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 : Intel Corporation (INTC) -- Ignore unavailable to you. Want to Upgrade?

To: Windsock who wrote (135508)	5/19/2001 10:53:34 AM
From: Dan3	Respond to of 186894

Re: If it is a "normal" behavior why can't McComas run an experiment that consistently shows clock throttling? The performance of a given chip/motherboard combination was consistent. What wasn't consistent was a randomly selected chip put into a randomly selected motherboard. One possible explanation that was presented was that critical parts of the core are very sensitive to uncontrollable (so far) manufacturing variations. So the performance of some of the chips is consistent with the hopes of the engineers who designed them. But most of the chips failed under traditional testing (if it were few, rather than most, those few could be down-binned or thrown out as defectives). So intel added a feature that limits the performance of the chip to its actual capability, regardless of what is reported as its speed or what speed part the customer was charged for. An intriguing comparison is between AMD's PowerNow, which increases the speed of the processor when that speed is needed under heavy load, to Intel's throttling, which reduces the speed of the processor under heavy load, just when that speed is needed, while burning up extra watts idling at high MHZ when compute power is not needed. Dan