| Sumario: | The article focuses on the history, speed, and design of computer chips. The first computer chips were designed to execute a series of straightforward operations. The chip could also store results and retrieve them again from a separate memory, which also held the program it was running. Then, as now, the movement of data to and fro, both inside the chip and between the chip and the memory, was co-ordinated using an oscillating crystal, which sends out a periodic signal like a ticking clock. Over the years, the frequency of this signal, known as the clock speed, became the key measure of processor performance. In parallel with Moore's Law, which predicts that the number of transistors on a chip increases exponentially, the clock speed has done the same, doubling roughly every 18 months from thousands of ticks per second in 1971, to millions in the 1980s, to billions today. But while optimists believe that this process will continue, chip developers across the industry now agree that clock speed will no longer be the key metric of processor performance, for several reasons. The first is the growth of parallelism--the practice of getting a chip to execute many different operations simultaneously. A second reason why clock speed will no longer be an accurate measure of performance is that distributing the clock's signal to all the different parts of a chip is more difficult than it sounds. Finally, getting chips to run at higher clock speeds is diminishing in importance because another problem is more pressing: getting them to consume less power. So designers are striving to minimise the power consumption of their chips, with speed as an ancillary consideration. One way of speeding things up would be to make chips in three dimensions, rather than on a flat plane as they are today.
|
|---|