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: Dan3 who wrote (157057)	1/27/2002 10:42:25 PM
From: wanna_bmw	Read Replies (1) \| Respond to of 186894

Dan, Re: "Do you think processors will be able to sustain performance as clock speeds increase without lower latency?" The quickest and easiest way to higher performance is by increasing the clock frequency. And that's a fact. At a higher frequency, small improvements in IPC will make a much bigger difference to overall performance. AMD has been pushing, and continues to push IPC, while they are desperately searching for process improvements like PD SOI to give them minor benefits to frequency. And yet, their processors are as hot as Intel's at a much lower frequency. Their packaging technology is far behind, and they're only compounding heat problems by shrinking the die size, and integrating a lot more circuitry. Re: "If the miss rate is as high as 5% (and it rarely is) that means a 10GHZ chip would need bandwidth of 10,000 million / 20 = 500 million 4 byte reads per second or 2 gigabytes per second." So now we're back to your over-simplified idiot posts, again? You should now that locality isn't as simple as taking the cache miss rate and multiplying it by the number of instructions per second. Getting performance is about getting the right data - when you need it. That's why 2.1GB/s isn't enough today for a 2GHz processor, let alone a 10GHz processor. You're not even close. wbmw