Mobileye and STMicroelectronics have collaborated on an automotive vision chip which they declare will act as the “central computer performing sensor fusion for Fully Autonomous Driving (FAD) vehicles starting in 2020.” The chip is optimized for a wide variety of computer-vision, signal-processing, and machine-learning tasks, including deep neural networks.
The sensor-fusion process has to simultaneously grab and process all the sensors’ data. With support of at least 40Gbps data bandwidth, the EyeQ5 is designed to process about 20 sensors simultaneously which is ideal for autonomous driving requiring fusion processing of dozens of sensors, including high-resolution cameras, radars, and LiDARs”, said the companies.
According to the announcement, the 5th gen Mobileye’s SoC, the EyeQ5, will be developed in 10nm or lower FinFET manufacturing process. With 8 multithreaded CPU cores and 18 vision processor cores, the chip is expected to increase performance 8x times over the current 4th generation EyeQ4.
Further, the chip will be capable of handling more than 12 Tera operations per second, while keeping power consumption below 5W, to maintain passive cooling at extraordinary performance..
“EyeQ5 is designed to serve as the central processor for future fully-autonomous driving for both the sheer computing density, which can handle around 20 high-resolution sensors and for increased functional safety,” said Prof. Amnon Shashua, cofounder, CTO and Chairman of Mobileye.
The EyeQ5 provides “super-computer” capabilities within a low-power envelope to enable price-efficient passive cooling, the company said. This is possible with diverse accelerator architectures which enable applications to save both computational time and energy by using the most suitable core for every task.
Further, the EyeQ5 is planned to support highest grade of functional safety targeting ASIL-D applications (autonomous driving). Also, an integrated Hardware Security Module on the chip enables system integrators to support over-the-air software updates, secure in-vehicle communication, etc.
The companies plan to provide the chip to carmakers and Tier1s along with a full suite of hardware accelerated algorithms and applications that are required for autonomous driving. Mobileye says it will also support an automotive-grade standard operating system and provide a complete SDK for the EyeQ5.
Further technical details of the chip include two PCIe Gen4 ports for inter-processor communication, which could allow system expansion with multiple EyeQ5 devices or for connectivity with an application processor. High computational and data bandwidth requirements are supported with four 32-bit LPDDR4 channels, operating at 4267MT/s.
The EyeQ5 is scheduled to sample in H1 2018. Development hardware with the full suite of applications and SDK are expected by the second half of 2018.
For further details, view the full Press release.