For practical purposes, the M1 Ultra acts like a single, impossibly large slice of silicon that does it all. Apple’s most powerful chip to date has 114 billion transistors packed into over a hundred processing cores dedicated to logic, graphics, and artificial intelligence, all of it connected to 128 gigabytes of shared memory. But the M1 Ultra is in fact a Frankenstein’s monster, consisting of two identical M1 Max chips bolted together using a silicon interface that serves as a bridge. This clever design makes it seem as if the conjoined chips are in fact just one larger whole.
As it becomes more difficult to shrink transistors in size, and impractical to make individual chips much bigger, chipmakers are beginning to stitch components together to boost processing power. The Lego-like approach is a key way the computer industry aims to progress. And Apple’s M1 Ultra shows that new techniques can produce big leaps in performance.
“This technology showed up at just the right time,” says Tim Millet, vice president of hardware technologies at Apple. “In a sense, it is about Moore’s law,” he adds, in reference to the decades-old axiom, named after the Intel cofounder Gordon Moore, that chip performance—measured by the number of transistors on a chip—doubles every 18 months.
It is no secret that Moore’s law, which has driven progress in the computer industry and the economy for decades, no longer holds true. Some extremely complex and costly engineering tricks promise to help shrink the size of components etched into silicon chips further, but engineers are reaching the physical limits of how small these components, which have features measured in billionths of a meter, can practically be. Even if Moore’s law is outdated, computer chips are more important—and ubiquitous—than ever. Cutting-edge silicon is crucial to technologies such as AI and 5G, and supply chain disruptions triggered by the pandemic have highlighted how vital semiconductors now are to industries such as automaking.
As each new generation of silicon takes a smaller step forward, a growing number of companies have turned to designing their own chips for performance gains. Apple has used custom silicon for its iPhones and iPads since 2010—then, in 2020, it announced that it would design its own chips for Macs and MacBooks, moving away from Intel’s products. Apple leveraged the work it did on smartphone chips to develop its desktop ones, which use the same architecture, licensed from the British company ARM. By crafting its own silicon, and by integrating functions that might normally be performed by separate chips into one system-on-a-chip, Apple has control over the entirety of a product, and it can customize software and hardware together. That level of control is key.
“I realized the whole [chipmaking] world was upside down,” says Millet, a chip industry veteran who joined Apple from Brocade, a US networking company, in 2005. In contrast to, say, Intel, which designs and makes chips that are then sold to computer makers, Millet explains that Apple can work on the design of a chip for a product at the same time as the software, hardware, and the industrial design.
Most PopularBusinessThe End of Airbnb in New York
Amanda Hoover
BusinessThis Is the True Scale of New York’s Airbnb Apocalypse
Amanda Hoover
CultureStarfield Will Be the Meme Game for Decades to Come
Will Bedingfield
GearThe 15 Best Electric Bikes for Every Kind of Ride
Adrienne So
When Apple announced the M1 Max, its previous desktop chip, in October last year, a few eagle-eyed onlookers noticed something odd: a long stretch of silicon along one edge that appeared to do nothing whatsoever. The mystery silicon would turn out to be part of the high-speed interconnect technology, featuring a dense array of fine connections, that Apple calls UltraFusion, which turns two M1 Max chips into one M1 Ultra.
When Apple began working on a new desktop computer for power users, a product that would become the Mac Studio, the chip team knew it wouldn’t be possible to rely on Moore’s law alone for a big boost in performance. But TSMC, the Taiwanese chipmaker that mints Apple’s designs, had begun perfecting a technology for joining two pieces of silicon using a high-speed interconnect, an idea that has been around for years but has previously been used mostly to combine cores that do different jobs. Apple customized the TSMC technique to make the mystery interface seen on the Max, stitching together two highly complex chips.
“UltraFusion gave us the tools we needed to be able to fill up that box with as much compute as we could,” Millet says of the Mac Studio. Benchmarking of the M1 Ultra has shown it to be competitive with the fastest high-end computer chips and graphics processor on the market. Millet says some of the chip’s capabilities, such as its potential for running AI applications, will become apparent over time, as developers port over the necessary software libraries.
The M1 Ultra is part of a broader industry shift toward more modular chips. Intel is developing a technology that allows different pieces of silicon, dubbed “chiplets,” to be stacked on top of one another to create custom designs that do not need to be redesigned from scratch. The company’s CEO, Pat Gelsinger, has identified this “advanced packaging” as one pillar of a grand turnaround plan. Intel's competitor AMD is already using a 3D stacking technology from TSMC to build some server and high-end PC chips. This month, Intel, AMD, Samsung, TSMC, and ARM announced a consortium to work on a new standard for chiplet designs. In a more radical approach, the M1 Ultra uses the chiplet concept to connect entire chips together.
Apple’s new chip is all about increasing overall processing power. “Depending on how you define Moore’s law, this approach allows you to create systems that engage many more transistors than what fits on one chip,” says Jesús del Alamo, a professor at MIT who researches new chip components. He adds that it is significant that TSMC, at the cutting edge of chipmaking, is looking for new ways to keep performance rising. “Clearly, the chip industry sees that progress in the future is going to come not only from Moore’s law but also from creating systems that could be fabricated by different technologies yet to be brought together,” he says.
Most PopularBusinessThe End of Airbnb in New York
Amanda Hoover
BusinessThis Is the True Scale of New York’s Airbnb Apocalypse
Amanda Hoover
CultureStarfield Will Be the Meme Game for Decades to Come
Will Bedingfield
GearThe 15 Best Electric Bikes for Every Kind of Ride
Adrienne So
“Others are doing similar things, and we certainly see a trend towards more of these chiplet designs,” adds Linley Gwennap, author of the Microprocessor Report, an industry newsletter.
The rise of modular chipmaking might help boost the performance of future devices, but it could also change the economics of chipmaking. Without Moore’s law, a chip with twice the transistors may cost twice as much. “With chiplets, I can still sell you the base chip for, say, $300, the double chip for $600, and the uber-double chip for $1,200,” says Todd Austin, an electrical engineer at the University of Michigan. Essentially, instead of chips getting faster each year for the same price, chiplets could mean extra performance comes at a premium. Austin adds that the approach, which is still relatively new, will also add new complexity to designing chips, which could also add cost.
The M1 Ultra demonstrates the kind of horsepower seen in some of the market’s most powerful chips thanks to a creative take on the chiplet approach. It also sets Apple up to achieve a significant edge for Macs—just as it has with the iPhone for years.
More Great WIRED Stories📩 The latest on tech, science, and more: Get our newsletters!Is Russia's largest tech company too big to fail?This is how the global energy crisis endsWe explain Matter, the new smart home standardThe future of NFTs lie with the courtsChernobyl was a wildlife haven. Then Russia invaded👁️ Explore AI like never before with our new database💻 Upgrade your work game with our Gear team’s favorite laptops, keyboards, typing alternatives, and noise-canceling headphones