So while Apple’s Far Out event on September 7 was a decidedly mobile event, there was something for those of us who dig deep into the nuts and bolts of computers.
I’ve had the privilege of testing some of the best processors on the market, from the best from Intel to the best AMD processors available, and even a recent deep dive into Apple Silicon. Computer processors have taken on an aura of exceptionalism that makes even the best phone processors look almost quaint, but look under the box and we’re starting to see some convergence, something the Apple A16 Bionic showcases more than ever.
To be clear, the new A16 Bionic isn’t a desktop chip or even one that can rival the best laptops, but given its specs, there are a number of things that point to it being more like these last two than you are. might initially think.
16 billion transistors is a lot for a processor, any processor
The central component of a processor is the transistor, the nanoscopic electronic switch that transforms electrical pulses into zeros and others that can present data and logic operations. This is the neuron of any microprocessor, so the more neurons you have, the more powerful the processor.
Being able to squeeze 16 billion transistors with aB into a mobile chip is nothing short of extraordinary, especially when you compare it to Apple’s M2 chip, which tops out at 20 billion. This puts the A16 Bionic at about 80% the transistor density of the Apple M2, but even more important is the size of these transistors.
The A16 Bionic is built using TSMC’s 4nm node, as opposed to the 5nm node used to manufacture the Apple M2. This means that even though the A16 Bionic matrix is smaller than the M2, it still reasonably approaches density parity in absolute terms.
This also allows a 5-core GPU and a 16-core neural engine to sit in the SoC along with the CPU, and while the A16 Bionic’s GPU is half the size of the M2, it should still be highly capable of some impressive graphics, especially for a mobile phone processor.
The neural engine, meanwhile, is the same size as the M2, and this is where much of the phone’s enhanced power can show itself, especially when it comes to editing photos and videos in real time.
Moore’s law is still one thing
The other thing to consider when it comes to the Apple A16 Bionic and Apple M2 chips is that there is still a physical limit to how many transistors you can fit.
This hard limit is set by physics, in fact, as transistors are already working at truly atomic scales. And while desktop processors especially will have more room to physically grow in size – much more than laptop processors and definitely more than those in phones and tablets – we’re really at the point where the physical constraints of array size are the that determine the performance of a processor. potential power rather than some remarkably smaller transistor in a desktop product.
Given that kind of constraint, what the A16 Bionic is likely to achieve in terms of performance is fantastic, but it’s still hitting the limits of transistor density a lot harder than desktop chips are likely to do for a while yet.
This means that high-end phone processors will still lag behind desktop and laptop processors, and that gap is likely to widen in the future because they need to be physically smaller to fit in a phone or tablet.
This is where the issue of transistor density will really come into play, as as we’ve seen with the M1 Pro, M1 Max and especially the M1 Ultra, utilizing the physical space you have for performance gains is a huge asset for these chips. of desktop and laptop.
So while the A16 Bionic appears to be quite powerful, there is literally a lot of room to grow, unlike Apple’s M-series chips, so any performance gain the A16 Bionic can squeeze is really limited to the effectively smaller transistor size than the A16 Bionic. 4nm node compared to the 5nm node used in the A15 Bionic and especially something like the Apple M1 chip. The latter was able to physically grow on the larger M1 Pro and M1 Max chips, where transistor density has a much greater impact on performance.
Phone processors will hit a wall long before MacBook chips
While it’s obvious that the A16 Bionic could easily run a computer from just a few years ago, including some of the best MacBooks and Macs that ran some of the best Intel processors of the day, the performance gains in Apple’s MacBook and iMac lines will accelerate ahead. of its mobile chips in terms of generation-to-generation performance gains.
As powerful as the A16 Bionic might be, it would struggle to run a MacBook Air, although it could, in theory, do so with some restrictions. After all, the Apple M1 chip also had 16 billion transistors, although it had a larger 7 or 8-core GPU.
And while it might have been able to power the kind of hardware on an older MacBook Pro running an older Intel chip, in no universe would a modern MacBook Pro, even the 13-inch, run on an A16 Bionic without seriously lowering your expectations.
Gen-on-gen, the Bionic A15 had 15 billion transistors, while Apple’s latest iPhone chip has 16 billion, or an increase of about 6.7%. Meanwhile, the Apple M2 saw a 25% increase in processor density over the Apple M1. Apple probably won’t exactly repeat this feat with the M3 (although 25 billion transistors aren’t entirely out of the question), but it will almost certainly surpass the 6% to 7% increase we’re likely to see in the A17 Bionic.
When the M3 launches in the next few years, no iPhone chip will come close to competing with its raw performance, and that gap is likely to only widen as time goes on. That’s not to say the A16 Bionic isn’t impressive, but what we expect from the best cheap processors with integrated graphics in the coming years is likely to be even more so.