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: Brian Hutcheson who wrote (32891)	5/26/1998 1:51:00 AM
From: Petz	Respond to of 1571808

Brian, PII does NOT process two floating point ops per cycle (FLOPS), but it CAN do two MMX (integer ops per cycle). Also, the vanilla K6 can only do one floating point op every other cycle. The only reason the vanilla K6 came close to the FP performance of the Intel MMX and PII is that it has lower latency -- only 2 clocks for the K6 but 5 for the MMX and 4(?) for the PII. Here's a summary CPU...........Max FLOPS/cycle................Latency AMD K6........0.5 (multiply) 1? (add)........2 AMD K6-2......4 (2*,2+,single precision)...2 Intel Pentium 1........................................5 Intel PentII. 1........................................4? Petz