Urgent.News

What's breaking now, across thousands of outlets.

AI

Arm's new Mali G2-Ultra NX GPU adds neural accelerators for sub-1-watt AI graphics on mobile

Not surprisingly, Arm just announced a series of agentic AI-focused enhancements to its range of IP offerings at its Arm Everywhere China event. The news encompasses mobile devices, physical AI and robotics, and AI infrastructure for the cloud and enterprise environments. Read Entire Article

Arm's new Mali G2-Ultra NX GPU adds neural accelerators for sub-1-watt AI graphics on mobile

Arm has recently unveiled a new Mali G2-Ultra NX GPU designed to perform AI tasks and graphics generation at sub-1 watt power levels on mobile devices. This advancement comes as part of Arm's broader push to incorporate AI accelerators across its entire range of IP offerings, with a focus on making its technologies more accessible to a wide array of computing devices, from edge devices to datacenters.

The new Mali G2-Ultra NX GPU is equipped with neural accelerators, enabling it to process AI-generated graphics in a manner similar to desktop PC graphics cards, but within the power constraints of mobile devices. This development is part of Arm's CSS for Mobile 2 platform, which integrates CPU, GPU, and system technologies into an AI-native compute platform for edge devices.

In addition to the Mali G2-Ultra NX, Arm has also introduced its latest C2-Ultra and C2-Pro CPUs, as well as compute blocks aimed at accelerating its SME2 instruction set extensions. These extensions are specifically designed to handle matrix math commonly used in AI workloads, potentially offering up to 1.7x performance improvements for AI applications and models.

Furthermore, Arm has expanded its presence in the physical AI and robotics domain by introducing the Arm Total Design for Physical AI. This initiative brings together over 80 companies to collaborate on various elements of robotics-based products, ranging from sensors and actuators to operating systems and semiconductor partnerships.

Arm's new Robotics Capability Framework categorizes autonomous robots into six types, based on increasing levels of autonomy, to help standardize the rapidly evolving field of AI-powered robotics.

Written by urgent.news from TechSpot's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at techspot.com →

More in AI

More from Thursday 10 September →