2 cores offering higher efficiency than standard CPUs and more versatility than a GPU. Programmable Macro Array
For hardware engineers, system integrators, and automotive developers, the is the foundational document. It provides the electrical specifications, thermal limits, pinout diagrams, and performance benchmarks necessary to integrate this powerful SoC into an Electronic Control Unit (ECU).
Supports up to eight cameras. This allows a typical configuration of one forward-facing trifocal camera assembly, side-view cameras, and rear-view cameras for a complete 360∘360 raised to the composed with power surround-view cocoon. eyeq4 datasheet
The Mobileye EyeQ4 is a high-performance, low-power System-on-Chip (SoC) designed specifically for camera-based Advanced Driver Assistance Systems (ADAS) and autonomous driving. Launched in 2018 as the successor to the EyeQ3, it offers roughly ten times the processing capability while maintaining a strict automotive power envelope.
The EyeQ4 is designed for seamless integration into a vehicle's network. 2 cores offering higher efficiency than standard CPUs
[8x Camera Inputs] → [ISP / Image Preprocessor] → [CNN Accelerator] → [Vector Cores] → [Fusion & Decision] ↓ ↓ ↓ [SRAM 2.5MB] [Safety CPU (lockstep)] [External LPDDR4]
The foundational magic of the EyeQ4 datasheet lies in its highly heterogeneous, many-core computing architecture. Rather than relying on a power-hungry general-purpose GPU, Mobileye engineered a proprietary mix of general-purpose RISC processor cores and highly specialized hardware accelerators. 1. General-Purpose Compute Layer Mobileye EyeQ4 Vision Processor Family - Yole Group Supports up to eight cameras
: Capable of reaching 2.5 Tera Operations Per Second (TOPS) (or 2.5 TFLOPS).