Cell chip: Hit or hype?

At the International Solid-State Circuits Conference on Monday, the joint developers of the long-awaited processor--Sony, Toshiba and IBM--unveiled a number of the details about it amid a surge of dramatic speculation. The New York Times said the chip could create "a new digital computing ecosystem that includes Hollywood, the living room and high-performance scientific and engineering markets."

Others speculated that the chip could drive everything from cell phones to servers, tying them into a grand computing grid.

"We believe a 10x performance over the PC, at the same power envelope, can be achieved," said IBM's Dac Pham, one of the designers of Cell. "It will usher in a new era of media-centered computing."

Intel's limping Itanium debuted with a similar level of fanfare. In 1994, the Microprocessor Report, examining the investment Intel planned to put behind the chip, predicted that it would become commonplace in desktops by 2004. It didn't happen.

Similarly, feelings ran high about the Emotion Engine, the microprocessor inside the original PlayStation 2 game console. Analysts said it could undercut chips from Intel and Advanced Micro Devices in PCs, and become the nerve center for DVD players and other home electronics. Toshiba even created a company, Artile, to license the Emotion.

But the Emotion Engine never migrated outside the PlayStation, and Toshiba snuffed out Artile in 2003. The PlayStation 2, meanwhile, didn't live up to the suggestion that it would serve as a conduit for movies, TV, e-mail and the Internet.

This sort of excitement and speculation about chips is driven by what I call the "Battlestar Galactica" principle. It goes as follows: If the domination of the universe isn't contested on a weekly basis, ratings will go down. Analysts, reporters, consumers and even executives need a gladiatorial contest to keep the job interesting.

The high-public profile of Sun Microsystems can partly be attributed to its role as the William Shatner of computing--donning a new uniform every three seasons to battle a new nemesis.

Put in that perspective, the Cell story starts to look different.

Going by papers presented at ISSCC, Cell looks like a tremendous achievement. However, this is the chip industry: Only a handful of companies--Samsung, Intel, Texas Instruments and Taiwan Semiconductor Manufacturing Co.--consistently produce profits. Most everyone else is seemingly always two steps away from the trailer park. Over the past few years, IBM Microelectronics has often reported quarterly losses. Cell will be a victory if it doesn't lead to layoffs.

In all likelihood, Cell will sell in far greater numbers than the just-as-trumpeted Itanium. Sony will put it into the PlayStation 3 video console. Unless gamers lose interest in stock cars, ninja stars and wiping out space aliens between now and 2006, that thing will sell. IBM and Toshiba will put it in products, too.

Still, whether the chip will be able to enter different markets is another question that hinges on factors such as:

Size: Cell contains 234 million transistors and takes up 221 square millimeters in the 90-nanometer production process. That's about double the size of the 90-nanometer 3.6GHz Pentium 4, with 112 square millimeters and 125 million transistors.

Big chips cost more to produce, can hide more bugs and can be tough to cram into portable devices. Cell will get cheaper when it goes to 65-nanometer production, but so will the alternatives.

Cost: Remember liquid crystal on silicon (LCOS)? The chip that would bring down the price of big-screen TVs? Intel and Brilliant Technologies failed at it. JVC and Sony succeeded. However, the latter two companies sell their LCOS chips to their own television units. The cost of the chip gets absorbed into the TV set.

Sony, Toshiba and IBM don't have to worry about the cost of Cell because they will sell it to themselves. It becomes part of a product that is tagged at a slightly higher price. An expensive Cell, however, will be a tough sell to any other manufacturers.

Alliances: Consumer electronics companies won't want to buy a processor from Sony and Toshiba. Similarly, not a lot of server manufacturers will line up to buy a Cell server chip from IBM. Why invite your rival to your top-secret design meetings?

Power: Cell will have to be air-cooled, IBM said. In other words, fans will probably be required. Ever talk on a cell phone with a fan?

While IBM didn't disclose the exact heat statistics, some at ISSCC said it could run as hot as 130 watts, more than most desktop and notebook chips. If Cell is in this range, kids will really be huddled around the PlayStation 3 at Christmas--for warmth.

On the cool engineering side, however, the chip will come with 10 digital heat sensors to warn of problems and another sensor to regulate temperature.

Memory: Cell comes with an integrated memory controller for high-performance XDR memory from Rambus--which means that the current design works exclusively with this pricey stuff. Sony used an earlier version of Rambus memory in the PlayStation, but it's been a tough sell outside of consumer electronics.

Cell is an outstanding achievement. But we have to wait and see whether it can get a job from someone other than its parents.