Memory Analysis

While testing the Pentium M on Linux, we came to the unofficial conclusion that Dothan was coming to a screeching halt on a lot of our benchmarks because it ran on antiquated DDR333. To put that theory to test, we took a few of the more memory intensive benchmarks and put the Dothan through its paces using different speeds of memory: DDR200, DDR266 and DDR333. To do these tests all on the same bus speed and multiplier, we had to tweak the memory ratio settings a bit, but fortunately, the motherboard was versatile enough to let us enable all of these modes. For this portion of the analysis, we are using the processor in a 100MHz bus with a 21X multiplier.

32-bit GZip 1.3.5 Memory Scaling

32-bit lame 3.96.1 Memory Scaling

Now that we have proven the obvious (DDR333 is faster than DDR200), consider the implications of these benchmarks. Our DDR400 overclocking experiment should provide a very detailed outlay of what the sanctioned DDR400 platform will provide, even though the next generation Alviso chipset will also support DDR2 with different latencies.

Compiler Optimizations Final Thoughts
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