HiSilicon Kirin 810 vs HiSilicon Kirin 950

The HiSilicon Kirin 810 and HiSilicon Kirin 950 are both powerful processors designed by HiSilicon Technologies, a subsidiary of Huawei. While they are both capable processors, they have some notable differences in their specifications.

Starting with the HiSilicon Kirin 810, it features an architecture consisting of 2x 2.27 GHz Cortex-A76 cores and 6x 1.88 GHz Cortex-A55 cores. With a total of 8 cores, it offers a versatile and efficient performance. It operates on the ARMv8.2-A instruction set and has a lithography of 7 nm, which means it is manufactured using a highly advanced and energy-efficient process. In terms of the number of transistors, it boasts 6900 million, showcasing its ability to handle complex tasks. Additionally, it has a thermal design power (TDP) of 5 Watt, making it energy-efficient. It also includes Ascend D100 Lite for neural processing, utilizing HUAWEI Da Vinci Architecture.

On the other hand, the HiSilicon Kirin 950 operates on an architecture comprising 4x 2.4 GHz Cortex-A72 cores and 4x 1.8 GHz Cortex-A53 cores. Similar to the Kirin 810, it also has a total of 8 cores. However, it employs the ARMv8-A instruction set and has a lithography of 16 nm, indicating it is manufactured on a slightly older and less energy-efficient process. It possesses 2000 million transistors, which is notably lower than the Kirin 810. This suggests that it may not handle more demanding tasks as efficiently as its counterpart. Like the Kirin 810, it also has a TDP of 5 Watts.

In summary, the HiSilicon Kirin 810 and HiSilicon Kirin 950 differ in terms of their CPU architecture, instruction set, lithography, number of transistors, and neural processing capabilities. The Kirin 810 is built on a more advanced 7 nm process and includes Ascend D100 Lite with HUAWEI Da Vinci Architecture, while the Kirin 950 operates on a 16 nm process and lacks dedicated neural processing hardware. These differences may impact their performance, energy efficiency, and ability to handle complex tasks.