Rise of ARMs: how changing the Mac processor could change the world

The return of the ARM processor and RISC technology to public discussion about the desktop market is like stumbling across an episode of “Friends” flipping through “Favorite Channels” on your TV remote control. First, you get a smiling little smile, a moment of warmth in your heart, watching those formerly young people dance with their rainbow umbrellas. You remember the dumbest moments when the characters did things you didn’t expect, before television saturated with those moments on a daily basis.

Then, over the next five minutes of the show, the characters recite a script you’ve seen so often that you can almost see the directors’ handwritten margin notes in your mind. You know where it goes. So, consider retiring and looking for something that won’t lead you exactly to the same tired situation comedy path.

Too: Arm-based Mac: Smart move for Apple, but irrelevant to the future of Windows PCs

Since the 1980s, the most successful (that is, the most read) technology news has been about competitive methods: MS-DOS vs. DR DOS, GEM vs. Windows, Apple vs. IBM, Motorola vs. Intel, RISC vs. CISC, Linux vs. Windows, Europe vs. Windows, Apple vs. Windows, Apple vs. the music industry, Apple vs. ___. Most of my career has been on technology issues that are best symbolized by a foothold.

Hence, the fact that recent Apple news resurrects the RISC vs. debate CISC of over 30 years should be welcomed by any tech news editor who appreciates the poignant power of reruns. During the pandemicWhen it is difficult to craft a story with a more difficult impact than the everyday issues of just going out, we can use as many reps as we can get.

The Apple ARM Processor Moment, as a few dozen amateur YouTube historians will inevitably call it, is a sign of the impending collapse of a very old (at least as old as in the industry) and very frequent deadlock. In late June, Apple announced that it was shifting production of the Intel x86 Mac CPU to its own ARM-based “Apple Silicon”. Using a design and manufacturing methodology inspired by the company’s existing approach to ARM-based chips for iPhone and iPad, the company will build custom A12Z processors for Mac, using the ARM64 instruction set licensed from ARM Holdings, Ltd. (Apple was actually a co-founder of the original manufacturer of ARM processors and a long-time shareholder in ARM Holdings.)

I know you are tempted. You have reached that point of completion. The Back button is within reach. However, I ask you this once, be patient with me. Yes, this column is on the same garden path you have walked before, I admit it. Yes, it is a pandemic, and it is hard to worry about technology when more than 1,000 Americans die every day, and the undercover police are taking out their frustrations on suburban mothers with batons. But no, this will not take you to the same destination you have seen a million times.

The end of Moore’s law

Until a few years ago, Intel’s formula for business success has been Moore’s Law, named for its founder, Gordon Moore. There was a virtuous business cycle by bundling more components into integrated circuits at a predetermined rate. Put another way, there is a market rate to appease consumer interest in bigger and better processors, even if “bigger” is not something that the consumer can physically see. If you can produce and sell electronic products with components at that market rate, you can be sure of a comfortable margin.

RISC’s counter-argument to Moore’s Law, as evidenced by ARM processors, has always been a David vs. Goliath (you have to love that “vs.”). You can get an efficiency gain if you can do the job of one big instruction with eight to ten smaller, logically connected instructions. And under controlled circumstances, those gains could be greater than the performance benefits of bundling more components. That’s why the smartphone in your purse or pocket can perform the function of a full-power PC if you so choose, despite the fact that your CPU doesn’t have an electric fan.

Must read:

Until now, x86’s competitive advantage, at least in the larger computer markets, has been maintained with a bit of leverage, supplied in due course by a number of fortunate circumstances. The software foundation for almost all large-scale computing has been compiled for x86 processors. Most people who still use PC still need Windows. (Yes, there is a Windows 10 for ARM processors. But have you seen it?) The accelerator industry, the GPU industry, and all the interfaces we have built for computers are the ubiquity of Industry Standard Architecture, whose latest twist on the “vs.” The arena arrived just before Iraq invaded Kuwait.

Not that x86 processors are the same gas-consuming giants as in the Pentium days. Intel engineers are responsible for many of the biggest efficiencies gains data centers have seen in the past six years. At the start of the Obama administration, the world’s data centers were projected to consume up to 12% of the world’s total electric power by the end of his second term. Today, researchers including Jonathan Koomey (according to my gauge, the Anthony Fauci of electricity) have shown that that figure is actually less than 1%.

So, we breathe a sigh of relief, for now. The unsustainability of our environment, along with that of our government and our culture, is something that we can reasonably ignore, within certain limits, as long as economies of scale, such as that discovered by Gordon Moore, continue. Don’t Break Us We know that we live today with a technology infrastructure that is unsustainable, in and of itself, in the long term, not just on x86 processors, but on the entire infrastructure network that supports them. AT&T has been ringing this wake-up call for years and repeats this message whenever possible.

The commercial end of the brave new world

Scale economies have limits. Moore’s Law demonstrated that competitive advantage and commodification could coexist and that the former could comfortably outperform the latter. All he needed was 1) a relatively stable global economy, 2) a nominally functional supply chain, 3) a secure reserve of disposable income equally distributed among consumers, 4) full and uninterrupted cooperation of the laws of physics.

At this point in history, we are one for four, and the one is hanging on a chiffon thread. A bad phone call from China, and everything is lost.

In any technology market since the invention of rock, there are two forces at work simultaneously. The supply side seeks to gain a competitive advantage and then enclose it. The demand side effectively drives every product and service toward mass commodification, to ensure availability and affordability. Every effort to automate the process, or, like Moore’s Law, to declare it automated for us, is a balancing act with these two forces. A market will tolerate their coexistence, within certain limits, as long as we play as if everything were peaceful and copacetic, and the “vs.” in our headlines it is not more significant than a professional wrestling match.

Too: Apple silicon: why developers shouldn’t worry TechRepublic

We have reached those limits, in fact, we have exceeded them. We can no longer put things on precarious platforms and wait another 18 or 24 months of uninterrupted profitability. Apple switching its Macs from x86 to ARM, with the promise of increased efficiency and performance for x86-based programs, should be a warning warning to all of us in the technology business, as we all witness one country somewhere, suddenly wear masks Our free ride is over. The days when Linux vs. Windows even mattered, they have passed. Thirty-year replays of old architectural disputes could also be the Lincoln / Douglas debates.

Our next moves in this world must be bold, far bolder than even Apple’s, so that we leave behind nothing but the rotting remnants of a repeat of the downfall of our society.

I told you.