Flashback: How the Apple M1 evolved from Apple’s iPad chipset

Apple’s first dedicated chipset, the Apple A4, was launched in 2010 with the original iPad and also appeared in the iPhone 4 a few months later. The A4 was manufactured by Samsung and used an improved Cortex-A8 CPU core dubbed “Hummingbird”.

Hummingbird was developed jointly with Samsung and Intrinsity and was announced in 2009 as the “world’s fastest ARM Cortex-A8 processor”. Multiple assignments had to be made in order for the core to reach its 1 GHz target. Apple acquired Intrinsity just months after unveiling the iPad. And two years before that, it acquired PA Semi.

After these major acquisitions, Apple embarked on working on internal chip designs for use in its mobile products. Today’s story begins in 2012 where we will focus on the improved X series of chips, which preceded the flagship Apple M1. AX chips are mainly used in iPads, but they sometimes appear in Apple TVs as well.

The second generation iPad introduced the Apple A5 to the world in 2011. It still uses off-the-shelf components, a Cortex-A9 CPU core from ARM and a PowerVR SGX543 GPU from Imagination. The third-generation iPad arrived a year later with an improved version of that chip, dubbed the Apple A5X, which made the ball roll.

The A5X doubled the GPU cores (from MP2 to MP4) and also incorporated a new four-channel memory controller, which delivered data transfer speeds of up to 12.8GB/s, nearly three times the bandwidth of the A5.

Flashback: How the Apple M1 evolved from Apple's iPad chipset

Future AX chips will follow the same game plan – use the same hardware, only more of them. Tablets are larger than phones, which means they have larger batteries and more space for heat dissipation, so they can handle more powerful chips.

The Apple A6 is distinguished by presenting the first dedicated CPU core designed in-house by Apple, called “Swift”. The GPU still comes from the imagination. The A6X was a bit disappointing as it only added an extra GPU core.

Two years later, the Apple A8X appeared, the first in the series to expand the hardware of the CPU as well as the GPU. It added an additional Typhoon core, for a total of three, while it doubled the number of GPU cores to eight. The A9X reverted to having the same CPU as the regular A9, but that was the last time – since then all AX chips will have bigger CPUs.

Flashback: How the Apple M1 evolved from Apple's iPad chipset

The 2016 Apple A10 chipset was the first for the company to adopt the big LITTLE architecture. It contained two large tornado cores along with two small Zephyr cores. A year later, the A10X came with three of each, with double the number of GPU cores.

Small cores are great for efficiency, but having more than a few doesn’t add much performance. This is why the Apple A12X chipset from 2018 only doubled the number of large CPU cores (to four), while using the same number of small cores (also four). The GPU has been upgraded to a 7-core design, and an octa-core version will arrive in 2020 with the name Apple A12Z.

Let’s jump into 2020 — after years of using Intel processors, Apple called them in and announced the first batch of Macs powered by the Apple M1. This was also a transition away from x86 and toward ARM, the same set of ARM instructions that power iPhones and iPads.

And this is no accident, the Apple M1 used slightly modified versions of the components in the A14 (the chip inside the iPhone 12 and the fourth-generation iPad Air) – large Firestorm cores and small Icestorm cores, which are also the same GPU architecture.

Flashback: How the Apple M1 evolved from Apple's iPad chipset

But as we’ve already seen, the trick to making the chipset faster is to add more cores. The M1 doubled the large CPU cores and doubled the GPU (although it introduced chipsets with 7-core GPUs as a cost-saving measure). As with the 12X, the smaller CPU cores were left as is. It helped that Apple’s designs were already on top in terms of performance and efficiency (TSMC deserves some of the credit for that), so the M1 handled desktop tasks with ease, even when passively cooled.

The Apple M2 chipset announced earlier this month follows the same pattern, although this time it is based on the A15 (iPhone 13) chipset. The M1 had Pro, Max and Ultra variants, and the M2 surely will too.

These just use different multipliers, for example, the M1 Pro has 50% or 100% larger CPU cores than the base M1 and doubles the GPU cores. The Pro cut the smaller cores in two, but as already discussed, a few are necessary. Max uses the same CPU formula, but offers 3 to 4 times as many GPU cores as the base M1. Ultra doubles CPU and GPU resources (already built from two Pro chips).

2012/2012 Apple A5 A5X
Large CPU cores 2x Cortex-A9 2x Cortex-A9
Few CPU cores
2012 Apple A6 A6X
Large CPU cores 2x Swift 2x Swift
Few CPU cores
2014 Apple A8 Apple A8X
Large CPU cores 2x Typhoon 3 times Typhoon
Few CPU cores
GPU 6XT 4 core 6XT Octa Core
2015 Apple A9 Apple A9X
Large CPU cores 2x Twister 2x Twister
Few CPU cores
GPU 7XT Hexa-Core 7XT 12 core
2016/2017 Apple A10 Apple A10X
Large CPU cores 2x Hurricane 3x Hurricane
Few CPU cores 2x exhale 3x exhale
GPU 7XT GT Hexa-Core 12 core
2018/2020 Apple A12 Apple A12X / A12Z
Large CPU cores 2x whirlpool 4x vortex
Few CPU cores 4x Storm 4x Storm
GPU G11P 4-core 7/8 core
2020 Apple A14 Apple M1
Large CPU cores 2x Firestorm 4x firestorm
Few CPU cores 4x ice 4x ice
GPU Apple 4 core Apple 7/8 core
2021/2022 Apple A15 Apple M2
Large CPU cores 2x avalanche 4x Avalanche
Few CPU cores 4x Blizzard 4x Blizzard
GPU 4 core 8/10 core