HiSilicon Kirin 620 | Google Tensor G2 | |
CPU comparisonHiSilicon Kirin 620 or Google Tensor G2 - which processor is faster? In this comparison we look at the differences and analyze which of these two CPUs is better. We compare the technical data and benchmark results.
The HiSilicon Kirin 620 has 4 cores with 4 threads and clocks with a maximum frequency of 1.20 GHz. Up to GB of memory is supported in 1 memory channels. The HiSilicon Kirin 620 was released in Q1/2015. The Google Tensor G2 has 8 cores with 8 threads and clocks with a maximum frequency of 2.85 GHz. The CPU supports up to 12 GB of memory in 2 memory channels. The Google Tensor G2 was released in Q4/2022. |
||
HiSilicon Kirin (29) | Family | Google Tensor (3) |
HiSilicon Kirin 620 (1) | CPU group | Google Tensor G2 (1) |
3 | Generation | 2 |
Cortex-A53 | Architecture | G2 |
Mobile | Segment | Mobile |
-- | Predecessor | Google Tensor |
-- | Successor | -- |
|
||
CPU Cores and Base FrequencyThe HiSilicon Kirin 620 has 4 CPU cores and can calculate 4 threads in parallel. The clock frequency of the HiSilicon Kirin 620 is 1.20 GHz while the Google Tensor G2 has 8 CPU cores and 8 threads can calculate simultaneously. The clock frequency of the Google Tensor G2 is at 2.85 GHz. |
||
HiSilicon Kirin 620 | Characteristic | Google Tensor G2 |
4 | Cores | 8 |
4 | Threads | 8 |
normal | Core architecture | hybrid (Prime / big.LITTLE) |
No | Hyperthreading | No |
No | Overclocking ? | No |
1.20 GHz 4x Cortex-A53 |
A-Core | 2.85 GHz 2x Cortex-X1 |
-- | B-Core | 2.35 GHz 2x Cortex-A78 |
-- | C-Core | 1.80 GHz 4x Cortex-A55 |
NPU AI performanceThe performance values of the processor's AI unit. The isolated NPU performance is specified here, the total AI performance (NPU+CPU+iGPU) can be higher. Processors with support for artificial intelligence (AI) and machine learning (ML) can process many calculations, especially audio, image and video processing, much faster than classic processors. |
||
HiSilicon Kirin 620 | Characteristic | Google Tensor G2 |
-- | AI hardware | Google Tensor AI |
-- | AI specifications | Google Edge TPU @ 4 TOPS |
-- | NPU + CPU + iGPU | -- |
Integrated graphics (iGPU)The HiSilicon Kirin 620 or Google Tensor G2 has integrated graphics, called iGPU for short. The iGPU uses the system's main memory as graphics memory and sits on the processor's die. |
||
ARM Mali-450 MP4 | GPU | ARM Mali-G710 MP7 |
0.53 GHz | GPU frequency | 0.90 GHz |
0.53 GHz | GPU (Turbo) | -- |
Utgard | GPU Generation | Vallhall 3 |
28nm | Technology | 4 nm |
1 | Max. displays | 1 |
4 | Compute units | 7 |
64 | Shader | -- |
No | Hardware Raytracing | No |
No | Frame Generation | No |
-- | Max. GPU Memory | -- |
0 | 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-450 MP4 | GPU | ARM Mali-G710 MP7 |
No | Codec h265 / HEVC (8 bit) | Decode / Encode |
No | Codec h265 / HEVC (10 bit) | Decode / Encode |
No | Codec h264 | Decode / Encode |
No | Codec VP9 | Decode / Encode |
No | Codec VP8 | Decode / Encode |
No | Codec AV1 | Decode |
No | Codec AVC | Decode / Encode |
No | Codec VC-1 | Decode / Encode |
No | Codec JPEG | Decode / Encode |
Memory & PCIeThe HiSilicon Kirin 620 can use up to GB of memory in 1 memory channels. The maximum memory bandwidth is --. The Google Tensor G2 supports up to 12 GB of memory in 2 memory channels and achieves a memory bandwidth of up to 53.0 GB/s. |
||
HiSilicon Kirin 620 | Characteristic | Google Tensor G2 |
LPDDR3 | Memory | LPDDR5-5500 |
Max. Memory | 12 GB | |
1 (Single Channel) | Memory channels | 2 (Dual Channel) |
-- | Max. Bandwidth | 53.0 GB/s |
No | ECC | No |
-- | L2 Cache | 8.00 MB |
-- | L3 Cache | 4.00 MB |
-- | PCIe version | -- |
-- | PCIe lanes | -- |
-- | PCIe Bandwidth | -- |
Thermal ManagementThe thermal design power (TDP for short) of the HiSilicon Kirin 620 is --, while the Google Tensor G2 has a TDP of 10 W. The TDP specifies the necessary cooling solution that is required to cool the processor sufficiently. |
||
HiSilicon Kirin 620 | Characteristic | Google Tensor G2 |
-- | TDP (PL1 / PBP) | 10 W |
-- | TDP (PL2) | -- |
-- | TDP up | -- |
-- | TDP down | -- |
-- | Tjunction max. | -- |
Technical detailsThe HiSilicon Kirin 620 is manufactured in 28 nm and has 0.00 MB cache. The Google Tensor G2 is manufactured in 4 nm and has a 12.00 MB cache. |
||
HiSilicon Kirin 620 | Characteristic | Google Tensor G2 |
28 nm | Technology | 4 nm |
Chiplet | Chip design | Chiplet |
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 |
Q1/2015 | Release date | Q4/2022 |
-- | Release price | -- |
show more data | show more data | |
HiSilicon Kirin 620
4C 4T @ 1.20 GHz |
|||
Google Tensor G2
8C 8T @ 2.85 GHz |
HiSilicon Kirin 620
4C 4T @ 1.20 GHz |
|||
Google Tensor G2
8C 8T @ 2.85 GHz |
HiSilicon Kirin 620
ARM Mali-450 MP4 @ 0.53 GHz |
|||
Google Tensor G2
ARM Mali-G710 MP7 @ 0.90 GHz |
HiSilicon Kirin 620
4C 4T @ 1.20 GHz |
|||
Google Tensor G2
8C 8T @ 2.85 GHz |
HiSilicon Kirin 620
4C 4T @ 1.20 GHz |
|||
Google Tensor G2
8C 8T @ 2.85 GHz |
HiSilicon Kirin 620
4C 4T @ 1.20 GHz |
|||
Google Tensor G2
8C 8T @ 2.85 GHz |
HiSilicon Kirin 620
4C 4T @ 1.20 GHz |
|||
Google Tensor G2
8C 8T @ 2.85 GHz |
Devices using this processor |
|
HiSilicon Kirin 620 | Google Tensor G2 |
Unknown | Google Pixel 7 Google Pixel 7 Pro |