Intel Corp (INTC)

[mike306oh]

Saturn, thanks for your good input. However:

"In the study, published in Thursday's journal Nature, the Intel researchers reported encoding 1 billion bits of data per second, 50 times faster than previous silicon experiments. They also said they could achieve rates of up to 10 billion bits per second within months."

"This is a significant step toward building optical devices that move data around inside a computer at the speed of light," said Pat Gelsinger, Intel's chief technology officer.

http://www.iapplianceweb.com/story/OEG20040212S0036.htm

Don't you agree that Intel's CTO implys the move is toward an all-optical chip? At least is how I read it. Only all optical components can move data inside the box (computer in this case) at the "speed of light." A hybrid chip simply can't do it.

You are very right in saying this will take time. But, it won't be as long as most might expect. Faster speed internet needs (and many other high speed applications) will put pressure on the computer makers to drastically increase the speed. And hybrid chips will simply not be able to deliver. As I see it, Intel's announcement is a very first good step in the all-optical chip direction.

To make an unrelated paralel: Does anyone still think hybrid cars will be the answer? Certainly not! Ultimatelly, the hydrogen cars will winn. And it will also happen, IMO, much faster than many people had expecteed.

Mike

---------------------------------
The all optical chip is a wet dream probably a decade or two away. We do not even have a decent discrete all optical switch , and we are miles away from all optical computing. Today you use fiber optics and photons for transmission, convert to electrons for amplification, switching and processing, and then the electronic signal is converted back to photons via a laser for further transmission or distribution. All this requires several components.

The Intel announcement implies that in 4 -5 years you will be able to integrate a laser and its control, switching and processing electrical functions on the same chip. This in itself will be a major step in improving the cost/ performance of optical communications. The integration on a single chip should greatly speed up the "slow electronics", and it will also be cheaper.

So Intel Inside will live on for another decade or so.

Maybe forever !!!