“I’ve bet the whole company on 18A,” Intel CEO Pat Gelsinger told an interviewer earlier this year—a baffling statement to non-techies, but the story behind it is understandable to anyone and worth knowing. It’s an uplifting reminder of human ingenuity’s endless reach, relevant to challenges of every kind.
As to what on earth Gelsinger was talking about: Intel is one of the world’s preeminent designers and manufacturers of computer chips, and the 18A is a chip that Intel intends to start making in volume next year. It will be the most advanced chip ever, though Taiwan Semiconductor Manufacturing Company (TSMC), the world’s largest chipmaker, will next year start making in volume a chip it claims at least matches the 18A. That designation, 18A, denotes the density of transistors on the chip, among other things, and the smaller the number, the higher the density. This is the smallest number of any chip yet; 18A means 18 angstroms, an angstrom being one ten-billionth of a meter. The rest of the industry labels chips by nanometers; TSMC’s new chip is 2 nm, and by that measure the 18A would be 1.8 nm. Even without understanding the production process, we stand in awe of its infinitesimal scale. Chipmakers now work at the level of atoms. An atom of silicon is 0.21 nanometers wide, for example.
That’s enough atomic physics. The important point is that these new chips are more than just astounding. They were supposed to be impossible. The famous Moore’s Law said the number of transistors on a chip—basically transistor density—doubles every two years or so. It proved accurate for decades, but even Gordon Moore himself acknowledged, “It can’t continue forever.” The laws of physics would allow transistors to get only so small. The crucial question was exactly how small.
Experts have been confidently and incorrectly predicting the answer for years. Some said 2010 would be the end, when the leading-edge chip was 28 nm. After chipmakers broke through that level, a new set of prognosticators saw 2020 as the limit, when the leading edge was 5 nm. Yet now even Intel’s 1.8 nm chip is not the end of the line. The company’s next chip—1.4 nm—is in development.
How can this be? The answer is in two parts, both of which are relevant to human ingenuity broadly.
· The chipmakers and their suppliers kept finding innovative new ways to extend the life of Moore’s Law, which prognosticators couldn’t foresee. For example, chipmakers figured out how to stack transistor components on top of each other, packing more computing power into a given space. Another example: Chipmaking involves shining light through a mask onto a silicon wafer, but as transistors got ever more microscopic, it was difficult to use light with wavelengths short enough to print sharp patterns. ASML, a Dutch maker of chipmaking equipment, developed machines that could handle the necessary extreme ultraviolet light, and today’s leading-edge chips can’t be made without those machines. To produce the 18A, Intel CEO Gelsinger negotiated with ASML to be first to receive the company’s latest model.
· Companies went around Moore’s Law. Adding more transistors isn’t the only way to get more value from a chip. Advanced algorithms and software now help users get better performance out of their computers’ chips. Chipmakers are also producing chips designed for specific applications, such as AI. Those chips aren’t the best at everything, but they’re great for specific tasks. Broadcom, the tech company that has quietly become one of the world’s most valuable companies, designs many such chips.
Strictly speaking, Moore’s Law is no longer valid. As transistors approach atomic scale, the number of transistors on a chip isn’t doubling every two years. But so what? Computing continues to advance at a scorching pace—with quantum computing and other wonders on the horizon—and that’s what counts.
The saga of Moore’s Law is an example of how we almost always underestimate human ingenuity. Early researchers in computer translation of languages were pessimistic that the field could ever progress beyond its nearly useless state as of the mid-1960s, yet today your phone has a free app that translates to and from over 100 languages very well, and it’s continually improving. MIT professor Hubert Dreyfus, in a 1972 book called What Computers Can’t Do, saw little hope that computers could make significant progress in playing chess beyond the mediocre level then achieved. Yet an IBM computer beat world champion Garry Kasparov in 1997, and Kasparov tells me the free chess app on your phone today is more powerful than the computer that defeated him.
There’s no telling what will happen with Pat Gelsinger’s rescue plan for Intel or with any individual quest. But broadly, over time, we can be sure at least two things will be infinite: human desires and human ingenuity. We’ll always be unsatisfied, with problems to solve, and we’ll always find astonishing, unexpected solutions to at least some of them. In this tumultuous world, that’s not a bad basis for optimism.