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: Ali Chen who wrote (39661)	10/20/1998 12:47:00 PM
From: Tenchusatsu	Read Replies (1) \| Respond to of 1578931

<K6 beats P-II on every benchmark at low core frequencies, where the "Intel architecture" P5-class memory subsystem become more balanced with K6 core capabilities (relative memory latencies become smaller).> Once again, I hear this same old tired argument that at low frequencies, K6 is better. In the same logic, that must mean that the Cyrix MII must be the best CPU core out there, given that it does the most work per cycle at low frequencies. And if I took the logic to the extreme, I can design a processor which can handle about 100 instructions per clock. Guess whose processor is going to be faster when you run at 10 Hz? That's right, mine! That must mean that my processor is the "best" core design out there! I'll bet that the K7 will run slower than a K6 if you take away the K7's L2 cache, run it at 166 MHz, and run the memory bus at 66 MHz. But who the heck will want to run that beast at castrated speeds? <You forgot the simple fact that AMD had no resources to change the P5-Intel-dominated infrastructure of the whole PC industry, and has to play within the P5 rules.> No, I didn't forget. I'll agree that AMD has done a very good job taking the Socket 7 architecture to the Super 7 platform. Tenchusatsu