The M1 is a great chip. Essentially an “X” variant of the A14 chip, it takes the iPhone and iPad processor and doubles the powerful CPU cores, GPU cores and memory bandwidth. The M1 chip is so good that it’s just as great for tablets and thin-and-light laptops as it is for desktops, easily outperforming any competing chip with similar power consumption and offering comparable performance to processors that consume at least twice the power.
Now a year and a half later, and after delivering three more powerful variants of the M1 (M1 Pro, M1 Max and M1 Ultra), it’s time for the next generation. Announced at WWDC and appearing first in the new MacBook Air and 13-inch MacBook Pro, the M2 is essentially the system-on-chip we predicted: what the M1 is to the A14, the M2 is. for the A15. It’s made of 20 billion transistors, 25 percent more than M1, and while still built using a 5nm manufacturing process, it’s a newly improved “second generation” 5nm process.
Here are the main ways the M2 has improved over the M1.
M2 vs M1: CPU
The M2 doubles the high-performance CPU cores of the A15, for an eight-core setup of four high-performance cores and four high-efficiency cores. In that respect it is just like the M1.
But there are some architectural improvements. On the performance cores, the shared L2 cache has grown from 12 MB to 16 MB, and the clock speeds could be slightly higher. The efficiency cores share the same cache as the M1, but receive different architectural improvements (probably higher peak clock speeds and faster memory access, as in the A15).
Together, Apple says this gives the M2 18 percent better overall CPU performance than the M1. This means that you can probably expect Geekbench 5 CPU test results somewhere around 8,800-9,000. That’s essentially comparable to a Ryzen 7 3800X desktop CPU at about 20 percent or less of its power consumption.
As a benchmark against the latest mobile low-power chips, Intel’s best current ultraportable CPU, the Core i7-1255U, scores just under 7,000 while consuming more than twice the power. There are definitely faster laptop processors available from both Intel and AMD, but they consume significantly more power and are best compared to M2 Max or M2 Ultra, when they arrive.
M2 vs M1: GPU
The A15 made an interesting change from the A14 before it. The number of GPU cores increased from 4 to 5, but that 5th core is only enabled in the iPhone 13 Pro and Pro Max. The M2 doubles the GPU cores of the A15 (as the M1 did through the A14), so it’s available with up to 10 GPU cores. However, the entry-level MacBook Air only has 8 GPU cores enabled.
If you simply have 25 percent more GPU cores, you would expect GPU performance to be up to 25 percent better. But many graphics performance tasks are limited by memory bandwidth, and M2 makes a big improvement there. Along with other refinements (probably a higher maximum clock speed made possible by the refined manufacturing process), Apple says GPU performance is up to 35 percent better than M1, but power consumption has also increased slightly. Apple’s chart actually shows the performance gain of 35 percent, but shows a capital gain of nearly the same amount. However, Apple claims that the M2 chip delivers 25 percent better performance at the same power level as M1.
25 percent more cores and 25 percent more performance. Who would have thought?
Still, this looks like an extremely power-efficient GPU. Apple likes to make wild comparisons, like saying it’s 2.3 times faster than the Intel Core i7-1255U at the same power level. We notice that Apple hasn’t compared its chip to AMD’s ultraportable laptop chips, which are generally superior to Intel’s in that regard.
In a way it doesn’t matter. Graphics performance improvements are always welcome, but 3D graphics performance is an area where you’d only compare it to a Windows PC insofar as it affects content creation apps like Adobe Premiere. It’s always dubious to compare processors of different architectures, and that goes doubly for trying to generalize “graphics performance” including GPU compute power, real-time 3D rendering, and more.
Suffice it to say that the M2 has a 25 percent larger GPU and is about that much faster, just like the A15 before the A14. You see a pattern here, right?
M2 vs M1: Memory
The memory subsystem is an area where the pattern “M2 is to A15 if M1 is to A14” is false. The A14 and A15 share the same main memory subsystem specifications: a 64-bit wide LPDDR4x interface. The M1 doubled that to 128 bits wide and stayed with LPDDR4x, for a peak of 68.25 GB/s, the M2 makes the switch to LPDDR5x, boosting the memory bandwidth to 100 GB/s.
Note that the M1 Pro has also switched to LPDDR5x, with a 256-bit memory interface giving it 200 GB/s of bandwidth. The M1 Max doubled that to a 512-bit interface, for 400 GB/s.
So while the M2 has 50 percent more memory bandwidth than the M1, it doesn’t required It’s true that the M2 Pro and M2 Max will have 50 percent more memory bandwidth than the M1 Pro/Max. Apple would need to make a wider memory bus for this, which is possible, but it’s starting to get pricey and complicated.
In addition to the big boost in memory bandwidth, the M2 is available with up to 24 GB of RAM. The M1 only offered 8GB and 16GB configurations, both of which are still available on the M2.
While it wasn’t mentioned outright, we’re willing to bet that the system-level cache (an on-chip cache that can be accessed by every aspect of the chip) is also 50 percent larger on the M2. Apple has increased this cache from 16 GB on the A14 to 32 MB on the A15. The M1 had 24MB of SLC and it’s fair to expect this to have doubled to 48MB in the M2. We won’t know until the M2 MacBooks ship in July and can be thoroughly tested, but the size of the SLC cache is a big deal. It helps with everythingbecause it can be accessed by the CPU, GPU, Neural Engine, media encoders, you name it.
M2 vs M1: other improvements
Of course, Apple is quick to point out that the M2 is more than a CPU, GPU and RAM. It’s a complete system-on-chip and includes key hardware acceleration blocks for the kinds of advanced features Apple continues to add to macOS and iPadOS. The Neural Engine, while still 16 cores, can perform up to 15.8 trillion operations per second, more than 40 percent more than the 11 trillion operations of the Neural Engine in the M1. This is exactly the same as the jump from the A14 (11 trillion) to the A15 (15.8 trillion).
The media engine, responsible for speeding up the encoding and decoding of audio and video, has also been upgraded from the one in the A14 to the newer engine in the A15. It supports H.264 and HEVC encoding and decoding up to 8K resolution and supports ProRes video acceleration. Interestingly, while the M1 does not have this version of the media engine, the M1 Pro and M1 Max do. Essentially, the M1 that comes with the media engine from the A14, and the M1 Pro, Max and Ultra, as well as the M2, has the media engine from the A15 (two in the M1 Max and four in the M1 Ultra ).
It’s quite possible that the media engine in the A16 will be upgraded again (perhaps with AV1 hardware acceleration) and the M2 Pro, Max and Ultra will be upgraded to that version.
All in all, it looks like the M2 is a nice upgrade over the M1, if not revolutionary. It takes all the architectural improvements we saw in the A15 and applies them to a thin and light laptop class chip in exactly the same way the M1 did for the A14. And since later M1 processors (the M1 Pro, Max and Ultra) gave us improvements like LPDDR5x memory and the newer media engine, it’s not a clear win across the board.
It will be interesting to watch Apple’s evolution towards the inevitable M2 Pro, M2 Max and M2 Ultra. We suspect they were made using TSMC’s more advanced 3nm process technology, and may include some of the improvements we’ll see in the A16 later this year when the iPhone 14 Pro is announced – likely an improved media engine and perhaps also a new Neural Engine. The M2 is a great start to Apple’s second-generation Apple Silicon for the Mac (and iPad Pro), but not surprisingly.