Kirin 990 (5G) is based on Balong 5000’s 5G connectivity capability, said to offer a peak downlink rate of 2.3 Gbit/s and an uplink peak rate of 1.25 Gbit/s.Huawei has unveiled its flagship Kirin 990 series of system-on-chip (SoC) with Kirin 990 and its 5G version. Kirin 990 was announced at an event at the ongoing IFA 2019 in Berlin, Germany. Huawei has said that Kirin 990 will power its upcoming Mate 30 series smartphones.
Huawei’s Kirin 990 (5G) is built on a 7 nm+ EUV manufacturing process, comes integrated with a 5G modem so the chip is smaller and power consumption is lower. The full-frequency 5G SoC supports non-standalone (NSA) as well as standalone (SA) architectures. The frequency bands supported are TDD/FDD.
Kirin 990 (5G) is based on Balong 5000’s 5G connectivity capability, said to offer a peak downlink rate of 2.3 Gbit/s and an uplink peak rate of 1.25 Gbit/s. It packs a dual-core (large and tiny) NPU, which is built on the Da Vinci architecture. The large cores are designed to achieve high performance in heavy computing scenarios while maintaining power efficiency. Meanwhile, the tiny core structure will empower ultra-low power consumption applications.
“Kirin 990 (5G) is the world’s first 5G SoC, and it will enable end users to access superb 5G connectivity experience one step ahead in the first year of 5G commercialization.” said Richard Yu, CEO of Huawei Consumer Business Group (CBG) in a press statement.
Also read: IFA 2019: From Nokia phones to Amazon OLED TV, all that has been announced so far
As for specifications, Kirin 990 (5G) is an octa-core processor with frequency up to 2.86 GHz. It uses a 16-core Mali-G76 GPU. The new Smart Cache is said ti effectively save bandwidth and lower power consumption. In terms of gaming features, the SoC ships with an upgraded Kirin Gaming+ 2.0 for an enhanced gaming experience.
In terms of photography, a new ISP 5.0 in Kirin 990 (5G) enables brighter and sharper images in low light environments. There is also dual-domain video NR features, which is claimed to process noise more accurately in videos. More features include real-time video post-processing and AI segmentation-based rendering that can adjust the image color frame by frame.
