Samsung Exynos 9610 vs HiSilicon Kirin 710A vs HiSilicon Kirin 970

Samsung Exynos 9610

The Samsung Exynos 9610 (or Exynos 7 Series 9610) is a mid-range SoC for Android based smartphones and tablets. It integrates 8 processor cores in two clusters (bigLITTLE concept). Four ARM Cortex A73 cores at up to 2.3 GHz for demanding tasks and four ARM Cortex A53 at up to 1.7 GHz for power efficiency.

The integrated LTE modem supports 4G at up to 600 Mbps download and 150 Mbps upload. Furthermore, 802.11ac WiFi and Bluetooth 5.0 are also integrated in the chip.

The on-board ARM Mali-G72 MP3 graphics card offers three clusters and support for Vulkan, DirectX 12 and OpenGL ES 3.2.

The Exynos 9610 is manufactured in the modern 10nm FinFET process and therefore relatively power efficient and also suited for smaller smartphones.

HiSilicon Kirin 710A

The HiSilicon Kirin 710A is a ARM-based mid-range Octa-Core-SoC for Android based smartphones and tablets. It is based on the Kirin 710, but manufactured in 14nm FinFET at SMIC (China) versus the TSMC in 12nm. It was announced mid 2020 and contains 8 processor cores (4x Cortex-A73 at up to 2 GHz, 4x Cortex-A53 at up to 1.7 GHz, BigLITTLE), an ARM Mali G51 MP4, a dual-channel LPDDR4 memory controller and a LTE radio (600 Mbps down, 150 Mbps up). Therefore, the CPU part is similar to the Kirin 960 and 970 (both higher clocked), but the graphics card is a lot slower. 

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.