“Bringing innovation to drivers faster is one of the toughest challenges automakers face today. Traditional silicon development times often delay vehicle rollouts, preventing carmakers from delivering the AI-powered features that today’s drivers expect,” said Dipta Vachani, SVP and GM of the Automotive Line of Business, Arm.
The Zena Compute Subsystem (CSS) will enable automakers to launch new vehicle models at least one year faster, while scaling AI capabilities across vehicle lines, and helping automakers to stay competitive in the rapidly evolving era of the AI-defined vehicle.
Arm technology can be found in almost all the leading automotive OEMs and is the foundational compute platform that powers everything from safety-critical ADAS to immersive in-cabin experiences. The next generation of vehicles will require pervasive and personalised intelligence that adapts and updates in real time across the vehicle.
“Automakers will need scalable compute, without compromising safety, power efficiency, or flexibility,” said Vachani, “Zena CSS reduces chip development time by up to 12 months and cuts silicon engineering effort by up to 20% per project, helping OEMs and silicon providers bring new vehicle models to market sooner with intelligent voice and touch interfaces, immersive digital cockpit experiences, driver assistance and automation, and real-time awareness.”
The next-generation of vehicles will need to be able to run diverse workloads including advanced driver assistance systems (ADAS), in-vehicle infotainment (IVI) and vehicle control systems with varying safety requirements and real-time constraints on a single platform.
“The transition to software-defined vehicles demands a shift in how we approach compute architectures. Standardised, pre-verified compute subsystems like Arm Zena CSS can significantly accelerate development timelines and reduce complexity across the industry,” said Magnus Östberg, Chief Software Officer, Mercedes-Benz.
Built on Armv9 Automotive Enhanced (AE) technology, Zena CSS is Arm’s first pre-integrated and pre-validated platform for AI-defined vehicles, and provides:
- 16 Armv9-based Cortex-A720AE cores, performance optimised for ADAS and IVI applications
- Cortex-R82AE powered Safety Island which is unique to Zena CSS and used for real-time ASIL D processing capabilities such as fault management, safety monitoring, system control and SoC boot
- Runtime Security Engine with safety-capable Hardware Root of Trust (RoT), leveraging Arm TrustZone technology to manage SoC-level security
- CPU coherency and chip-to-chip connectivity provided by CMN S3AE
- Optional Image Signal Processing powered by Mali-C720AE and Mali GPU for ADAS use-cases including surround view and driver-monitoring
- Support for easy integration of accelerators and partner-specific logic to meet evolving workload demands for advanced, AI-capable SoC design
This compute platform gives OEMs and silicon providers the ability to reuse architectures and software, accelerating global vehicle delivery, and simplifying system development and integration – all while streamlining functional safety and security certification.
“This is critical because developing custom hardware and software stacks for every vehicle model and application is costly and burdensome to validate and certify,” explained Vachani. “Importantly, Zena CSS allows our partners to innovate and differentiate on top of a standard platform in areas that add distinct value to their product lines.”
Several leading OEMs – including top EV manufacturers – and major silicon providers have already licensed Zena CSS or are in advanced stages of engagement.
In addition to reducing time-to-market for silicon, Arm’s partners can begin software development on Zena CSS immediately using cloud-based virtual platform support from AWS, Cadence, Siemens and Synopsys, accelerating time-to-market for software innovation by up to two years.
Zena CSS is built on open standards including AUTOSAR, COVESA, eSync, and Virtio, and is backed by SOAFEE, with 150+ members such as General Motors, CARIAD, Continental, and Tata Motors.