Jump to content

Apple M2

From Wikipedia, the free encyclopedia
(Redirected from Apple M2 Max)

Apple M2
The icon for the Apple M2 ARM-based system on a chip used by Apple Inc. in its software, advertising et cetera.
General information
LaunchedJune 24, 2022; 2 years ago (2022-06-24)
Designed byApple Inc.
Common manufacturer
Performance
Max. CPU clock rate3.49 GHz[1]
Cache
L1 cachePerformance cores: 192+128 KB per core
Efficiency cores: 128+64 KB per core
L2 cachePerformance cores: 16–64 MB
Efficiency cores: 4–8 MB
Last level cacheM2: 8 MB

M2 Pro: 24 MB
M2 Max: 48 MB

M2 Ultra: 96 MB
Architecture and classification
ApplicationNotebook (MacBook family), tablet (iPad Pro and iPad Air), desktop (Mac Mini, Mac Studio, Mac Pro), mixed reality headset (Vision Pro)[2]
Technology node5 nm (N5P)
Microarchitecture"Avalanche" and "Blizzard"
Instruction setARMv8.6-A[3]
Physical specifications
Transistors
  • 20–134 billion
Cores
  • 8–24 (4–16 high-performance + 4–8 high-efficiency)
Memory (RAM)
  • 6400 MT/s LPDDR5 memory (up to 192 GB)
GPUApple-designed integrated graphics (8–76 core)
Products, models, variants
Variant
History
PredecessorApple M1
SuccessorApple M3
Mac transition to
Apple silicon
The Apple M1

Apple M2 is a series of ARM-based system on a chip (SoC) designed by Apple Inc., launched 2022 to 2023. It is part of the Apple silicon series, as a central processing unit (CPU) and graphics processing unit (GPU) for its Mac desktops and notebooks, the iPad Pro and iPad Air tablets, and the Vision Pro mixed reality headset. It is the second generation of ARM architecture intended for Apple's Mac computers after switching from Intel Core to Apple silicon, succeeding the M1. Apple announced the M2 on June 6, 2022, at Worldwide Developers Conference (WWDC), along with models of the MacBook Air and the 13-inch MacBook Pro using the M2. The M2 is made with TSMC's "Enhanced 5-nanometer technology" N5P process and contains 20 billion transistors, a 25% increase from the M1. Apple claims CPU improvements up to 18% and GPU improvements up to 35% compared to the M1.[4]

The M2 was followed by the professional-focused M2 Pro and M2 Max chips in January 2023. The M2 Max is a higher-powered version of the M2 Pro, with more GPU cores and memory bandwidth, and a larger die size.[5] In June 2023, Apple introduced the M2 Ultra, a desktop workstation chip containing two M2 Max units.[6] Its successor, Apple M3, was announced on October 30, 2023.

Design

[edit]

CPU

[edit]

The M2 has four high-performance @3.49 GHz "Avalanche" and four energy-efficient @2.42 GHz "Blizzard" cores, first seen in the A15 Bionic, providing a hybrid configuration similar to ARM DynamIQ, as well as Intel's Alder Lake and Raptor Lake processors. The high-performance cores have 192 KB of L1 instruction cache and 128 KB of L1 data cache and share a 16 MB L2 cache;[7] the energy-efficient cores have a 128 KB L1 instruction cache, 64 KB L1 data cache, and a shared 4 MB L2 cache. It also has an 8 MB system level cache shared by the GPU.

The M2 Pro has 8 performance cores and 4 efficiency cores in the unbinned model, or 6 performance cores and 4 efficiency cores in the binned model. The M2 Max has 8 performance cores and 4 efficiency cores in both the binned and unbinned SKUs, and operates at a slightly higher 3.7GHz clock speed in some models.[8]

GPU

[edit]

The M2 integrates an Apple designed ten-core (eight in some base models, nine in the M2 iPad Air) graphics processing unit (GPU). Each GPU core is split into 16 execution units, which each contain eight arithmetic logic units (ALUs). In total, the M2 GPU contains up to 160 execution units or 1280 ALUs, which have a maximum floating point (FP32) performance of 3.6 TFLOPs.

The M2 Pro integrates a 19-core (16 in some base models) GPU, while the M2 Max integrates a 38-core (30 in some base models) GPU. In total, the M2 Max GPU contains up to 608 execution units or 4864 ALUs, which have a maximum floating point (FP32) performance of 13.6 TFLOPS.

The M2 Ultra features a 60- or 76-core GPU with up to 9728 ALUs and 27.2 TFLOPS of FP32 performance.

Memory

[edit]

The M2 uses 6,400 MT/s LPDDR5 SDRAM in a unified memory configuration shared by all the components of the processor. The SoC and RAM chips are mounted together in a system-in-a-package design. 8 GB, 16 GB and 24 GB configurations are available. It has a 128-bit memory bus with 100 GB/s bandwidth, and the M2 Pro, M2 Max, and M2 Ultra have approximately 200 GB/s, 400 GB/s, and 800 GB/s respectively.[9]

Other features

[edit]

The M2 contains dedicated neural network hardware in a 16-core Neural Engine capable of executing 15.8 trillion operations per second. Other components include an image signal processor, a NVM Express storage controller, a Secure Enclave, and a USB4 controller that includes Thunderbolt 3 (Thunderbolt 4 on Mac mini) support. The M2 Pro, Max and Ultra support Thunderbolt 4.

Supported codecs on the M2 include 8K H.264, 8K H.265 (8/10bit, up to 4:4:4), 8K Apple ProRes, VP9, and JPEG.

Products that use the Apple M2 series

[edit]

M2

[edit]

M2 Pro

[edit]

M2 Max

[edit]

M2 Ultra

[edit]

Variants

[edit]

The table below shows the various SoCs based on the "Avalanche" and "Blizzard" microarchitectures.[10][11]

Variant CPU cores GPU Neural Engine (NPU) LPDDR5-6400 memory Transistor
count
P[a] E[b] Cores[c] EU ALU Cores Performance Size (GB)[d] Bandwidth
A15 Bionic 2 3 5 80 640 16 15.8 TOPS 4 34.1 GB/s 15 billion
4 4 64 512
5 80 640 6
M2 4 8 128 1024 8–24 102.4 GB/s 20 billion
9 144 1152
10 160 1280
M2 Pro 6 16 256 2048 16–32 204.8 GB/s 40 billion
8
19 304 2432
M2 Max 30 480 3840 32–96 409.6 GB/s 67 billion
38 608 4864
M2 Ultra 16 8 60 960 7680 32 31.6 TOPS 64–192 819.2 GB/s 134 billion
76 1216 9728
  1. ^ Performance Cores
  2. ^ Efficiency cores
  3. ^ Each GPU core has 16 execution units (EUs) and 128 arithmetic logic units (ALUs)
  4. ^ Each LPDDR5-6400 memory controller contains a 16-bit memory channel and can access up to 4GiB of memory.[11]

See also

[edit]

References

[edit]
  1. ^ "CLOCK RATE SECRETS: SHAPING THE FUTURE OF COMPUTING". 99Encrypt. November 12, 2024. Retrieved November 25, 2024.
  2. ^ a b "Apple Vision Pro is Apple's new $3,499 AR headset". The Verge. June 5, 2023. Retrieved June 5, 2023.
  3. ^ "llvm-project/llvm/unittests/TargetParser/TargetParserTest.cpp at main · llvm/llvm-project · GitHub". GitHub. September 10, 2024. Retrieved September 10, 2024.
  4. ^ "Apple unveils M2, taking the breakthrough performance and capabilities of M1 even further" (Press release). Apple. June 6, 2022. Archived from the original on June 10, 2022. Retrieved June 11, 2022.
  5. ^ "Apple unveils MacBook Pro featuring M2 Pro and M2 Max". Apple Newsroom (Press release). Archived from the original on January 17, 2023. Retrieved January 17, 2023.
  6. ^ "Apple introduces M2 Ultra". Apple. June 5, 2023. Retrieved June 5, 2023.
  7. ^ "Apple Announces M2 SoC: Apple Silicon for Macs Updated for 2022". AnandTech. June 6, 2022. Archived from the original on November 10, 2022. Retrieved November 9, 2022.
  8. ^ Hinum, Klaus. "Apple M2 Max Processor - Benchmarks and Specs". Notebookcheck. Retrieved January 22, 2024.
  9. ^ a b c d "Apple unveils new Mac Studio and brings Apple silicon to Mac Pro". Apple. June 5, 2023. Retrieved June 5, 2023.
  10. ^ "Apple M2 Chip: Everything You Need to Know". MacRumors. Retrieved July 30, 2022.
  11. ^ a b Andrew Cunningham (October 31, 2023). "Apple introduces new M3 chip lineup, starting with the M3, M3 Pro, and M3 Max". Ars Technica.
Retrieved from "https://wiki.riteme.site/w/index.php?title=Apple_M2&oldid=1260763182"