When Apple released the M1 chip in late 2020, we were amazed at the speed improvements over its Intel predecessors. A year later, Apple did it again with the M1 Pro and M1 Max. In March 2022, Apple unveiled the M1 Ultra, completing the lineup of M1 chips and drastically changing our expectations for Apple’s roadmap. At WWDC in June 2022, Apple introduced the next generation of Apple silicon with the M2. So what now? Here’s how the Apple silicon transition started and has gone so far — and where it’s headed.
M1: Dec 2020
Apple’s M1 processor is based on the 5nm A14 chip that first appeared in the iPad Air (4th generation) and iPhone 12. It has four powerful cores with 192 KB L1 instruction cache and 128 KB L1 data cache and shared 12 MB L2 cache and four power-efficient cores with 128 KB instruction cache, 64 KB L1 data cache, and shared 4 MB L2 cache. That makes a total of eight cores evenly distributed in power and efficiency, leading to huge speed boosts over the previous models. The system-on-a-chip also has an eight-core GPU in most models (the entry-level MacBook Air and 24-inch iMac have a 7-core GPU) with 128 units of execution and up to 24576 concurrent threads.
Memory has also changed. With the M1, the LP-DDR4 memory isn’t just soldered to the motherboard, it’s actually part of the chip itself. That means it’s faster and more efficient than before, but it’s also a bit more limited: you can only get 8GB or 16GB in an M1 Mac, and there’s no way to upgrade it after purchase. (That shouldn’t come as a surprise to MacBook buyers, but the same goes for desktop models, though we’re not sure about the Mac Pro just yet.) And finally, the chip has a 16-core Neural Engine, along with the Secure Enclave and USB4/Thunderbolt support.
M1 Pro and M1 Max: October 2021
We heard about the development of an M1X chip earlier this year, but the rumors weren’t quite right. Apple calls its next-gen processors the M1 Pro and M1 Max, and true to their name, they’re a giant leap from the M1.
Built using the same 5nm process as the M1, the M1 Pro and M1 Max bring a new 10-core CPU, including eight high-performance cores and two high-efficiency cores, delivering speeds up to 70 percent faster than the M1. The M1 Pro offers up to 200 GB/s of memory bandwidth with support for up to 32 GB of unified memory, while the M1 Max delivers up to 400 GB/s of memory bandwidth with support for up to 64 GB of unified memory.
On the graphics side, the M1 Pro has a 14-core or 16-core GPU that is up to 2x faster than M1, while the M1 Max adds a 32-core GPU option for up to 4x faster graphics performance than M1. According to Apple, the new M1 Max MacBook Pro ProRes video in Compressor can transcode up to 10x faster compared to the Intel 16-inch MacBook Pro.
In addition, the chips also feature a 16-core Neural Engine, additional Thunderbolt 4 controllers, and a new display engine that can power up to four external displays on the M1 Max. You’ll find them in the 14- and 16-inch MacBook Pro.
M1 Ultra: March 2022
The M1 Ultra came as a surprise at Apple’s Peek Performance event in March. Apple did a good job of keeping this processor a secret – the rumors that surfaced about the Mac Studio a few days before the event simply described the Ultra as a variant of the M1 Max.
It turns out it’s misleading to call the M1 Ultra a variant: it’s actually two Max chips working together as one. Apple has created an extremely fast connection called UltraFusion, which provides 2.5 TBps of bandwidth between the two dies, allowing the Ultra to be recognized by macOS as a single SoC.
Since the Ultra is two Maxen, you can double the specs of a single Max and get the Ultra low. It has 20 CPU cores, with 16 performance cores and 4 efficiency cores, and a 48-core or 64-core GPU. The M1 Ultra is available with 64 or 128 GB of unified memory, with a memory bandwidth of 800 GBps. And it has a 32-core Neural Engine.
The Ultra also has all the media engines found in the Max, but again, it has twice as many: two video decoding engines, four video encode engines, and four ProRes encoding and decoding engines. Simply put, this is an ideal processor for video editing.
M2: June 2022
Apple took the wraps off the M2 at WWDC in June 2022. The first Macs with the new chip are the MacBook Air and the 13-inch MacBook Pro. The M2 will eventually replace the M1 as the basis for the M-series, but Apple will be offering Macs with the M1 for months and maybe years to come.
The M2 is a 5nm chip with a basic configuration that has the same number of cores as the M1: eight CPU cores (four performance, four efficiency) and an eight-core or 10-core GPU. That’s the same as the M1, but Apple has made improvements to improve performance: the L2 cache of the performance cores has been increased from 12 GB to 16 GB and the clock speeds are higher. Apple said the M2 offers an 18 percent overall CPU boost over the M1 and a 35 percent boost with GPU performance.
The M2 also has a higher maximum RAM configuration than the M1-24GB with 8GB and 16GB options. The M2’s memory bandwidth is now 100 Gbps, up from the M1’s 68.25 GBps. The 16-core Neural Engine is also faster than that of the M1. The M2 also has an enhanced media engine that supports H.264 and HEVC encoding and decoding up to 8K resolution and includes the ProRes support for video acceleration.
The M2 will likely make its way to the Mac mini later this year. It could also make its way to the 24-inch iMac, but since that model shipped in May 2021, it may not get an update until early 2023.
M2 Pro and M2 Max: Mid to late 2023
The next generation of Apple’s high-end laptop processors could have different performance levels, such as the M1 Pro and M1 Max, with as many as 20 compute cores, comprising 16 high-performance and four high-efficiency cores, according to a Bloomberg report. Based on what we know about the M2, the M2 Pro and Max could have 12 CPU cores, up to 38 or 40 GPU cores, and higher RAM limits. Based on current cadence, we expect these to launch in 2023, possibly at WWDC or the fall Mac event, but some reports suggest they could launch later in 2022.
M2 Extreme: mid 2023
When John Ternnus announced the M1 Ultra processor at the “Peek Performance” event, he stated that it was the last chip in the M1 family. Later in the presentation, he teased the latest Mac to move to Apple silicon, the Mac Pro. Assuming both things are true, Apple is working on a workstation-caliber desktop chip for the next generation of its Mac Pro tower that will be something other than a mere upgrade to the M1 Ultra. The Mac Pro chip is rumored to have up to 40 cores due to a four-die process or the pairing of chips with 32 performance cores, as well as a 64-core or 128-core GPU.
Those numbers look a lot like two M1 Ultra chips. So it’s possible that Apple will do something similar to what it did with the M1 Max by fusing two M1 Ultra chips together into a megachip that yields those highly rumored specs: 40 CPU cores (32 performance, eight efficiency), 128 GPU cores, 64 neural Motor cores and up to 356 GB RAM. Gurman teased the existence of that same chip that could launch next year, tentatively dubbed the M2 Extreme.
We don’t know if Apple will continue to offer PCI slots for graphics and storage or just add more ports for expansion, but the Mac Pro is definitely the most interesting Mac in Apple’s silicon transition. We were able to take a look inside the machine at WWDC with a launch in November or December.
M3: end of 2023
According to the latest rumors, Apple is already working on the third generation of its M-series processor. It will likely be the first Mac processor to use a 3nm process, offering a significant speed boost over the M2 due to a new architecture, potentially with more GPU and CPU cores, higher RAM limits, and additional Thunderbolt capabilities. gates. The code name is Ibiza.
M3 Pro and M3 Max: Late 2024 – Early 2025
We don’t know much about the M3 Pro and M3 Max, except that their codenames are reportedly Lobos and Palma, and the chip will be based on the M3 processor. Based on the M1 timeline, this chip probably won’t arrive until 2025