Apple chips on the table

Apple’s move to its own processors is almost over. The company’s last spring event saw the appearance of Mac Studio and M1 Ultra Processor – the strongest piece of silicone to date. But it also revealed what the future of Apple’s computers could look like.

For the first time, all Apple chips are on the table.

The first crucial insight is that Apple is now a force to be reckoned with when it comes to chips (if they haven’t already). The incredibly positive reception of the first wave of M1 computers, along with similar success M1 Pro and M1 Max-powered MacBook Pro laptops last year, The company was established in good faith. But the M1 Ultra saw Apple take its biggest swing yet, with what it boasts of being “the world’s most powerful chip for a PC.”

These chips have already become selling points for computers. Buying a Mac isn’t just about getting the Apple software or the design aesthetic anymore — it’s about getting the kind of performance and battery life that no one else can offer.

Apple fired shots at Intel’s top-tier processor, the Core i9-12900K, claiming a 90 percent improvement over the M1 Ultra in multi-threaded performance at the same power level and the ability to match Intel’s best numbers while using 100 watts less power. company Take a similar victory over the Nvidia RTX 3090 GPU, which Apple claims outperforms while consuming 200 watts less power. (Obviously, we look forward to testing these numbers ourselves in the coming days and weeks.) The Apple Silicon transition isn’t an experience anymore – it’s Apple’s future and one that PC manufacturers must pay attention to moving forward.

Photo: Apple

Next, there’s the way Apple builds its chips. Right now, Apple has four different models of its Arm-based M1 chipsets, which blur the line between product form factors in a way we don’t usually see from semiconductors. Apple takes a different approach — instead of building chips for specific hardware, Apple effectively built one really good chip: its own A-series processor. And all he was doing was scaling it up, seemingly limitless. From the phone, to the laptop, to what is claimed to be the most powerful desktop, it seems that Apple’s secret sauce is nothing more than Double the size of each slice And the Throw more cooling at every step. But it’s cool because no company has managed to do this before — and because it allows Apple to build a whole family of computers from 430 dollars to 8000 dollars (and counting) about one point in its silicon engineering roadmap.

The M1 in the MacBook Air or iPad is the same chip found in Apple’s iMac and Mac Mini desktop computers, and it works at roughly the same speeds and efficiency. The M1 Max goes from a MacBook Pro laptop to a desk with Mac Studio. And even the company’s ultra-powerful M1 Ultra isn’t quite a desktop-focused design, since it only suffices to make use of the M1 Max processors in a raincoat. Devices are tagged based on certain features or form factor, not necessarily how powerful they are.

Photo by Vjeran Pavic / The Verge

Photo by Amelia Holowaty Krales/The Verge

It’s that scaling style we’ll likely see with Apple’s upcoming Mac Pro, too Bloomberg Mark Gurman reports later this year with up to 40 CPU cores and 128 graphics cores on a chip (the equivalent of four M1 Max processors combined together, or two M1 Ultra chips). It’s another complication – more cooling is supposed to be added to compensate.

In the same vein that Apple has differentiated the Mac Studio and the Macbook Pro with different form factors, ports, and feature sets, we’ll likely see a similar shift to help the new Mac Pro stand out from the Mac Studio. The current Mac Pro is Apple’s most powerful (and most expensive) product, one that fits a very different niche than some other computers — and one that has no small share of the mistakes the company has made over the years. Apple also misjudged it What power users need from their devices.

The M1-powered Mac Pro will likely need more than just double the number of M1 cores to satisfy the pros; It needs scalability, modularity, and customization. Things like PCIe cards, user-accessible memory slots, compatibility with discrete graphics cards and external hardware accelerators — the same factors that made the last update of 2019 a success (and the lack of which led to 2016). trash can model almost straightforward). None of Apple’s Arm-based designs offered any of these things, and it remains an open question whether Apple would be interested in offering them at any level.

Photo: Apple

The sheer power of Apple’s CPU and GPU could mean it can beat today’s RTX 3090; The 128-core GPU in Mac Pro provides a larger cushion for a longer period of time. But without user-upgradable parts, Apple will force future Mac Pro buyers to anticipate all their needs from the start. We’ll have to wait for a more official announcement to see if Apple can evade the trap of leaning too hard on non-upgradable systems again, though.

The increasingly blurry streak between products also applies to the chips themselves — while core counts, the split between efficient cores, and performance vary from model to model (and even within processor families, where Apple offers a variety of configurations), the cores themselves are the same: a performance core Firestorm on the $999 MacBook Air is about the same as on the M1 Ultra from Mac Studio at $3999, Up to 3.23GHz clock speed, although more powerful chips feature additional cache and dynamic memory bandwidth. Technically, the M1’s Firestorm cores aren’t much different than those in the A14’s in the iPhone 12, although the iPhone’s cores run a bit slower.

Intel’s latest 12th generation processors are built using a similar tiered approach, with a blend of performance and efficient cores from the most powerful desktop chips to the most battery-friendly models of lightweight laptops. But Intel chips aren’t quite expanding in the same way Apple does here, with products still more traditionally divided into multiple buckets for different classes of laptop and desktop models. Intel desktop chips (mostly) don’t transfer to laptops or tablets the same way Apple does.

M2 . question

Finally, there’s the future of Apple processors. Apple Silicon is clearly here to stay (at this time, Apple only sells a pair of Intel-based devices: an old Mac Mini with very old hardware and a soon-to-be replaced Mac Pro). This means that at some point – perhaps as early as this year – we will start seeing a file next one A wave of wizards, whether it’s called “M2” or some other name.

Whatever Apple’s next generation of chips may be, it probably won’t be the same kind of huge leap forward that had to switch from Intel to the M1. Instead, it’s likely to be a gradual and incremental upgrade — similar to the changes from one generation of iPhone A-series processors to the next.

When it comes to upgrading processors, there are two effective ways to do it. You can use a new (or updated) architecture that offers more powerful or efficient CPU or GPU cores, or you can move to a smaller manufacturing node – allowing you to pack more transistors into a similar space or shrink similar devices further.

picture; an Apple

We know Apple already has designs that are better than silicon: The company’s A15 chipset has the most advanced high-performance Avalanche and energy-efficient Blizzard cores, which (at least on paper) are better than the Firestorm and Icestorm cores that replaced them (which were Apple Originally It debuted with the A14 chip in the iPhone 12 lineup). Historically, Apple has tended to focus on improving its single core designs with its A-series chipsets on the iPhone, but profits tend to be smaller from year to year.

The “M2” could follow in the future in this vein and begin updating Apple’s chipset lineup with Avalanche and Blizzard cores, potentially offering similar performance or efficiency gains as the iPhone 12 upgrade to iPhone 13. At most. One rumor from 9to5Mac It indicates that Apple is looking to do this for its M2 lineup, along with adding additional GPU cores to some of its chipset models.

Apple could also – as many rumors suggest – do a more modest upgrade and take existing M1 designs and move them to a more advanced production node. This is something that may happen as soon as this year, with reports That Apple may ship a new MacBook Air with a largely identical chipset built on the 4nm TSMC node, rather than the 5nm node it currently uses for M1 chips – which could allow Apple to increase performance and/or power efficiency.

Barring some misfortunes with the Mac Pro, it’s clear that Apple has pulled off the first generation of computers in a big way. But its competitors aren’t staying idly by: Intel is finally shipping its next-generation laptop chips, and AMD’s products are better than ever, too. And that doesn’t even include arm-based competition – like Qualcomm’s looming plans to bring the fight to Apple with its Nuvia-designed chipset in 2023.

Apple Silicon was a fresh start for the company’s PC hardware that pushed it ahead of its competition. But with the transition nearing completion, Apple has to do more than just impress it once – it needs to maintain this ongoing momentum for future products, too.