GCN LAB IMPRESSIONS

How Intel could exceed Moore's Law with '3-D' chip

New 22-nanometer, tri-gate transistor will boost performance while reducing power consumption

The wheel is a nice piece of technology. It’s been around for quite a while, and is used nearly everywhere. And it pretty much has stayed the same since its invention – you know, round and all.

The microprocessor is a different story. This basic building block of computer technology has only been around for about 50 years. In that time, however, its designers have followed Moore's Law like clockwork, regularly doubling the amount of transistors they could cram into a processor. The 4-bit chips gave way to 8 bits and on up to 64 bits, and then the multicore designs came along.

But now, Intel may be able to get ahead of Moore’s schedule with a new transistor design, some nine years in the making. They are calling it a 3-D transistor, but let’s be clear here: Very small, older transistors also existed in all three physical dimensions. A more accurate term would be a tri-gate transistor.

Here’s the basic idea. A transistor has power flowing through it from the source end to the drain end. The presence or absence of a current is determined by the voltage level of the gate that bridges the two. The major problem with the traditional setup involves signal loss resulting from the fact that the gate only contacts the source and drain on one surface.

A tri-gate, or 3-D if you really insist, transistor has three gates that make contact on three sides at once, effectively tripling the amount of surface through which electrons can travel. This produces less data leakage and uses less power than the older design.

Intel asserts that this equates to a third more processing speed, and about half as much power consumption. And at 22 nanometers, they are able to make them smaller than ever before. This means they could pack in twice as many transistors in about the same-sized chip for the same power usage, which operate a third faster – effectively giving us 2 2/3 as much processing ability for the same power consumption. Take that, Mr. Moore! (Although we suppose that since Moore’s Law is named after Gordon Moore, co-founder of Intel, breaking the law is OK in this case.)

In the GCN Lab, we can hardly wait to see what effect this new processor design will have on computer performance, battery life and, of course, cost to consumers and government. We’ve already been in talks with major computer manufacturers who have put us in the front of the queue to check out a new workstation featuring these tri-gate monsters.

Sadly, the new chips aren't slated to come out in systems until early next year. And although we will do our best to get ahold of a prototype as soon as possible, I guess we’ll have to wait a little while longer.

About the Author

Greg Crowe is a former GCN staff writer who covered mobile technology.

Reader Comments

Wed, May 11, 2011

Sounds like Greg has a FETish for the old tube terminology.

Wed, May 11, 2011

Bipolar transistors have a base, collector and an emitter. The Field Effect Transistor (FET) has a source, drain and gate. The bipolar is controlled by base current while the FET is controlled by gate voltage. Hence, the FET is *much* more efficient.

Wed, May 11, 2011

Bipolar transistors (BJT) have a base, collector and emitter. Field Effect Transistors (FET)has source,gate and drain. Both are transistors.

Wed, May 11, 2011 John Tacoma, Wa

Great article, great humor. I like source and drain rather than collector base and emitter, as I am no electrician and those terms would be lost on me.

Wed, May 11, 2011

This is good humor...but I thought a transistor had collecter base and emitter not source gate and drain.

Please post your comments here. Comments are moderated, so they may not appear immediately after submitting. We will not post comments that we consider abusive or off-topic.

Please type the letters/numbers you see above