Arm, a tech company that designs processors for electronic devices, has unveiled a suite of new automotive technologies aimed at accelerating the development of AI-powered vehicles by up to two years. This package includes next-generation Armv9 processors specifically designed for the demands of autonomous driving, along with the introduction of server-class processing power and virtual prototyping tools to streamline development cycles.
The automotive market is experiencing a significant transformation marked by a growing demand for autonomy, advancing user experiences. This transformation also includes a shift towards electrification, leading to a surge in software and AI integration. Vehicle electronics are undergoing increased complexity. This prompts a need for a fundamental reassessment of product development approaches to meet the pace of change. In a series of industry initiatives, Arm and its ecosystem are introducing the latest Arm Automotive Enhanced (AE) processors and new virtual platforms. These initiatives aim to expedite automotive development cycles by up to two years, with immediate availability to the industry.
Next-generation AE processors bring Armv9 and server-class performance to automotive for the first time
For the first time, Arm is introducing Armv9-based technologies to the automotive sector. This facilitates the industry’s utilization of AI, security, and virtualization capabilities provided by this latest generation of the Arm architecture. Moreover, Arm is utilizing its leadership in the infrastructure market by introducing server-class Neoverse technology to automotive. They are introducing new Armv9-based Cortex-A products for scalability, addressing contemporary vehicles’ increasing performance needs alongside other advancements. Furthermore, the full line-up of products we’re announcing today includes:
- Arm Neoverse V3AE: Bringing Neoverse technology to the automotive sector for the first time, delivering server-class performance for AI-accelerated autonomous and ADAS workloads
- Arm’s first v9-based Cortex-A processors purpose-built for automotive:
- Arm Cortex-A720AE: Delivering industry-leading sustained performance with SoC design flexibility for a broad range of software-defined vehicle (SDV) applications
- Arm Cortex-A520AE: Providing leading power efficiency with functional safety features to scale across automotive use cases
- Arm Cortex-R82AE: The highest-ever performing real-time processor for functional safety which delivers 64-bit computing to real-time processing for the very first time
- Arm Mali-C720AE: A configurable ISP optimized for the most demanding computer and human vision use cases
- A range of configurable system IP to enable the Arm silicon ecosystem to deliver scalable, high-performance automotive SoCs
The road ahead: Arm Compute Subsystems (CSS) for Automotive
They are not stopping there. Looking ahead, it is perceived that systems are only going to become more complex. The increasing demand for safety necessitates consolidating compute components for partners, standardizing crucial aspects to ensure consistency. Arm CSS for Automotive aims to deliver pre-integrated and validated configurations of Arm AE IP optimized for performance, power, and area using a leading-edge foundry process. Moreover, their first CSS for automotive is anticipated to be delivered in 2025.
Virtual prototypes will enable ecosystem to leverage Arm AE IP for software development ahead of silicon
The traditional automotive development cycles follow a linear progression. Initially, processor IP is delivered, followed by the commencement of silicon development. Subsequently, hardware becomes available approximately two years later, enabling software developers to begin their work. However, a new approach aims to alter this conventional process. Industry-leading Arm AE IP enables software developers to begin work prior to physical silicon readiness through virtual prototyping. Partnerships with industry such as Amazon Web Services (AWS), Cadence, Corellium, Siemens, and others are instrumental in delivering these virtual platforms and cloud solutions. This approach fosters earlier and more seamless development across the entire software stack. It collaborates with partners like Autoware Foundation, BlackBerry QNX, Elektrobit, Kernkonzept, LeddarTech, Mapbox, Sensory, Tata Technologies, TIER IV, Vector, and more.
The announcement made today signifies a significant advancement in facilitating the automotive ecosystem. Opening fresh opportunities, it expedites time to market for developers, OEMs, Tier 1 suppliers, silicon partners, and software providers in automotive. Moreover, they are collectively shaping the future of software-defined vehicles on Arm.
