Google Tensor G2 vs Apple A16 Bionic. Specifications, performance, tests

Background information about the processors being compared, series, generation and market segment.

• Family
  Google Tensor Apple A series
• CPU group
  Google Tensor G2 Apple A16
• Segment
  Mobile Mobile
• Generation
  2 16
• Predecessor
  Google Tensor Apple A15 Bionic (5-GPU)

Basic parameters such as number of cores, number of threads, base and turbo frequency, and cache size. These parameters indirectly tell about the speed of the processor, the higher they are the better.

• CPU Cores / Threads
  8 / 8 6 / 6
• Core architecture
  hybrid (Prime / big.LITTLE) hybrid (big.LITTLE)
• A-Core
  2x Cortex-X1 2x Everest
• B-Core
  2x Cortex-A78 4x Sawtooth
• Hyperthreading / SMT
  No No
• Overclocking
  No No
• A-Core Frequency
  2.85 GHz 3.46 GHz
• B-Core Frequency
  2.35 GHz 2.02 GHz

Internal Graphics does not affect the performance of the CPU, performs the work of the graphics card in its absence or on mobile devices.

• GPU name
  ARM Mali-G710 MP7 Apple A16 (5 GPU Cores)
• GPU frequency
  0.90 GHz 0.70 GHz
• GPU (Turbo)
  No turbo No turbo
• Execution units
  7 160
• Shader
  0 1280
• Max. GPU Memory
  -- 8 GB
• Max. displays
  1 3
• Generation
  Vallhall 3 13
• Direct X
  12 --
• Technology
  4 nm 4 nm
• Release date
  Q2/2021 Q3/2022

Built-in codecs used to encode and decode content. Significantly speeds up the required operations.

• h265 / HEVC (8 bit)
  Decode / Encode Decode / Encode
• h265 / HEVC (10 bit)
  Decode / Encode Decode / Encode
• h264
  Decode / Encode Decode / Encode
• VP8
  Decode / Encode Decode / Encode
• VP9
  Decode / Encode Decode / Encode
• AV1
  Decode No
• AVC
  Decode / Encode Decode
• VC-1
  Decode / Encode Decode
• JPEG
  Decode / Encode Decode / Encode

Types, channel quantity of RAM supported by Apple A16 Bionic and Google Tensor G2. Depending on the motherboards, higher or lower memory frequencies may be supported.

• Memory type
  LPDDR5-5500 LPDDR5-6400
• Max. Memory
  12 GB 6 GB
• Memory channels
  2 (Dual Channel) 1 (Single Channel)
• Bandwidth
  53.0 GB/s 51.2 GB/s
• ECC
  No No
• AES-NI
  No No

Compare the TDP requirements of TDP Google Tensor G2 and Apple A16 Bionic to select a cooling system. Note, the TDP value refers to thermal watts, not electrical watts.

• TDP (PL1)
  10 W 8.5 W

Architecture, interfaces, additional instructions supported by Google Tensor G2 and Google Tensor G2, virtual machine technologies and process technology.

• Technology
  4 nm 4 nm
• Chip design
  Chiplet Chiplet
• Socket
  N/A N/A
• L2-Cache
  8.00 MB 20.00 MB
• L3-Cache
  4.00 MB 24.00 MB
• Architecture
  G2 A16
• Operating systems
  Android iOS
• Virtualization
  None None
• Instruction set (ISA)
  ARMv8-A64 (64 bit) ARMv8-A64 (64 bit)
• Release date
  Q4/2022 Q3/2022