IBM and Samsung unveil revolutionary microchip design
This article is a part of Future Explored, a weekly guide to technologies that change the world. You can receive stories like this straight to your inbox every Thursday morning by register here.
If you didn’t know semiconductor chips were important before the pandemic, you know now.
Also known as ‘microchips’, these little bits of technology form the brains behind new cars, phones, computers, game consoles and countless other products that we rely on every day (all of which are now in short supply. ).
Now IBM and Samsung have unveiled a new microchip design that promises dramatically faster and more efficient chips – and a significant upgrade to all of our technologies that depend on it.
The challenge: Semiconductor chips contain tiny gates called “transistors” that control the flow of electricity. This is what allows a traditional computer to process information, using a binary on / off code. (If a door is open, it is a “1”. If it is closed, it is a “0”.)
To make faster, more powerful computers, we need chips with more transistors, but to keep chips, well, microphone, we had to keep packing more and more transistors in the same area.
We are now hitting a wall in the amount of transistors we can pack on a microchip.
The end of the line: In 1975, semiconductor pioneer Gordon Moore predicted that we would be able to double the number of transistors on electronic chips every two years, and this projection – “Moore’s Law” – has been held to be correct for decades, thanks to the heroic efforts of engineers.
However, now we are up against a wall in the amount of transistors we can pack on a microchip. Making them smaller has become physically impossible – the ones we have today are so small that 1,000 of them placed end to end are only the width of a human hair.
“The point is, when they talk about building physical entities like semiconductors and transistors, you can only go that small,” Robert Sutor, chief quantum exponent at IBM, says Electronic Products.
“Atoms have a certain size and you are approaching almost atomic molecular distances at this point,” he continued. “You are limited by this. “
The idea: IBM, Samsung’s New Design Stacks Transistor Components vertically on a microchip, with electricity flowing from top to bottom, rather than the traditional horizontal design, with electricity flowing from side to side.
They call their approach “Vertical-Transport Nanosheet Field Effect Transistor” (VTFET), and they say that this could not only allow more transistors on a microchip, but also make the flow of electricity through them more efficient.
Compared to today’s standard transistor design (called FinFET), devices with VTFET chips would have “a two-fold improvement in performance or an 85% reduction in power consumption,” according to IBM.
This means that batteries could last much longer (or be much smaller) and computers could produce much less waste heat, which impacts performance and requires powerful fans to keep the system cool.
In other words: smartphone batteries that last the week, rather than one day.
“Scaling silicon isn’t the only way to get lower power and better performance. “
The overview: IBM and Samsung haven’t said when they plan to start producing chips with the stacked solid-state design, so we don’t know when they might actually start showing up in your phone or watch, but it usually takes a few years to get there. move from the drawing board to find out how to mass-produce chips and build devices that can use them.
However, the stacked design and more densely packaged transistors aren’t the only ways to keep the power of growing computers going for decades to come.
“Scaling silicon isn’t the only way to achieve lower power and better performance,” Valeria Bertacco, director of the Applications Driving Architectures research center at the University of Michigan, said EE Times in 2019. “It was just the easiest way until 10 years ago.”
Another way is to specialize microchips for specific tasks and divide up the work of the computer.
“Hardware customized for particular areas can be much more efficient and use significantly fewer transistors, allowing applications to run tens to hundreds of times faster,” said Tao Schardl, researcher at MIT. told MIT News in 2020.
More efficient software and better algorithms could also allow progress to continue even if the number of transistors does not increase. Replacement of semiconductor materials, such as silicon, in chips with other materials, like graphene, could also trigger significant performance improvements.
Then there’s the ultimate game changer: quantum computers, which aim to completely eliminate transistor-laden microchips. Instead, they encode information into tangled particles that can represent 1s, 0s, or both simultaneously, which greatly increases the potential processing power of the computer.
But today’s silicon microchip electronics aren’t going to be replaced anytime soon by quantum versions or even graphene, so in the short term we’ll have to rely on smart new designs to craft another round of improvements. Moore’s Law.
We would love to hear from you! If you have a comment on this article or have a tip for a future Freethink story, please email us at [email protected].