SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : Advanced Micro Devices - Moderated (AMD)
AMD 246.76-0.5%Nov 14 9:30 AM EST

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: zetopan who wrote (227029)2/28/2007 8:52:51 PM
From: pgerassiRead Replies (1) of 275872
 
Dear Zetopan:

They are not artificial. Using Base is artificial. Even SPEC does not say peak in their scores, just plain SPECfp_2006. For base they use the qualifier base. And with the rules SPECfp_2006 uses the base scores, if there aren't peak ones. So even SPEC uses the peak scores in comparisons.

Using the same type OS is also not artificial. When comparing two things one tries to keep as much similar as possible. Even Intel did not use their compilers when submitting the only C2D SPECfp_rate2006 score. They used gcc under SUSE. If you want to compare Extreme X6800s with DDR2, you must also use A64 FXs with DDR2 as well. You can use a FX-74 with PC2-8500 and watch those scores rise over those of Opterons which use RDDR.

Using Linux and 3rd party compilers, Opteron with RDDR PC-3200 got the same percentage of Woodcrest with FBDIMM 667MHz in both SPECint_2006 and SPECfp_2006, 84%. In real world applications on real world servers, Opteron does better than C2D. Remember the complaints of many PC buyers that P4s in real world usage did not do as well as the benchmarks claimed. There is even a class action lawsuit pending about it. The various K8 flavors did about what the benchmarks claimed or better. Thus, no similar suit against OEMs using AMD CPUs.

Pete
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext