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.

Politics : Formerly About Advanced Micro Devices -- Ignore unavailable to you. Want to Upgrade?

To: Yousef who wrote (64402)	7/8/1999 11:11:00 AM
From: Ali Chen	Respond to of 1586285

Dr. Yousef: Re<plus-minus 10% in switching performance> <But that has been my point all along, Ali .> You still did not get the point. <AMD's .25um process is not at the same gate length as the Intel .25um process.> Which variant of AMD process do you mean? Stunted for K6? Or regular for K7? <This is readily verified by the operating voltage and gate oxide thickness.> Which operating voltage do you have in mind? 2.5V or 1.6V? <BTW Ali, I believe that the K6-2 versus PII/PIII benchmarks show that the AMD "achitecture" is inferior at the same Mhz.> You are confusing system architecture with CPU core architecture (which determines the CPU speed for a given technology). The system architecture also includes the memory in a broad sense, which includes L2/L3/DRAM architectures, plus I/O architecture. For the K6-2, the external system architecture was frozen by Intel at inferior to P-II levels. As you might know, the K6-3 (same core but improved L2 "architecture") beats P-II/III in many benchmarks. The "inferiority" or "superiority" also depends on the main user application. For chess players even K6-2-450 beats Xeon-450 and P-III-500 by 3-5%: rebel.nl Therefore, K6 is clearly superior to Pentiums for that group of users. <Not a good thing, IMHO.> I'm glad you started to think eventually. Keep it moving. "LaughAthlon" is coming.