Arm unveils next-generation autonomous systems IP
Arm has unveiled a suite of devices aimed at autonomous systems in automotive and industrial applications.
Chet Babla, Vice President, Automotive and IoT Business at Arm describes them as “a step change in compute for autonomous systems in automotive and and industrial automation, which Arm believes will be an $8 billion silicon opportunity by 2030.”
Designed with safety first, Arm Cortex-A78AE is Arm’s highest performance CPU with safety, Arm Mali-G78AE is Arm’s first safety capable GPU, and Arm Mali-C71AE enables
safety for vision use cases
The new IP enables solutions for autonomous applications, supported by the Arm ecosystem, software and tools, Safety Ready technology, System IP and Physical IP
The Arm Cortex-A78AE CPU will run different, complex workloads for autonomous applications such as mobile robotics and driverless transportation.
• A 30% performance uplift compared to its predecessor.
• Supports features to achieve the relevant automotive and industrial functional safety standards, ISO 26262 and IEC 61508 for applications up to ASIL D / SIL 3.
• New enhanced Split Lock functionality (Hybrid Mode) to offer maximum flexibility.
Hybrid Mode is designed to specifically enable applications that target lower levels of ASIL requirements without compromising performance and allow the deployment of the
same SoC compute architecture into different domain controllers.
Arm says that the Mali is the number one shipping GPU worldwide, and the new Mali-G78AE is Arm’s first GPU to be designed for safety, delivering rich user experiences and heterogenous compute to safety-critical autonomous applications.
The Mali-G78AE enables:
• A new approach to autonomous GPU workloads with Flexible Partitioning, with up to four fully independent partitions for workload separation for safety use cases.
• GPU resources can now be utilised for safety-enabled human machine interfaces or for the heterogeneous compute needed in autonomous systems. For example, an infotainment system,
an instrument cluster with ASIL B requirements and a driver monitoring system can now all run concurrently and independently with hardware separation within an automotive application.
Arm describes the Mali-C71AE as an evolution in ISP safety
Autonomous workloads need to be aware of their surroundings, often through cameras that must operate in a wide range of lighting conditions.
To support a broad range of vision applications across automotive and industrial, the Mali-C71AE offers:
• The flexibility needed to support both human and machine vision applications such as production line monitoring and ADAS camera systems.
• Enhanced safety features, supports features to achieve ASIL B / SIL2 safety capability.
• Support for four real time cameras, or 16 buffered cameras, delivering a 1.2 giga pixel per second throughput.
As autonomous systems move towards more software-defined functionality, Arm is working to accelerate the development of software that will fully realise the benefits of these new
technologies through initiatives such as Project Cassini, aimed at laying the foundation for the adoption of cloud native software paradigms across the entirety of edge computing.
Arm is also working with multiple open source communities and specialist software vendors to widely enable the autonomous software ecosystem, adopting innovations from the established cloud native ecosystem, and collaboratively driving new development to support the features required for autonomous workloads.