The advance of Apple silicon is not slowing down. To power the new high-end Mac mini and 14-inch and 16-inch MacBook Pro systems, Apple unveiled the all-new M2 Pro and M2 Max processors, inheriting all the improvements from the A16 processor and applied to the Mac chips, resulting in a significant performance boost over the M1 line.
Apple claims that the M2 Pro and M2 Max have 20 percent better CPU performance than the M1 Pro/Max, and 30 percent faster GPU performance. They also include the newer Neural Engine, which is up to 40 percent faster than those in the M1 series.
As impressive as these new chips are, they’re not surprising. Some rumors of more advanced manufacturing, new GPUs or other improvements have turned out to be untrue, and the M2 Pro and M2 Max appear to be exactly what we expected: the M2 scaled up with more CPU and GPU cores and a wider memory bus . In fact, the M1 Pro/Max chips had more to distinguish from the M1 than the M2 Pro/Max from the M2. Here are some of the key features worth noting.
Same CPU core design and performance as M2
When Apple introduced the M2, it claimed an 18 percent improvement in CPU performance over the M1. Now it says the M2 Pro and M2 Max have 20 percent better CPU performance than the M1 Pro and M2 Max. In other words, you can expect the same overall architectural and performance improvements as the M2 compared to the M1.
Part of this simply comes down to the number of cores. The M2 Pro and M2 Max have eight powerful cores, just like the M1 Pro/Max, but the number of efficiency cores goes from two to four. So the M2 Pro and M2 Max have 12-core CPUs, while the M1 Pro/Max have 10-core CPUs.
GPU gains are better, but there’s no major architectural shift
Apple says the GPUs in the M2 Pro/Max are 30 percent faster than in the M1 Pro/Max. That’s not surprising, given that the M2 is said to have graphics performance up to 35 percent better than the M1.
This is likely due to the addition of a few more graphics cores and some minor architectural tweaks. The M2 Pro has up to 19 graphics cores (versus 16 in the M1 Pro) and the M2 Max has up to 38 graphics cores (versus 32 in the M1 Max).
Those are unusual numbers: the number of cores is usually even in number, and often powers of two, so it’s likely that the design is for 20/40 GPU cores with room for one failed core to shut down, putting production yields at improve these big chips. Still, that’s an almost 20 percent increase in the number of cores, so with some improved caching and higher clock speeds you could get to 30 percent.
If you were hoping for an all-new GPU from Apple with modern features like ray-tracing acceleration, which GPUs from AMD and Nvidia have had for several years, you’ll be disappointed.
Memory bandwidth is the same even with more RAM
Memory bandwidth on the M2 Pro is 200 GB/sec, just like the M1 Pro. The M2 Max doubles that to 400 GB/s. So we’re almost certainly still looking at a 256-bit LPDDR5 memory bus on the Pro and 512-bit LPDDR5 on the Max. Apple improved caching in the A16, and those architectural improvements are likely to carry over to the M2 Pro and M2 Max.
While the M2 Pro has a maximum of 32 GB of RAM (the same as the M1 Pro), the M2 Max can go up to 96 GB – 50 percent more than the M1 Max’s 64 GB limit. But there’s a catch: the 96GB RAM option is limited to the version of the M2 Max with 38 GPU cores. The cheaper option with 30 GPU cores comes in at 64GB.
Only one video encoding engine, with no AV1 support
The M1 Pro had a new video encoder and decoder that added hardware acceleration for the ProRes format, and the M1 Max doubled the number of encoders to two.
Oddly enough, that’s not the case with the M2 Max, which only has one video encoder left. It supports the same formats as before: H.264, HEVC, ProRes and ProRes RAW. That means support for the newer AV1 codec is still nowhere to be found, despite it being available in current GPUs from Nvidia, AMD, and Intel. Apple is behind on this.
We noticed that all of Apple’s video production marketing benchmarks, which claim improvements of about 30 percent, cover activities like color correction or rendering 3D effects, which are typically limited by GPU performance. Apple hasn’t provided any benchmarks showing an improvement in video encoding speed, so it’ll be interesting to check out the early reviews of the M2 Max to see if a single new video encoder can keep up with the two encoders in the M1 Max .
It’s all still 5nm
There’s been a lot of speculation about when Apple will start using TSMC’s new 3nm manufacturing process. Apple would be the first major manufacturer to do so, and some rumors said the new M2 Pro and Max chips would be where Apple would make the jump.
It looks like we’ll be waiting for an M2 Ultra later this year, or possibly the A17 to be introduced with the iPhone 16 this fall. Apple says the M2 Pro and Max are made with “second generation 5nm technology”. It’s likely that this is the same process that Apple somewhat erroneously called “4nm” in its September 2022 iPhone 15 presentation. TSMC calls its N4 node an “enhanced” 5nm process, and Apple appears to be correcting its language here.