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: wanna_bmw who wrote (51170)	8/15/2001 5:34:04 PM
From: pgerassi	Respond to of 275872

Wann_bmw: P4 has a 28 stage pipeline if you include decoding of the instructions. It is even longer for floating point as the Athlon has a longer floating point pipeline than the integer pipeline. The P4 trace cache can shrink that to 20 stages, if and only if, it has all of the instructions in it. Also, only one instruction can be decoded per cycle. Thus if the code jumps around a lot, the P4 becomes really slow. If it mispredicts the branches very frequently, and this is borne out by testing really nasty (to P4) programs, it is slower than a Celeron at half the clock. There are more balancing problems in the P4. Pete