Programmers up against ‘power wall’, try to match faster chips

Programmers up against ‘power wall’, try to match faster chips

Redmond, Washington: When he was CEO of Intel Corp. in the 1990s,Andrew Grove would often talk about the “software spiral"—the?interplay?between?ever-faster microprocessor chips and software that required ever more computing power.

The potential speed of chips is still climbing, but now the software they run is having trouble keeping up. Newer chips with multiple processors require complex software that breaks up computing chores into chunks that can be processed at the same time.

The challenges have not dented the enthusiasm for the potential of new parallel chips at Microsoft Corp., where executives are betting that the arrival of manycore chips—processors with more than eight cores, possible as soon as 2010—will transform the world of personal computing.

Grove’s software spiral started to break down two years ago. The microprocessors were generating so much heat, they were melting, forcing Intel to change direction and try to add computing power by placing multiple smaller processors on a single chip.

The chip industry has known about the hurdles involved in moving to parallel computing for four decades. One problem is that not all computing tasks can be split among processors.

The most aggressive of the Microsoft planners believe the new software designed to take advantage of microprocessors, now being refined by firms such as Intel and Advanced Micro Devices, Inc. (AMD), could bring as much as a hundredfold computing speed up in solving some problems.

Microsoft executives argue such an advance would herald the advent of a class of consumer- and office-oriented programs that could end the keyboard-and-mouse computing era by allowing even hand-held devices to see, listen, speak and make complex real-world decisions.

The industry will continue to be able to add more transistors to a silicon chip for now, but the problem lies in the amount of power they consume and the heat generated. That will limit the rate at which processing speeds increase.

The need to get around what the industry is calling the “power wall" has touched off a frantic hunt for new computing languages, as well as new ways to automatically break up problems so they can be solved more quickly in parallel.

Although the Microsoft effort was started about five years ago by Craig Mundie, one of the company’s three chief technical officers, it picked up speed recently with the hiring of a number of experts from the supercomputing industry and academia.

The more recent arrivals at Microsoft include Burton Smith, a supercomputer designer whose ideas on parallel computing have been widely adopted, and Dan Reed, an expert on parallel computing.

Dual-core microprocessors are already plentiful in consumer devices. For example, both Intel and AMD’s standard desktop and portable chips now have two cores.

Microsoft sees this as its principal opportunity, and industry executives have said the arrival of manycore microprocessors is likely to be timed to the arrival of “Windows 7"—the follow-on operating system to Windows Vista.

The opportunity for the company is striking, Mundie said. He envisions modern chips that will increasingly resemble musical orchestras. Rather than having tiled arrays of identical processors, the microprocessor of the future will include different computing cores, each built to solve a specific type of problem.

There are those who argue that there will be no easy advances in the field—including some inside Microsoft. “I’m sceptical until I see something that gives me some hope," said Gordon Bell, one of the nation’s pioneering computer designers, who is now a fellow at Microsoft Research.

Bell said, in the 1980s, he tried to persuade the computer industry to take on the problem of parallel computing while he was a program director at the National Science Foundation.

“They told me, ‘You can’t tell us what to do’... Now the machines are here and we haven’t got it right."