| Name: | Google Tensor |
| Family: | Google Tensor |
| Group: | Google Tensor |
| Segment: | Mobile |
| Generation: | 1 |
Google Tensor Benchmark, Test and specs
Last updated:
CPU lineage
The Google Tensor features 8 processor cores and has the capability to manage 8 threads concurrently. It was released in Q4/2021 and belongs to the 1 generation of the Google Tensor series.
CPU Cores and Base Frequency
The Google Tensor has 8 CPU cores and can calculate 8 threads in parallel. The clock frequency of the A-Core is 1.8 GHz. The number of CPU cores greatly affects the speed of the processor and is an important performance indicator.
| CPU Cores: | 8 |
| Threads: | 8 |
| Cores A: | 2x Cortex-X1 |
| Cores B: | 2x Cortex-A76 |
| Cores C: | 4x Cortex-A55 |
| Core architecture: | hybrid (Prime / big.LITTLE) |
| Hyperthreading: | No |
| Overclocking: | No |
| A-Core Frequency: | 1.8 GHz |
| A-Core Frequency Turbo: | 2.8 GHz |
Internal Graphics
The Google Tensor has integrated graphics, called iGPU for short. Specifically, the Google Tensor uses the ARM Mali-G78 MP20, which has 320 texture shaders and 20 execution units. The iGPU uses the system's main memory as graphics memory and sits on the processor's die.
| GPU name: | ARM Mali-G78 MP20 |
| GPU frequency: | 0.76 GHz |
| GPU (Turbo): | -- |
| Execution units: | 20 |
| Shaders: | 320 |
| Max. GPU Memory: | 0 bytes |
| Max. displays: | -- |
| Generation: | Vallhall 2 |
| Direct X: | 12 |
| Technology: | 5 nm |
| Release date: | Q4/2021 |
Artificial Intelligence and Machine Learning
| AI hardware: | Google Tensor AI |
| AI specifications: | Google Edge TPU @ 1.6 TOPS |
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.
| h265 / HEVC (8 bit): | Decode / Encode |
| h265 / HEVC (10 bit): | Decode / Encode |
| h264: | Decode / Encode |
| VP8: | Decode / Encode |
| VP9: | Decode / Encode |
| AV1: | Decode |
| AVC: | Decode / Encode |
| VC-1: | Decode / Encode |
| JPEG: | Decode / Encode |
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.
| Memory type: | LPDDR5-5500 |
| Max. Memory: | 12.0 GB |
| Memory channels: | 2 |
| Bandwidth: | 53.0 GB/s |
| ECC: | No |
| PCIe: | pci |
| AES-NI: | No |
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.
| TDP (PL1 / PBP): | 10 W |
| TDP (PL2): | None |
| TDP up: | None |
| TDP down: | None |
| Tjunction max: | -- |
Technical details
The Google Tensor is manufactured using a 5 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.
| Technology: | 5 nm |
| Chip design: | -- |
| Socket: | |
| L2-Cache: | 8.0 MB |
| L3-Cache: | 0 bytes |
| Architecture: | G1 |
| Operating systems: | Android |
| Virtualization: | None |
| Instruction set (ISA): | ARMv8-A64 (64 bit) |
| ISA extensions: | |
| Release date: | Q4/2021 |
| Release price: | -- |
| Part Number: | -- |
| Documents: | Technical data sheet |
ADS
Benchmarks
AnTuTu 9 Benchmark
|
Samsung Exynos 2100
8C 8T @ 2.9 GHz
|
724660
|
|
Qualcomm Snapdragon 865 Plus
8C 8T @ 3.1 GHz
|
716498
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
691770
|
|
MediaTek Dimensity 1300
8C 8T @ 3.0 GHz
|
689042
|
|
|
MediaTek Dimensity 1200
8C 8T @ 3.0 GHz
|
669042
|
AnTuTu 8 Benchmark
|
|
MediaTek Dimensity 1200
8C 8T @ 3.0 GHz
|
627817
|
|
|
Qualcomm Snapdragon 865 Plus
8C 8T @ 3.1 GHz
|
616032
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
612494
|
|
|
Samsung Exynos 2100
8C 8T @ 2.9 GHz
|
602990
|
|
|
Qualcomm Snapdragon 865
8C 8T @ 2.84 GHz
|
598103
|
Geekbench 3, 64bit (Multi-Core)
|
Intel Core i7-4770T
4C 8T @ 2.5 GHz
|
12713
|
|
|
Intel Core i7-6700T
4C 8T @ 2.8 GHz
|
12707
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
12594
|
|
|
Intel Core i7-4870HQ
4C 8T @ 2.5 GHz
|
12586
|
|
|
Intel Core i7-4712HQ
4C 8T @ 2.3 GHz
|
12568
|
Geekbench 3, 64bit (Single-Core)
|
AMD Ryzen Threadripper 1950X
16C 32T @ 3.4 GHz
|
4616
|
|
|
AMD Ryzen Threadripper 1920X
12C 24T @ 3.5 GHz
|
4616
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
4564
|
|
Intel Core i5-8600K
6C 6T @ 3.6 GHz
|
4561
|
|
Intel Xeon E3-1280 v5
4C 8T @ 3.7 GHz
|
4536
|
Geekbench 6 (Multi-Core)
|
|
Intel Core i5-8250U
4C 8T @ 1.6 GHz
|
3311
|
|
|
Intel Core i5-6500
4C 4T @ 3.2 GHz
|
3305
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
3304
|
|
AMD Ryzen 3 2300X
4C 4T @ 3.5 GHz
|
3279
|
|
|
Intel Core i7-5750HQ
4C 8T @ 2.5 GHz
|
3276
|
Geekbench 5, 64bit (Multi-Core)
|
Intel Core i7-3820QM
4C 8T @ 2.7 GHz
|
2926
|
|
Intel Xeon Bronze 3104
6C 6T @ 1.7 GHz
|
2917
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
2915
|
|
|
Intel Core i5-4690
4C 4T @ 3.5 GHz
|
2913
|
|
|
Intel Core i7-3610QE
4C 8T @ 2.3 GHz
|
2911
|
iGPU - FP32 Performance (Single-precision GFLOPS)
|
AMD Ryzen 7 5700U
8C 16T @ 1.8 GHz
|
1946
|
|
AMD Ryzen 9 5900HS Creator Edition
8C 16T @ 3.3 GHz
|
1946
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
1943
|
|
|
Intel Core i7-1165G7
4C 8T @ 2.8 GHz
|
1933
|
|
|
Intel Core i7-1255UL
10C 12T @ 2.6 GHz
|
1916
|
Geekbench 6 (Single-Core)
|
|
Intel Xeon E3-1245 v5
4C 8T @ 3.5 GHz
|
1414
|
|
Intel Xeon W-3275
28C 56T @ 2.5 GHz
|
1414
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
1414
|
|
|
Intel Xeon W-3275
28C 56T @ 2.5 GHz
|
1414
|
|
|
Intel Xeon E3-1245 v5
4C 8T @ 3.5 GHz
|
1414
|
Geekbench 5, 64bit (Single-Core)
|
AMD EPYC 7302P
16C 32T @ 3.0 GHz
|
1043
|
|
Intel Xeon Gold 6140
18C 36T @ 2.3 GHz
|
1043
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
1043
|
|
|
AMD Ryzen 3 7320U
4C 8T @ 2.4 GHz
|
1043
|
|
|
Intel Xeon Gold 6148
20C 40T @ 2.4 GHz
|
1043
|
Performance for Artificial Intelligence (AI) and Machine Learning (ML)
|
|
MediaTek Dimensity 1000+
8C 8T @ 2.6 GHz
|
4.5
|
|
|
Google Tensor G2
8C 8T @ 2.85 GHz
|
4
|
|
|
Google Tensor
8C 8T @ 1.8 GHz
|
1.6
|
|
Apple A11 Bionic
6C 6T @ 2.39 GHz
|
0.6
|
