This month, Apple introduced the M2 chip – the second-generation custom silicon chip for the Mac. After the M1 chip revolutionized the Mac from November 2020, how much better is the M2†
Apple says the “M2” chip takes the performance per watt of the “M1” even further with an 18 percent faster CPU, a 35 percent more powerful GPU and a 40 percent faster Neural Engine. There are also other major improvements such as more memory bandwidth and support for up to 24 GB of unified memory.
As the second major iteration of Apple silicon, it may not be clear how significant an improvement is made to the M2 over the M1, especially as it sticks to a 5nm fabrication process, as opposed to some rumors that suggested there would be a bigger leap in performance and efficiency. The M2 chip debuts in the 13-inch MacBook Pro and the redesigned MacBook Air, so how much better the M2 is than its predecessor could be an important consideration when buying a new Mac. Read on to learn about the differences between the two chips.
M1 chip
- Created using TSMC’s 5nm process (N5)
- 16 billion transistors
- 4 powerful “Firestorm” cores
- 4 energy-efficient “Icestorm” cores
- 3.2GHz CPU Clock Speed
- CPU cores first seen in the iPhone 12 lineups A14 Bionic chip
- 8 core GPU
- Support for 8 GB or 16 GB unified memory
- 68.25 GB/s memory bandwidth
- neural motor
- Media engine for hardware accelerated H.264 and HEVC
- Video decoding engine
- Video encoding engine
- Image Signal Processor (ISP)
M2 chip
- Made with TSMC’s enhanced 5nm process (N5P)
- 20 billion transistors
- 4 powerful “Avalanche” cores
- 4 energy-efficient “Blizzard” cores
- 3.49GHz CPU Clock Speed
- CPU cores first seen in the iPhone 13 Lineups A15 Bionic Chip
- 10-core GPU
- Support for 8 GB, 16 GB or 24 GB unified memory
- 100 GB/s memory bandwidth
- 40 percent faster neural motor
- Media engine for hardware accelerated H.264, HEVC, ProRes and ProRes RAW
- Higher bandwidth video decoding engine
- Video encoding engine
- ProRes encoding and decoding engine
- “New” Image Signal Processor (ISP)
Manufacturing Process and Transistors
Like the A14 Bionic, the M1 chip is built using TSMC’s first-generation 5nm fabrication process. On the other hand, the M2 uses the 5nm process of second-generation TSMC, such as the A15 Bionic chip. The M2 adds four billion extra transistors for a total of 20 billion – 25 percent more than M1. The improved 5nm manufacturing process is at the heart of many of the M2’s performance and efficiency improvements.
Processor
The “M1” and “M2” both have four high-performance and four energy-efficient cores, but while the “M1” has “Firestorm” and “Icestorm” cores from the A14 Bionic chip, the “M2” offers “Avalanche” and “Blizzard ” of the A15 Bionic chipping. According to Apple, this results in 18 percent better multithreaded performance than M1.
In early Geekbench benchmarks, the M2, which runs at 3.49 GHz compared to 3.2 GHz for the M1, achieved a single-core score of 1,919, which is about 12 percent faster than the 1.7M1 13-inch MacBook’s single-core score Pro. The M2 achieved a multi-core score of 8,928, an increase of approximately 20 percent over the 7,419 score of the M1 model. This matches Apple’s claim that the M2 chip is up to 18 percent faster than the M1.
Both chips have powerful cores with 192 KB L1 instruction cache and 128 KB L1 data cache. The low-power cores have a 128 KB L1 instruction cache, 64 KB L1 data cache, and a shared 4 MB L2 cache. The only difference here is that the shared L2 cache is larger on the M2 chip — 16 MB instead of 12 MB on the M1.
GPU
The M2 has two more GPU cores compared to the M1, resulting in a moderate boost in graphics performance. Apple says the “M2” has up to 25 percent better graphics performance than the “M1” at the same power level, and up to 35 percent better performance at maximum power. In early benchmarks from Geekbench Metal, the M2 chip scored 30,627, a notable improvement over the M1’s 21,001 score.
media engine
Both the M1 and M2 have dedicated video encoding and decoding engines for hardware-accelerated H.264 and HEVC, but the M2’s video engines are also capable of accelerating ProRes and ProRes RAW to enable multi-stream playback of 4K and 8K video to enable. In addition, the M2’s media engine includes a higher bandwidth video decoder, which supports 8K H.264 and HEVC video.
Unified Memory
The M1 and the M2 come in 8GB or 16GB unified memory configurations, but the M2 adds an additional, premium 24GB configuration. The M2’s memory controller can also deliver 100 GB/s of uniform memory bandwidth, a significant improvement over the M1’s 68.25 GB/s memory bandwidth.
Other improvements
M2 includes improvements to several Apple custom silicon technologies. For example, the Neural Engine can process up to 15.8 trillion operations per second – over 40 percent more than “M1”. The M2 also includes Apple’s latest Secure Enclave and a new Image Signal Processor (ISP) for better image noise reduction.
Final Thoughts
Overall, the M2 chip offers moderate improvements over the M1, even if most M1 users are unlikely to notice any significant improvements when upgrading to the M2. The improvements of the M2 are generally worthwhile, if not transformative, and the chip will certainly provide a more up-to-date experience with lower-spec Apple silicon machines – especially for those coming from one on Intel. based machine.
While the M2 offers improvements across the board thanks to the improved 5nm process, updated cores, and additional GPU cores, the major upgrades come for users who need to work with video, as well as those with memory-intensive workflows. The M2’s higher bandwidth video decoder and dedicated engine for ProRes and ProRes RAW video provide significant improvements for video editors, while the 24 GB unified memory layer and 100 GB/s memory bandwidth significantly increase the capacity of the M2 machines to work with. memory-hungry applications and intensive multitasking.