Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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) -- Ignore unavailable to you. Want to Upgrade?

To: Joe NYC who wrote (62380)	11/6/2001 2:29:38 PM
From: Petz	Read Replies (1) \| Respond to of 275872

Infoworld thumbs down on Windows XP in Test Center comparision. infoworld.com Using a scripting program called CSA Benchmark Studio Professional, they tested 3 varieties of computers under four workload levels using both Windows XP and Windows 2000. Windows XP was about 35% slower under the "baseline" workload, and even worse (sometimes >100% slower) under heavy load. Unfortunately the 3 systems tested were Pentium 4 1.5 GHz Pentium 3 733 MHz SMP Pentium 3 1GHz I suggested to one of the authors, PJ Connolly that, in a followup article, they include an Athlon XP system and an Athlon system. Petz

To: Joe NYC who wrote (62380)	11/6/2001 2:43:40 PM
From: Petz	Respond to of 275872

Joe, I suspect Kap "knows." I think the idea of a trace cache came first in the P4 design, but it was supposed to be bigger. It's purpose was to smooth out the requirement for decoder throughput so that a slower decoder could be used. Intel has very good memory cells, compared to AMD, so anything to replace logic with memory is probably a good tradeoff for them. Unfortunately, the 0.18 P4 was too big and the cache sizes had to be reduced. I'm sure the 0.13 P4 will have bigger caches [maybe not L1 data cache] to improve the integer IPC considerably. Not sure if they'll improve the FPU to increase FP IPC by the same amount, though. Petz