Google Tensor
Qualcomm Snapdragon 870
Select video card 1
Select video card 2

Google Tensor vs Qualcomm Snapdragon 870. Specifications, performance, tests

User rating
star star star star star
Released
Q4/2021
Google Tensor
Google Tensor
Released
Q2/2021
User rating
star star star star star
Qualcomm Snapdragon 870
Qualcomm Snapdragon 870

What's the best choice Google Tensor or Qualcomm Snapdragon 870? Which processor is faster?

We have prepared a comparison to help you choose the best processor. Compare their specifications and benchmarks.

Google Tensor has a base frequency of 2.80 GHz. 8 / 8 CPU Cores / Threads. Stated TDP / base power 10 W. Released in Q4/2021.

Qualcomm Snapdragon 870 has a base frequency of 1.80 GHz. 8 CPU Cores / Threads. Stated TDP / base power 10 W. Released in Q2/2021.

Differences

Google Tensor Reasons to consider
Google Tensor
Report a bug
  • Higher clock speed

    Around 56% better clock speed

    2.80 GHz left arrow 1.80 GHz

Positions in all rankings

Common positions Google Tensor CPU in popular benchmarks, for comparison with other models.

  • Geekbench 5, 64bit (Single-Core)
    385 place
  • Geekbench 5, 64bit (Multi-Core)
    620 place
  • iGPU - FP32 Performance (Single-precision GFLOPS)
    104 place

Positions in all rankings

Common positions Qualcomm Snapdragon 870 CPU in popular benchmarks, for comparison with other models.

  • Geekbench 5, 64bit (Single-Core)
    397 place
  • Geekbench 5, 64bit (Multi-Core)
    503 place
  • iGPU - FP32 Performance (Single-precision GFLOPS)
    203 place
  • AnTuTu 8 benchmark
    7 place

Specifications

Technical data
Google Tensor Google Tensor
Qualcomm Snapdragon 870 Qualcomm Snapdragon 870
CPU family and group

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

  • CPU group
    Google Tensor left arrow Qualcomm Snapdragon 865/870
  • Family
    Google Tensor left arrow Qualcomm Snapdragon
  • Generation
    1 left arrow 7
  • Segment
    Mobile left arrow Mobile
CPU Technical specs

Core counts, threads, cache and clock modes describe the CPU configuration. Performance depends on the workload and comparable measured results.

  • A-Core
    2x Cortex-X1 left arrow 1x Kryo 585 Prime
  • B-Core
    2x Cortex-A76 left arrow 3x Kryo 585 Gold
  • Base Frequency
    2.8 GHz left arrow 1.8 GHz
  • C-Core
    4x Cortex-A55 left arrow 4x Kryo 585 Silver
  • Core architecture
    hybrid (Prime / big.LITTLE) left arrow hybrid (Prime / big.LITTLE)
  • CPU Cores
    8 left arrow 8
  • CPU Threads
    8 left arrow 8
  • Hyperthreading / SMT
    No left arrow No
  • Overclocking
    No left arrow No
  • Turbo Frequency (1 Core)
    No turbo left arrow 3.2 GHz
  • Turbo Frequency (8 Cores)
    No turbo left arrow 2.42 GHz
IGPU

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

  • DirectX Version
    12 left arrow 12.0
  • Execution units
    20 left arrow 2
  • Generation
    Vallhall 2 left arrow 6
  • GPU Frequency
    760 MHz left arrow 250 MHz
  • GPU name
    ARM Mali-G78 MP20 left arrow Qualcomm Adreno 650
  • GPU Turbo
    No turbo left arrow 670 MHz
  • Max. displays
    1 left arrow 1
  • Release date
    Q4/2021 left arrow Q4/2019
  • Shader
    320 left arrow 512
  • Technology
    5 nm left arrow 7 nm
Hardware codec support

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

  • AV1
    Decode left arrow No
  • H.264 / AVC
    Decode / Encode left arrow Conflicting source values: Decode | Decode / Encode
  • h265 / HEVC (8 bit)
    Decode / Encode left arrow Decode / Encode
  • h265 / HEVC (10 bit)
    Decode / Encode left arrow Decode / Encode
  • JPEG
    Decode / Encode left arrow Decode / Encode
  • VC-1
    Decode / Encode left arrow Decode
  • VP8
    Decode / Encode left arrow Decode / Encode
  • VP9
    Decode / Encode left arrow Decode / Encode
Memory specs & PCI

Types, channel quantity of RAM supported by Qualcomm Snapdragon 870 and Google Tensor. Depending on the motherboards, higher or lower memory frequencies may be supported.

  • ECC
    No left arrow No
  • Max. Memory
    12 GB left arrow 16 GB
  • Memory channels
    2 left arrow 4
  • Memory type
    LPDDR5-5500 left arrow LPDDR4X-4266LPDDR5-5500
Encryption
  • AES-NI
    No left arrow No
Thermal Management

Compare the TDP requirements of TDP Google Tensor and Qualcomm Snapdragon 870 Power specifications describe different manufacturer limits. TDP, base power and maximum turbo power are separate values; they do not establish measured system consumption.

  • TDP (PL1, legacy label)
    10 W left arrow 10 W
Technologies and extensions

Architecture, interfaces, additional instructions supported by Google Tensor and Qualcomm Snapdragon 870, virtual machine technologies and process technology.

  • Architecture
    - left arrow Kryo 585
  • Instruction set (ISA)
    ARMv8-A64 (64 bit) left arrow ARMv8-A64 (64 bit)
  • L2-Cache
    8 MB left arrow 2 MB
  • L3-Cache
    - left arrow 3 MB
  • Part Number
    - left arrow SM8250-AC
  • Release date
    Q4/2021 left arrow Q2/2021
  • Technology
    5 nm left arrow 7 nm
  • Virtualization
    None left arrow None

Benchmarks

Performance tests CPUs

Based on the results of several benchmarks, you can more accurately estimate the difference in performance between Google Tensor and Qualcomm Snapdragon 870.

Compare the synthetic test values and choose the best processor!

These are saved results from the earlier catalog. Measurement dates and test configurations were not recorded. Models with no comparable results are omitted.

Recent models: test results with identified primary sources — Cinebench R23 · Cinebench R20 · Cinebench R15 · Cinebench 2026 · RandomX benchmark

Geekbench 5, 64bit (Single-Core)
Geekbench 5 SC is a popular cross-platform performance test for desktop or mobile processors that uses system memory intensively

Higher values are better in this metric.

1038.000000
Google Tensor
1029.000000
Qualcomm Snapdragon 870
Geekbench 5, 64bit (Multi-Core)
Geekbench 5 MC is a popular cross-platform performance test for desktop or mobile processors that uses system memory intensively

Higher values are better in this metric.

2810.000000
Google Tensor
3488.000000
Qualcomm Snapdragon 870
iGPU - FP32 Performance (Single-precision GFLOPS)
The performance of the iGPU - the internal GPU in games

Higher values are better in this metric.

1943.000000
Google Tensor
1418.000000
Qualcomm Snapdragon 870

Latest comparisons