Droptop makes running your business easier. Invoicing, scheduling, VIN scanning, OEM recommendations, integrated payments and so much more, all at your fingertips, on any device.
Learn why Droptop is trusted by hundreds of shops.
More versatile and efficient than a standard GPU, handling complex control and data management.
Developed by Mobileye and manufactured by STMicroelectronics using 28nm FD-SOI (Fully Depleted Silicon On Insulator) technology, which helps maintain low power consumption despite high performance.
The datasheet mandates strict sequencing: VDD_IO must rise before VDD_CORE. Minimum reset low pulse width: 50 µs.
Inside the EyeQ4: The "Supercomputer" Driving Your Next Car Mobileye EyeQ4 eyeq4 datasheet
The chip incorporates . The PMA provides compute density similar to fixed-function hardware but retains software programmability. It acts as an accelerator for deep learning layers, particularly pooling, convolutions, and fully connected layers found in modern Deep Neural Networks (DNNs). Multi-Threaded Processing Cores (MPC)
Multi-camera processing, pixel-level scene segmentation, crowd-sourced mapping (REM), and object detection.
: It can output real-time data, including a target list of up to 10 obstacles (cars, trucks, pedestrians) with details like ID, position, speed, and dimensions; detection of up to 4 lane lines ; traffic sign recognition; and vehicle signal status (e.g., brake lights, turn signals). More versatile and efficient than a standard GPU,
. They use special accelerators to process image data very fast. EyeQ4-High Cameras Supported Cameras Supported Up to 3 Cameras 3 MIPS InterAptiv 4 MIPS InterAptiv Total Power Around 2.5 Watts Total Power Around 3 Watts Processor Architecture Mobileye EyeQ4 Vision Processor Family - Yole Group
: Focused on monocular processing for standard collision avoidance.
The EyeQ4 enables several safety and autonomous functions that were difficult for previous generations: The Evolution of EyeQ - Mobileye Minimum reset low pulse width: 50 µs
: Multi-threaded execution modules optimized to perform specific pipeline steps more efficiently than standard CPUs, while maintaining greater flexibility than rigid ASICs.
Six cores for image processing and integral types used in computer vision. MPC (Multi-threaded Processing Cluster):
| Design Parameter | Value | | :--- | :--- | | | 3.3V or 5V (±5%) | | Output Voltage (VOUT) | 1.0V | | Max Load Current (IOUT) | 12A typical (16A max with LP875761A-Q1) | | Voltage Tolerance | ±3% under all conditions (DC & transient) | | Recommended Inductor (L) | 330nH nominal |
: Used by major manufacturers including BMW, Nissan, Honda, and General Motors.
Copyright 2026, Vast Forum
