower DDR333 probably does not help either, and we will have a chance to revisit that theory before the end of the benchmarks. With a moderate amount of overclocking via "scaling_setspeed", we were able to squeeze much better performance out of the chip - and we are still using the 40mm fan!

Update: We found an inconsitency after several days of trials in our test setup. It seems as though the PATA controller on our DFI motherboard is behaving irregularly. We believe this is localized to only this motherboard, but the controller is not behaving properly, and limiting our transfer rates. The GCC compile test is the only test in our benchmark that is HD bottlenecked.
Encryption Benchmarks Compiler Optimizations
Comments Locked

47 Comments

View All Comments

  • KristopherKubicki - Friday, December 24, 2004 - link

    phaxmohdem: these were just linux tests, but i do believe we have all of those render benchmarks coming up in the Windows analysis.

    Kristopher
  • overclockingoodness - Friday, December 24, 2004 - link

    #44: The results could be better on the Windows platform, as stated in the conclusion.
  • sprockkets - Friday, December 24, 2004 - link

    If you want to see the clock speed dynamically adjusted just roll your mouse over the kpowersave daemon running in the tray (at least it works for me under SuSE 9.2). Even my little Via C3 800mhz system will scale from 399 to 800mhz depending on load. It may even work in 9.1 (the part I couldn't enable was the suspend options). Hell, SuSE even can make my Hitachi Desktar drive go quiet to performance mode right in the OS!
  • formulav8 - Friday, December 24, 2004 - link

    As this article shows, alot of people way overhyped this chip. Yes its not bad, but not the P4 Killer that alot of people claimed.

    It is interesting but it doesn't look like Intel will make a Desktop chip based on this cpu yet in the near future. Dual cores would be very interesting though.

    JAson

  • phaxmohdem - Friday, December 24, 2004 - link

    This chip seems to be a god-send for the corporate IT directors needing machines for their monkeys to do Word and Excel documents on. As for me though, I don't think I could purchase a chip that has as spuratic performance levels as this. I do so many different things on my box, especially in content creation, that I much prefer the consistant performance of my current Athlon64 proc. across all applications.

    Just a suggestion, I would love to see some Adobe benchmarks on these chips... After Effects render times, Premeire Render times, Photoshop performance, etc as these are all applications I use nearly daily. Thanks.
  • HardwareD00d - Friday, December 24, 2004 - link

    When someone does a full set of benchmarks of the Pentium M for all categories across the board vs A64 and P4, then I'll seriously consider if this chip is worth its salt. Until then, I am unconvinced that it is anything special. If it is so good, then why hasn't Intel made any attempt to push it as a desktop chip?
  • segagenesis - Friday, December 24, 2004 - link

    It was looking pretty good until you mentioned the price :( Ouch.
  • Ozenmacher - Friday, December 24, 2004 - link

    And go Vikings!
  • Ozenmacher - Friday, December 24, 2004 - link

    Merry Christmas to you too!
  • skunkbuster - Friday, December 24, 2004 - link

    merry christmas!

Log in

Don't have an account? Sign up now