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: Bilow who wrote (75848)	10/18/1999 9:47:00 AM
From: Ali Chen	Respond to of 1572507

Carl, <Great post on the AMD versus INTC> Thank you. As far as your remarks about details of superpipeline implementation, you are of course correct. But getting in such details when talking to undereducated morons like Fudd and Paul Yousef is a waste of time. Therefore I used all these simplifications just trying to illustrate the point. Re. <it is almost always impossible to exactly split logic between several register stages. Because of this, designs with long pipelines tend to be somewhat less efficient.> That's absolutely true. Even more, as you might have noticed, the whole construction (when the reduced length of pipeline was attributed entirely to the same increase in gate depth complexity between stages) is rather artificial. However, your remark that the logic cannot be split evenly makes the explanation even more realistic, because it is enough to have only one overloaded stage to drag the whole design down in frequency. Again, thank you for your understanding and support.