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 : Intel Corporation (INTC)
INTC 40.56+10.2%Nov 28 9:30 AM EST
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Joe NYC who wrote (128245)2/24/2001 5:39:04 AM
From: Scumbria   of 186894
 
Joe,

We have arrived at a point in CPU design where blindly throwing transistors at performance is no longer of any value.

1. AMD L1 Caches are big enough for desktop apps. Duron is almost as fast as Athlon at the same clock rate. P4 took a step back in cache size, but I doubt Intel will be dumb enough to make that mistake again.

2. Attempts to further exploit instruction level parallelism have failed.

The future lies in:

1. Exploiting coarse-grained parallelism. P4's SIMD SSE2 unit does this, and has shown excellent scores for recompiled FPU apps. The AMD hammer family will extend this idea to multiprocessing on a single substrate.

2. Data prefetching into the L2. P4 does this now, and benefits a lot on scientific apps which use large static data structures (arrays.)

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

HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News