Autonomous driving, say the partners, requires fusion processing of dozens of sensors, including high resolution cameras, radars and LiDARs. To meet power consumption and performance targets, EyeQ5 will be targeted at 10nm or smaller FinFET technology. It will feature eight multithreaded CPU cores, along with 18 of Mobileye’s vision processor cores. According to the partners, the enhancements will bring an 800% increase in performance over the current device, with EyeQ5 capable of handling more than 12TOPs, while consuming less than 5W. EyeQ5’s dedicated I/O will support a bandwidth of at least 40Gbit/s.
“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 Professor Amnon Shashua, Mobileye’s CTO and chairman.
Marco Monti, general manager of ST’s automotive and discrete group, added: “With our joint commitment to the fifth generation of the industry’s leading ADAS technology, ST will continue to provide a safer, more convenient smart driving experience.”
Engineering samples of EyeQ5 are expected in the first half of 2018.
