Arm breaks out new IP for autonomous vehicles and machines

Arm prioritized safety in its new processor designs that will be used in future driverless vehicles and industrial machines, including factory robots. (Arm)

Arm announced new silicon designs Tuesday for autonomous and safe decision making in the auto and industrial sectors.

The new IP includes a Cortex CPU, a Mali GPU and a new Mali image signal processor with multi-camera support and safety enablement. Chip makers like Nvidia and Intel as well as manufacturers of cars and industrial gear will be able to adapt the chip designs for their specific needs.

Chet Babla, vice president of automotive and IoT at Arm, said the new technology prioritizes safety but also provides power efficiencies and performance boosts.

Free Daily Newsletter

Interesting read? Subscribe to FierceElectronics!

The electronics industry remains in flux as constant innovation fuels market trends. FierceElectronics subscribers rely on our suite of newsletters as their must-read source for the latest news, developments and predictions impacting their world. Sign up today to get electronics news and updates delivered to your inbox and read on the go.

The new Arm Cortex-A78AE CPU offers a 30% performance boost over its predecessor and is designed to help companies meet several critical auto and industrial safety standards.  A new hybrid mode allows a split lock function where processors run in pairs and lower-level safety requirements can be met without a compromise to performance while the system-on-chip compute architecture also can be deployed to different domain controllers.

Arm’s new Mali-G78AE GPU provides flexible partitioning for up to four independent partitions for separate safety workloads. For example, an infotainment system in a vehicle as well as an instrument cluster with safety requirements and a driver monitoring system can now all run at the same time and independently with hardware separation.

Finally, the new Mali-C71AE is an image signal processor with support for ASIL B/SIL 2 safety capability and support for four real-time cameras or 16 buffered cameras that deliver 1.2 giga pixel per second throughput.

In a statement, Nvidia said the new Cortex CPU will deliver the advanced performance and safety for edge AI in the next-generation Nvidia Orin SoC. Almotive, an automated driving tech provider based in Budapest, as well as German robotics supplier KUKA and Volkswagen Group also praised the new Arm IP.  Nvidia has announced plans to buy Arm for $40 billion.

Autonomous systems in auto and industrial automation will grow by 20 times over the next decade, with $8 billion in sales in 2030, Arm predicts.  Arm has partnered with carmakers since 1996 and partners with multiple OEMs in industrial, Babla said in a briefing with reporters.

“Autonomy is the future of mobility,” he said, adding, “there’s no autonomy without safety.” Radar, LiDAR and power controls will all be powered by Arm silicon.

Babla said Arm Cassini software will help companies build applications for the cloud native edge and promised to share more at the Arm Development Summit Oct. 6-8.

RELATED: Arm shares roadmap with Zeus and Perseus chip designs

Suggested Articles

The world’s largest chipmaker saw a 47% decline in data center sales to enterprise and government, even as it forecast a full year 2020 record of $75B

Working with Jacoti of Belgium, Qualcomm wants to make earbuds recognize the hearing anomalies of users.

Deep learning is one of the most promising techniques for training machines to "think" like people.