TORONTO, Canada – April 16, 2024 – Untether AI, a company developing energy-efficient processors for artificial intelligence, specifically focusing on accelerating AI tasks at the edge and in the cloud, announced a collaboration with Arm, a company that designs processors for various devices, known for being energy-efficient and found in many smartphones and tablets, to develop best-in-class solutions optimized for next-generation automotive applications. As part of this collaboration, Untether AI will enable its inference acceleration technology to be implemented alongside the latest-generation Automotive Enhanced (AE) technology from Arm, to create solutions that address performance, power, safety, and security requirements for advanced Driver Assistance Systems (ADAS) and autonomous vehicle (AV) applications.
Compute workloads radically changed in the past several years with the deployment of AI. The increasing complexity of AI and conventional software algorithms has elevated the demand for heterogeneous computing platforms employing domain-specific architectures. This trend, especially prevalent in the automotive sector, results in an ideal computing platform. Moreover, the technology integrates CPUs, AI accelerators, memory, and networking tech, all tailored for neural network acceleration and software-defined vehicles.
“The increase in advanced user experiences, ADAS, and AV applications means more heterogeneous compute is needed in the vehicle,” said Suraj Gajendra, vice president of products and solutions, Automotive Line of Business, Arm. “By collaborating with Untether AI to ensure our leading-edge AE technology can work well alongside their acceleration capability. Moreover, we are enabling our partners to power cutting edge AI workloads across the vehicle.”
Untether AI’s innovative at-memory architecture for neural network inference delivers high performance. Moreover, it provides the energy efficiency needed to support next-generation SDV technology. High AI compute performance with low latency in a small form factor and low-power envelope have become the cornerstone requirements. These are essential for leading ADAS platforms at L2+ levels and above. The demand for high levels of AI compute performance in a small footprint has further accelerated. Moreover, the automotive industry is embracing software-defined vehicles (SDV), driving a general trend toward an underlying centralized architecture.
Through close collaboration with leading OEMs, automotive suppliers, and membership in the SOAFEE consortium, Untether AI has developed an in-depth understanding of the unique requirements associated with emerging SDV architectures. SOAFEE, an industry-wide consortium, focuses on developing a common SDV platform to enable lower cost and faster time-to-market deployment.
“Untether AI designed its chiplet-based solution expressly for the automotive market. It delivers unsurpassed energy efficiency without compromising performance and meets stringent safety requirements,” said Robert Beachler, vice president of product, Untether AI. “Arm’s AE IP portfolio enables the flexibility, scale, and choice OEMs need. This capability combined with it, allows them to create differentiating next-generation intelligent automotive applications.”
News related to Arm –
