HiSilicon Kirin 960s vs MediaTek MT8163 V/B 1.3 GHz vs HiSilicon Kirin 970

HiSilicon Kirin 960s

The HiSilicon Kirin 960S is an ARM based mid-range octa-core SoC for smartphones and tablets, which was introduced with the 2018 10.5-inch Huawei MediaPad M5. Compared to the normal Kirin 960, the 960S offers an additional NPU for AI calculations from the Kirin 970. Looks like to be slower clocked than the older Kirin 960.

Besides 8 CPU cores (4x Cortex-A73, 4x Cortex-A53), the SoC is also equipped with a modern Mali-G71 MP8 graphics adapter, a dual-channel LPDDR4 memory controller as well as an LTE Cat. 12/13 modem. It is one of the fastest ARM SoCs in the end of 2016. The Kirin 960 is manufactured in a modern 16-nm process at TSMC.

MediaTek MT8163 V/B 1.3 GHz

The MediaTek MT8163 V/B is an ARM based entry-level to mid-range SoC for (Android based) tablets. It offers four ARM Cortex-A53 processor cores (quad-core) that are clocked with up to 1.3 GHz. Furthermore, an ARM Mali-T720 MP2 graphics card clocked at 520 MHz, a DDR3x32 1600Mbps memory controller, Bluetooth 4.0, 802.11 b/g/n, GPS and FM are integrated in the SoC.

The similar named MediaTek MT8163 V/A is the faster version, with a CPU clock o up to 1.5 GHz and GPU of up to 600 MHz.

The performance is situated in the entry level of 2015 and often similar to the Kirin 910T (see benchmark below).

HiSilicon Kirin 970

The HiSilicon Kirin 970 is an ARM based high-end octa-core SoC for smartphones and tablet, which was introduced with the Huawei Mate 10 in late 2017. Besides 8 CPU cores (4x Cortex-A73, 4x Cortex-A53), the SoC is also equipped with a modern Mali-G72 MP12 graphics adapter, a dual-channel LPDDR4 memory controller as well as an LTE (4x4 MIMO, 5-band-carrier-aggregation, QAM-256, up to 1.2 Gbit/s) modem.

The performance cluster is clocked at up to 2.4 GHz and the four A53 power saving cores with up to 1.8 GHz. The performance should improve by about 20 percent according to Huawei and the power consumption reduced by 20 percent.

On the chip HiSilicon also included a dedicated Neural Processing Unit (NPU) for running machine learning tasks very efficiently compared to the CPU cores.