Last year, Arm introduced Lumex Compute Subsystem (CSS) – a turnkey solution for chipset designs. Today, the institution is unveiling CSS for Mobile 2, an AI-native compute level for smartphones.
It is built astir the Arm Mali G2-Ultra NX GPU, which has built-in AI acceleration hardware and an Arm C2 CPU clump including Ultra and Pro cores with SME2 (Scalable Matrix Extension) for agentic AI tasks.

The Arm Mali G2-Ultra NX is the archetypal Mali GPU with dedicated AI acceleration. This enables 4x higher show per watt for neural graphics – that is graphics that are enhanced, reconstructed oregon adjacent afloat generated by Arm Neural Technology.
The Arm C2-Ultra CPU cores are the company’s fastest cores – they tin present 15% higher single-thread show than the C1-Ultra oregon 38% powerfulness savings astatine the aforesaid show level. Meanwhile the C2-Pro cores absorption connected efficiency. Two SME2 units alteration low-latency AI compute connected the CPU itself – they bring doubly the compute powerfulness of the C1 procreation design, which results successful a 70% speedup connected Small Language Models.

SME2 has been adopted by Android and iOS devices, with enactment done by Alipay, Google AI Edge Gallery, Oppo and vivo.




























English (US) ·