Google Tensor G3 vs Google Tensor G2

Last updated:

CPU comparison with benchmarks

-VS-

CPU lineage

Google Tensor G3 or Google Tensor G3 – which processor offers superior performance? In this comparison, we examine disparities and assess which of these two CPUs outperforms the other. We delve into technical specifications and benchmark outcomes.
The Google Tensor G3 features 8 processor cores and has the capability to manage 8 threads concurrently.
It was released in Q3/2023 and belongs to the 3 generation of the Google Tensor series.
The Google Tensor G2 features 8 processor cores and has the capability to manage 8 threads concurrently.
It was released in Q4/2022 and belongs to the 2 generation of the Google Tensor series.
Mobile Segment Mobile
Google Tensor G3 Name Google Tensor G2
Google Tensor Family Google Tensor
3 Generation 2
Google Tensor G3 Group Google Tensor G2
 
 

CPU Cores and Base Frequency

The Google Tensor G3 has 8 CPU cores and can calculate 8 threads in parallel.
The clock frequency of the A-Core is 3.0 GHz.
The number of CPU cores greatly affects the speed of the processor and is an important performance indicator.
The Google Tensor G2 has 8 CPU cores and can calculate 8 threads in parallel.
The clock frequency of the A-Core is 2.85 GHz.
4x Cortex-A510 Cores C 4x Cortex-A55
2.15 GHz C-Core Frequency 1.8 GHz
2.45 GHz B-Core Frequency 2.35 GHz
3.0 GHz A-Core Frequency 2.85 GHz
4x Cortex-A715 Cores B 2x Cortex-A78
1x Cortex-X3 Cores A 2x Cortex-X1
No Overclocking No
hybrid (Prime / big.LITTLE) Core architecture hybrid (Prime / big.LITTLE)
8 Threads 8
No Hyperthreading No
8 CPU Cores 8
 
 

Internal Graphics

The Google Tensor G3 has integrated graphics, called iGPU for short.
and 10 execution units.
The iGPU uses the system's main memory as graphics memory and sits on the processor's die.
The Google Tensor G2 has integrated graphics, called iGPU for short.
and 7 execution units.
0.89 GHz GPU frequency 0.9 GHz
Q4/2022 Release date Q2/2021
12 Direct X 12
ARM Immortalis-G715 MP10 GPU name ARM Mali-G710 MP7
4 nm Technology 4 nm
-- Max. displays --
-- Shaders --
0 bytes Max. GPU Memory 0 bytes
10 Execution units 7
Vallhall Generation Vallhall 3
-- GPU (Turbo) --
 
 

Artificial Intelligence and Machine Learning

Google Edge TPU AI specifications Google Edge TPU @ 4 TOPS
Google Tensor AI AI hardware Google Tensor AI
 
 

Hardware codec support

A photo or video codec that is accelerated in hardware can greatly accelerate the working speed of a processor and extend the battery life of notebooks or smartphones when playing videos.
Decode / Encode AVC Decode / Encode
Decode / Encode VC-1 Decode / Encode
Decode / Encode VP9 Decode / Encode
Decode / Encode h265 / HEVC (10 bit) Decode / Encode
Decode / Encode h264 Decode / Encode
Decode / Encode VP8 Decode / Encode
Decode / Encode h265 / HEVC (8 bit) Decode / Encode
Decode / Encode JPEG Decode / Encode
Decode / Encode AV1 Decode
 
 

Memory & PCIe

The processor supports a maximum memory capacity of 12.0 GB distributed across 2 memory channels. It offers a peak memory bandwidth of 53.0 GB/s. Both the type and quantity of memory can have a substantial impact on the overall system performance.
2 Memory channels 2
12.0 GB Max. Memory 12.0 GB
pci PCIe pci
No AES-NI No
No ECC No
53.0 GB/s Bandwidth 53.0 GB/s
LPDDR5-5500 Memory type LPDDR5-5500
 
 

Thermal Management

The processor has a thermal design power (TDP) of 10 W watts.
TDP indicates the cooling solution needed to effectively manage the processor's heat. It generally provides an approximate indication of the actual power consumption of the CPU itself.
-- Tjunction max --
10 W TDP (PL1 / PBP) 10 W
 
 

Technical details

The Google Tensor G3 is manufactured using a 3 nm process.
A smaller manufacturing process indicates a more contemporary and energy-efficient CPU.
A substantial cache can significantly enhance the processor's performance, particularly in scenarios like gaming.
The Google Tensor G2 is manufactured using a 4 nm process.
In total, this processor boasts a generous 4.0 MB cache.
Q3/2023 Release date Q4/2022
-- Part Number --
0 bytes L2-Cache 8.0 MB
None Virtualization None
ISA extensions
Chiplet Chip design Chiplet
G3 Architecture G2
3 nm Technology 4 nm
Socket
Android Operating systems Android
-- Release price --
Technical data sheet Documents Technical data sheet
ARMv9-A64 (64 bit) Instruction set (ISA) ARMv8-A64 (64 bit)
0 bytes L3-Cache 4.0 MB