HiSilicon Kirin 655 | Google Tensor | |
CPU comparisonIn this CPU comparison, we compare the HiSilicon Kirin 655 and the Google Tensor and use benchmarks to check which processor is faster.
We compare the HiSilicon Kirin 655 8 core processor released in Q2/2016 with the Google Tensor which has 8 CPU cores and was introduced in Q4/2021. |
||
HiSilicon Kirin (29) | Family | Google Tensor (3) |
HiSilicon Kirin 650 (4) | CPU group | Google Tensor (1) |
4 | Generation | 1 |
Cortex-A53 / Cortex-A53 | Architecture | G1 |
Mobile | Segment | Mobile |
-- | Predecessor | -- |
-- | Successor | Google Tensor G2 |
|
||
CPU Cores and Base FrequencyThe HiSilicon Kirin 655 is a 8 core processor with a clock frequency of 2.12 GHz. The processor can compute 8 threads at the same time. The Google Tensor clocks with 2.80 GHz, has 8 CPU cores and can calculate 8 threads in parallel. |
||
HiSilicon Kirin 655 | Characteristic | Google Tensor |
8 | Cores | 8 |
8 | Threads | 8 |
hybrid (big.LITTLE) | Core architecture | hybrid (Prime / big.LITTLE) |
No | Hyperthreading | No |
No | Overclocking ? | No |
2.12 GHz 4x Cortex-A53 |
A-Core | 2.80 GHz 2x Cortex-X1 |
1.70 GHz 4x Cortex-A53 |
B-Core | 2.25 GHz 2x Cortex-A76 |
-- | C-Core | 1.80 GHz 4x Cortex-A55 |
Artificial Intelligence and Machine LearningProcessors with the support of artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. Algorithms for ML improve their performance the more data they have collected via software. ML tasks can be processed up to 10,000 times faster than with a classic processor. |
||
HiSilicon Kirin 655 | Characteristic | Google Tensor |
-- | AI hardware | Google Tensor AI |
-- | AI specifications | Google Edge TPU @ 1.6 TOPS |
Internal GraphicsGraphics (iGPU) integrated into the processor not only enable image output without having to rely on a dedicated graphics solution, but can also efficiently accelerate video playback. |
||
ARM Mali-T830 MP2 | GPU | ARM Mali-G78 MP20 |
0.90 GHz | GPU frequency | 0.76 GHz |
-- | GPU (Turbo) | -- |
Midgard 4 | GPU Generation | Vallhall 2 |
28nm | Technology | 5 nm |
2 | Max. displays | 1 |
2 | Compute units | 20 |
32 | Shader | 320 |
No | Hardware Raytracing | No |
No | Frame Generation | No |
-- | Max. GPU Memory | -- |
11 | DirectX Version | 12 |
Hardware codec supportA 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. |
||
ARM Mali-T830 MP2 | GPU | ARM Mali-G78 MP20 |
Decode / Encode | Codec h265 / HEVC (8 bit) | Decode / Encode |
Decode | Codec h265 / HEVC (10 bit) | Decode / Encode |
Decode / Encode | Codec h264 | Decode / Encode |
No | Codec VP9 | Decode / Encode |
Decode / Encode | Codec VP8 | Decode / Encode |
No | Codec AV1 | Decode |
No | Codec AVC | Decode / Encode |
No | Codec VC-1 | Decode / Encode |
Decode / Encode | Codec JPEG | Decode / Encode |
Memory & PCIeUp to GB of memory in a maximum of 2 memory channels is supported by the HiSilicon Kirin 655, while the Google Tensor supports a maximum of 12 GB of memory with a maximum memory bandwidth of 53.0 GB/s enabled. |
||
HiSilicon Kirin 655 | Characteristic | Google Tensor |
LPDDR3-933 | Memory | LPDDR5-5500 |
Max. Memory | 12 GB | |
2 (Dual Channel) | Memory channels | 2 (Dual Channel) |
-- | Max. Bandwidth | 53.0 GB/s |
No | ECC | No |
-- | L2 Cache | 8.00 MB |
-- | L3 Cache | -- |
-- | PCIe version | -- |
-- | PCIe lanes | -- |
-- | PCIe Bandwidth | -- |
Thermal ManagementThe HiSilicon Kirin 655 has a TDP of --. The TDP of the Google Tensor is 10 W. System integrators use the TDP of the processor as a guide when dimensioning the cooling solution. |
||
HiSilicon Kirin 655 | Characteristic | Google Tensor |
-- | TDP (PL1 / PBP) | 10 W |
-- | TDP (PL2) | -- |
-- | TDP up | -- |
-- | TDP down | -- |
-- | Tjunction max. | -- |
Technical detailsThe HiSilicon Kirin 655 has 0.00 MB cache and is manufactured in 16 nm. The cache of Google Tensor is at 8.00 MB. The processor is manufactured in 5 nm. |
||
HiSilicon Kirin 655 | Characteristic | Google Tensor |
16 nm | Technology | 5 nm |
Chiplet | Chip design | Unknown |
Armv8-A (64 bit) | Instruction set (ISA) | Armv8-A (64 bit) |
-- | ISA extensions | -- |
-- | Socket | -- |
None | Virtualization | None |
No | AES-NI | No |
Android | Operating systems | Android |
Q2/2016 | Release date | Q4/2021 |
-- | Release price | -- |
show more data | show more data | |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
HiSilicon Kirin 655
ARM Mali-T830 MP2 @ 0.90 GHz |
|||
Google Tensor
ARM Mali-G78 MP20 @ 0.76 GHz |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
HiSilicon Kirin 655
8C 8T @ 2.12 GHz |
|||
Google Tensor
8C 8T @ 2.80 GHz |
Devices using this processor |
|
HiSilicon Kirin 655 | Google Tensor |
Unknown | Google Pixel 6 Google Pixel 6 Pro |