WOA Issue 84
In this issue ASTRA – A Large Scale ARM64 HPC…
When Apple finally confirmed the scuttlebutt about making the move from Intel chips to Macs built with its own Arm-based “Apple Silicon“, no one was particularly surprised.
After all, the rumors had been swirling through the grapevine for nearly a decade that a change was going to come. And though it marked the first significant shift in Apple’s desktop computing hardware since 2005 — when the company announced Intel chips would, in fact, reside inside its iconic machines — the switch feels more like deja vu than ‘deja new’ for those who know their history.
Apple and Arm have been core to each other’s businesses since the early 1990s, and their on-again, off-again affaire de l’esprit has been key in the rise of Apple’s mobile and tablet market domination. This summer’s blockbuster announcement is more than just a culmination of events — it bears the seeds of an industry groundbreaker.
Despite all the sturm and drang of exactly how porting over apps to a new architecture is going to work, Arm and Apple are not a hot new power couple on the scene. In fact, they’ve been canoodling since the early 90s, when Apple’s leadership fell to John Sculley, who had engineered Steve Job’s relatively short-lived absence from the company’s C-level suites.
Under Sculley, Apple began developing the Newton, the company’s first Personal Device Assistant (PDA). When a collaboration with AT&T to produce a chip for the Newton didn’t pan out, Apple’s Larry Tesler turned to RISC (Reduced Instruction Set Computer) architecture for the price/performance advantages the Newton team was looking for. Once testing proved successful, Apple not only chose the ARM610 processor for its new pet project, but also acquired 43 percent of the Arm company and put Tesler on Arm’s board of directors.
In a 1992 internal presentation to the Apple team, Arm co-founder (and later CTO) Mike Muller summed up the synergy between Apple’s trailblazer culture and Arm’s capabilities: “Arm is all about the crossover between the desktop PC and consumer applications, where you want things small, cheap, and low-power,” he said. “We’ve never claimed to be the fastest RISC processor in the world — we’re just one of the cheapest and one of the most power-efficient.”
But when the project direction shifted away from Tesler’s original vision, and the Newton morphed into a smaller handheld device, development was thrown into disarray and the product was rushed to market. By the time the Newton MessagePad rolled off the production line and into consumers’ hands, Sculley was no longer Apple’s head honcho and the Newton’s technology flaws were exposed to a decidedly underwhelmed public.
When Steve Jobs returned to Apple as “interim” CEO a few years later, the Newton was one of the first projects he axed, and Apple began selling off its stake in Arm to fund new innovations — including the iMac and the Mac OS X. At Jobs’ instigation, both would ultimately run on Complex Instruction Set Computing (CISC)-based Intel chips.
From little acorns, however, great successes (and sometimes monumental ironies) grow. Even though Jobs had ditched the Newton, it would return in another guise a decade later, as Apple catapulted app-driven mobile devices into the stratosphere.
When Jobs announced the release of the iPhone at MacWorld 2007, he proclaimed Apple’s love for all things software and prophetically quoted computing pioneer Alan Kay: “People who are really serious about software should make their own hardware.”
Despite being asked by Apple, Intel had opted to bow out of the iPhone processor game and every iPhone ever produced (and iPods, and later iPads) runs on processors designed by Apple with Arm licenses technology. By the end of this year, Macs will ship with Apple Silicon inside, bringing the Apple-Arm connection — and the RISC vs. CISC debate — full circle nearly 30 years later.
“From the beginning, the Mac has always embraced big changes to stay at the forefront of personal computing. Today we’re announcing our transition to Apple Silicon, making this a historic day for the Mac,” said Apple CEO Tim Cook in a company release. “With its powerful features and industry-leading performance, Apple Silicon will make the Mac stronger and more capable than ever. I’ve never been more excited about the future of the Mac.”
Included in the framework of its two-year transition to the Arm architecture, macOS Big Sur (rumored to be released in September(ish), will offer tools & resources to make the transition to Apple silicon as frictionless as possible.
“With everything built into Xcode 12, such as native compilers, editors, and debugging tools, most developers will be able to get their apps running in a matter of days. Using Universal 2 application binaries, developers will be able to easily create a single app that taps into the native power and performance of the new Macs with Apple silicon, while still supporting Intel-based Macs,” Apple shared in its official release. “With the translation technology of Rosetta 2, users will be able to run existing Mac apps that have not yet been updated, including those with plug-ins. Virtualization technology allows users to run Linux. Developers can also make their iOS and iPadOS apps available on the Mac without any modifications.”
Apple’s move, and the roadmap the company has meticulously laid out, not only paves the way for ever more powerful, efficient products from and for developers across its own ecosystem, but it also opens the door in the PC market for a new era of custom-designed technology at the lowest levels. Some even say it compels it.
In a recent blog post, former head of Macintosh development Jean-Louis Gassée lauds the “exciting messy transition” and maintains the move will force Microsoft to “fix app compatibility problems and offer an ARM-based alternative to Apple’s new Macs.” Which will in turn domino all the way down the stack for competitors across the board.
“This won’t happen overnight and there will be an interesting mess of x86 and Arm SoC machines fighting it out in the marketplace. Large organizations need continuity and would balk at the prospect of servicing two kinds of Windows machines and apps,” Gassée predicts. “As usual, they’ll downplay Apple’s advantage and curse Microsoft for causing trouble. But if the newer machines are actually better, rogue members within these organizations will sneak in new devices and software; they always do.”