A look inside Apple’s silicon playbook

This week, Apple introduced a set of new MacBook Pro laptops. During pre-recording launch event, Apple engineers and executives made it clear that the MVPs in these new products are the chips that power them: the Chips M1 Pro and M1 Max. With 34 billion and 57 billion transistors, respectively, they are the engines that power the super-high-resolution displays of new Mac devices, delivering incredible speed and extending battery life. Laptops represent the apotheosis of a 14-year strategy that has transformed the company, literally under the hood of its products, in a massive effort to design and build its own chips. Apple is now methodically replacing the microprocessors it buys from vendors like Intel and Samsung with its own, which are optimized for the needs of Apple users. The effort has been amazingly successful. Apple was once a company defined by design. Design is still fundamental at Apple, but now I consider it a silicon company.

A couple of days after the keynote, I had a rare official conversation about Apple Silicon with Senior Vice President of Worldwide Marketing Greg Joswiak (aka “Joz”), Senior Vice President of Hardware Engineering John Ternus, and Senior Vice President of Johny Srouji hardware technology. I’d been asking Apple to get in touch with Srouji for years. His title only hints at his status as the chip czar at Apple. Although he has started to appear on camera at recent Apple events, he generally avoids being the center of attention. Srouji, an Israeli-born engineer who previously worked at Intel and IBM, joined Apple in 2008, specifically to fulfill a mandate from Steve Jobs, who felt that the chips in the original iPhone could not meet his demands. Srouji’s mission was to lead Apple in making its own silicon. The effort has been so well executed that I think Srouji is secretly succeeding Jony Ive as the ultimate creative wizard who makes the secret sauce in Apple’s offerings.

Twitch sues users over alleged hate raids against streamers

Srouji, of course, will not accept that. After all, the playbook for Apple executives is spending their hyperbole on Macs, iPhones, and iPads, not on themselves. “Apple makes the best silicon in the world,” he says. “But I always keep in mind that Apple is first and foremost a product company. If you are a chip designer, this is heaven because you are building silicon for a company that makes products. “

Srouji is clear about the advantages of releasing his own chips, rather than buying them from a vendor like Intel, which was summarily ripped from MacBook Pros this week in favor of the M’s. “When you are a merchant, a company that offers standard components or silicon to many customers, you have to find out what is the lowest common denominator: what is it that everyone needs for many years?” he says. “We work as a team (the silicon, the hardware, the software, the industrial design and other equipment) to enable a certain vision. When you translate that into silicon, that gives us a unique opportunity and freedom because now you are designing something that is not only truly unique, but optimized for a certain product. ”In the case of the MacBook Pro, he says, he sat with leaders like Ternus and Craig Federighi several years ago and envisioned what users could get their hands on in 2021. It would all come out of silicon. Can we go further? And then if it’s not restricted by physics and it’s a matter of time, we’ll figure out how to build it. “

Think about it: the only restriction Apple’s chipmakers give is the physical limit of what’s possible.

Srouji explained how his journey at Apple has been one of conscious iteration, built on a solid foundation. A key element of the company’s strategy has been to integrate the functions that used to be distributed among many chips into a single entity, known as the SOC or system-on-a-chip. “I always felt and fundamentally believed that if you have the right architecture, you have a chance to build the best chip,” he says. “So we started with the architecture that we think would scale. And by scaling, we mean scaling to performance and features and power envelope, whether it’s a watch, iPad, or iMac. And then we start to selectively calculate the technologies inside the chip; we wanted to start owning them one by one. We start with the CPU first. And then we move on to the graphics. Then we move on to signal processing, display engine, and so on. Year after year, we develop our engineering muscle and our wisdom and ability to deliver. And a few years later, when you do all this and do it well, you find yourself with really good architecture and IP and a team behind you that is now able to repeat that recipe. “

Ternus explains: “Traditionally, there is a team in a company that designs a chip and they have their own set of priorities and optimizations. And then the product team and another company have to take that chip and make it work in their design. With these MacBook Pros, we started all over again – the chip was designed just when the system was thought of. For example, power delivery is important and challenging with these high-performance parts. Working together [early on], the team was able to find a solution. And the system team was able to influence the shape, aspect ratio, and orientation of the SOC so that it can better fit the rest of the system components. “(Perhaps this helped convince Apple that restore missing ports that so many had longed for in the previous MacBook).

Clearly, these executives believe the new Macs represent a milestone in Apple’s strategy. But it is not the last. I suggest that a future milestone could be custom silicon to enable an augmented reality system, producing the intensity of graphics, precision geolocation, and low power consumption that AR glasses would require. Unsurprisingly, the vice presidents did not comment on that.

Before the conversation ends, I have to ask Joswiak about the now-discontinued Touch Bar, the dynamic function key feature that Apple launched with great fanfare five years ago but was never successful. Unsurprisingly, his autopsy makes for a great gift for new users. “There’s no question that our Pro customers love that full-size tactile feel from those function keys, and that’s the decision we made. And we feel very good about that, ”he says. He notes that for Touch Bar lovers, whoever they are, Apple continues to sell the now-obsolete 13-inch version of the MacBook Pro with the function keys intact.

The history of the Touch Bar reminds us that even the best silicon cannot guarantee that designers will make the right decisions. But as Srouji points out, when done right, it can unleash an infinite number of innovations that might not otherwise exist. Perhaps the most telling indicator of Apple’s silicon success this week came not from the launch of the MacBook Pro, but from Google’s presentation of the Pixel 6 Phone. Google boasted that the key virtues of the phone stemmed from a decision to go the way Apple and Srouji forged 14 years ago in building the company’s own chip, the Tensor processor.

“Is this a case of ‘Imitation is the sincerest form of flattery,'” I ask the Apple team.

“You took my line!” Joswiak says. “Clearly, they think we are doing something right.”

“If you gave Google or some other company some friendly advice on their journey to silicon, what would it be?” I ask.

“Oh, I don’t know,” says Joz. “Buy a Mac.”

This story originally appeared in wired.com.

Leave a Comment