As TR reported last December, computer industry executives have begun to question in recent years whether it’s fair, or even useful, to market new chips solely on the basis of their clock speed. (Clock speeds are those numbers like “2.5 Gigahertz,” meaning that a chip’s internal clock ticks 2.5 billion times per second; each tick is a signal to the chip that it can perform one set of operations.) The problem is that most chips’ real-world performance is determined by many factors aside from clock speed, such as input/output capacity and the size of the “cache” or onboard memory. AMD adopted a new naming scheme for its chips several years ago, and now industry leader Intel has decided to go along. The company has announced that starting next month, its various processors will be renamed using a three-digit scheme tied to the chips’ particular architectures, rather than their clock speed. For example, numbers in the 300s will be reserved for Intel’s low-end Celeron processors, while those in the 700s will be used for more expensive mobile processors like the Pentium M family.
Initially at least, consumers might have a harder time deciphering the processor names than they did comparing clock speeds. Intel warns explicitly against using the numbers, which will be phased in between May and July, to compare processors in different families. “710 is not ‘better’ than 510 simply because 7 is greater than 5,” a company statement says. But over time, Intel says, “these processor numbers will allow end customers to intelligently and accurately distinguish among individual processors by taking into account a broader set of features that contribute to the overall user experience.”
We’ll see. What the change really reflects—and what customers need to acknowledge and cope with–is that buying a computer is almost as complex these days as buying a car. And few people over the age of 19 buy a car based simply on how fast it can go. Eventually, we may even see consumer versions of clockless chips in which operations can proceed at their own pace, without having to wait for the next clock tick (see “It’s Time for Clockless Chips,” TR October 2001). At that point, the Gigahertz really will be ready for the garbage can.
Capitalizing on machine learning with collaborative, structured enterprise tooling teams
Machine learning advances require an evolution of processes, tooling, and operations.
The Download: how to fight pandemics, and a top scientist turned-advisor
Plus: Humane's Ai Pin has been unveiled
The race to destroy PFAS, the forever chemicals
Scientists are showing these damaging compounds can be beat.
How scientists are being squeezed to take sides in the conflict between Israel and Palestine
Tensions over the war are flaring on social media—with real-life ramifications.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.