1 Blatchington Rd, Brighton and Hove, Hove BN3 3YP, United Kingdom
Mobileye EyeQ4 is a high-performance vision system-on-chip (SoC) designed specifically for advanced driver-assistance systems (ADAS) and semi-autonomous driving. Developed by Mobileye (an Intel company) and manufactured by STMicroelectronics, it represented a massive jump in processing power—roughly 10 times that of its predecessor, the EyeQ3, while consuming only 20% more power. Key Specifications & Architecture
is built on a 28nm Fully Depleted Silicon On Insulator (FD-SOI) process, which is critical for maintaining high performance with a low power envelope of approximately 3 watts. -High Specifications Compute Performance ~2.5 Teraflops (1.26 Billion MAC/s) CPU Cores
4 multi-threaded MIPS InterAptiv cores (4 hardware threads each) Vision Accelerators
6 Vector Microcode Processors (VMP), 2 Multithreaded Processing Clusters (MPC), 2 Programmable Macro Arrays (PMA) Camera Input Up to 8 cameras simultaneously at 36 fps Functional Safety ISO 26262 ASIL-B(D) Packaging Flip-Chip FBGA 784-pin (22.5 x 22.5 x 1.7mm) Specialized Processing Cores The "magic" of the
datasheet lies in its heterogeneous architecture, which uses different types of proprietary accelerators for specific vision tasks:
Vector Microcode Processors (VMP): A VLIW and SIMD machine optimized for computer vision and deep learning algorithms.
Multithreaded Processing Cluster (MPC): More versatile and efficient than a standard GPU, handling complex control and data management.
Programmable Macro Array (PMA): A CGRA dataflow machine providing compute density similar to fixed-function hardware while remaining programmable. Product Variants: High vs. Mid The Evolution of EyeQ - Mobileye
The Mobileye EyeQ4 is a high-performance vision system-on-chip (SoC) designed for Advanced Driver Assistance Systems (ADAS) and semi-autonomous driving. It provides approximately 2.5 teraflops of processing power while maintaining a low-power automotive-grade envelope of roughly 3W. Technical Specifications Summary
The EyeQ4 architecture is based on a heterogeneous computing model that assigns specific tasks to specialized cores for maximum efficiency. Feature Specification Details Processor Cores
4x multi-threaded 64-bit RISC MIPS CPUs (4 hardware threads each) Vision Accelerators
6x Vector Microcode Processors (VMP), 2x Multithreaded Processing Clusters (MPC), 2x Programmable Macro Arrays (PMA) Compute Power >2.5 Teraflops (or 2.5 TOPS depending on variant) Power Consumption ~3 Watts (up to 5W in some high-load configurations) Process Node
28nm Fully Depleted Silicon On Insulator (FD-SOI) by STMicroelectronics Camera Support Up to 8 cameras simultaneously at 36 FPS Safety Standard ISO 26262 compliant with ASIL-B(D) safety level Packaging Flip-Chip FBGA 784-pin; 22.5 x 22.5 x 1.7 mm EyeQ4 Variant Differences
Mobileye developed multiple versions of the chip to support different vehicle capabilities: EyeQ4-High (EyeQ4H)
: The most capable version, supporting trifocal front-sensing, surround-view systems (4 cameras), and sensor fusion with radar and laser scanners. EyeQ4-Medium (EyeQ4M)
: A cost-optimized variant with a subset of cores, typically used for monocular or trifocal camera configurations in standard ADAS applications. Key Interfaces and Connectivity
According to the EyeQ4 Product Brief, the chip includes the following I/O: Memory: Dual 32-bit LPDDR4 SDRAM interfaces at 1.6GHz. Network: 1Gb Ethernet port. eyeq4 datasheet
Video Input: 4x MIPI CSI-2 Rx serial video ports and 1x parallel video port.
Automotive Buses: 3x CAN ports (>1Mbps), 3x UART, 3x I2C, and 4x SPI interfaces. Documentation and Resources Mobileye EyeQ4 Vision Processor Family - Yole Group
Mobileye EyeQ4 is a high-performance vision processor System-on-Chip (SoC) designed specifically for Advanced Driver Assistance Systems (ADAS) and semi-autonomous driving. Launched in 2018, it represented a significant jump in performance, offering roughly 10 times the processing power of its predecessor, the EyeQ3, with only a 20% increase in power consumption. Core Specifications & Performance
The EyeQ4 architecture is built on a 28nm FD-SOI (Fully Depleted Silicon On Insulator) process technology from STMicroelectronics, which is critical for its high efficiency. Specification Details Performance Over 2.5 Teraflops (TFLOPS) or 2.5 TOPS Power Consumption Approximately 3 Watts for typical automotive use Video Processing
Can process up to 8 cameras simultaneously at 36 FPS (high version) Package Size 22.5 x 22.5 mm (784-pin Flip-Chip FBGA) Architecture Overview
The EyeQ4 uses a heterogeneous "accelerator-rich" architecture. It doesn't rely solely on standard CPUs but instead uses four specialized classes of programmable accelerators designed for computer vision tasks.
MIPS CPU Cores: Features four multi-threaded MIPS InterAptiv processor cores (with 4 threads each) for general-purpose management and control.
Vector Microcode Processors (VMP): Six programmable cores optimized for vision algorithms like image filtering and feature extraction.
Multithreaded Processing Cluster (MPC): Two cores designed to be more versatile than a GPU and more efficient than a CPU for complex vision tasks.
Programmable Macro Array (PMA): Two cores offering compute density similar to fixed-function hardware while remaining fully programmable. Key ADAS Capabilities
The EyeQ4 enables several safety and autonomous functions that were difficult for previous generations: The Evolution of EyeQ - Mobileye
Deep Learning Accelerator. Dedicated high-performance AI engine. The main source of horse power for convolutional neural networks. ZF and Mobileye Safety Technology Chosen by Toyota
Mobileye EyeQ4 represents a pivotal bridge in the evolution of automotive technology, moving from simple driver assistance to high-level semi-autonomous driving. As a System-on-Chip (SoC) designed specifically for vision processing, its datasheet reveals a sophisticated architecture engineered to handle the chaotic, real-world environment of modern roads. The Architecture of Vision
At the heart of the EyeQ4 is a specialized heterogeneous architecture. Unlike a standard computer processor, the EyeQ4 utilizes a mix of multi-threaded CPU cores vector microcode processors (VMPs)
. This "asymmetric" design allows the chip to perform massive parallel processing—essentially "seeing" and "interpreting" multiple data streams from cameras and sensors simultaneously—while maintaining a remarkably low power profile of approximately 3 to 5 watts. Safety and Redundancy
A critical takeaway from the EyeQ4 specifications is its focus on functional safety L2+ Highway Assist: Using a forward-facing camera (1
. In the automotive world, a chip failure can have life-altering consequences. The EyeQ4 was built to meet
safety standards, meaning it includes hardware-level redundancies. It doesn't just process pixels; it constantly checks its own work to ensure that the "decisions" it passes to the car’s braking or steering systems are reliable and error-free. Capability vs. Efficiency
While modern chips like the EyeQ5 or NVIDIA’s Orin offer more raw tera-operations per second (TOPS), the EyeQ4 is a masterclass in efficiency
. It provides the computational muscle for Level 2 and Level 3 autonomous features—such as lane keeping, traffic sign recognition, and pedestrian detection—without requiring the liquid cooling or massive battery drain seen in more experimental platforms. Conclusion
The EyeQ4 datasheet is more than a technical list; it is a blueprint for the "eyes" of the modern vehicle. By balancing high-speed visual processing with rigorous safety standards and low power consumption, Mobileye created a platform that transitioned autonomous driving from a laboratory concept into a scalable, everyday reality for millions of drivers. (like TOPS) or compare it to the newer EyeQ5/EyeQ6
The Mobileye EyeQ4 is a 28nm FD-SOI, high-performance System-on-Chip (SoC) designed for camera-based Advanced Driver Assistance Systems (ADAS), delivering over 2.5 teraflops of processing power at 3W. Featuring six VMP cores, two MPC cores, and two PMA cores, it supports up to 8 simultaneous cameras for advanced computer vision and autonomous emergency braking. For more details, visit Mobileye.
The Mobileye EyeQ4 is a high-performance vision processor (SoC) designed specifically for advanced driver-assistance systems (ADAS) and autonomous driving. Launched in 2018, it represented a significant jump in performance, offering roughly ten times the processing capability of its predecessor, the EyeQ3. Key Technical Specifications
The EyeQ4 architecture is built for "super-computer" capabilities within a low-power automotive-grade package. Performance: Capable of more than 2.5 Teraflops (2.5 TOPS).
Power Consumption: Extremely efficient, typically consuming only 3 watts.
Manufacturing Process: 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.
Safety Rating: Designed to meet ISO-26262 standards with a safety level of ASIL-B(D).
Camera Support: Can process information from up to 8 cameras simultaneously at 36 frames per second (fps). Architecture & Hardware Cores
The EyeQ4-High variant features a diverse array of 14 computing cores designed to handle specific vision tasks efficiently: Description MIPS CPUs
Four multi-threaded MIPS processor cores (often InterAptiv) for general data management and control. VMP Cores
Six Vector Microcode Processors for dedicated image processing tasks. MPC Cores
Two Multithreaded Processing Cluster cores, more versatile and efficient than standard GPUs for automotive tasks. PMA Cores the chip is best suited for:
Two Programmable Macro Array cores, providing high compute density for fixed-function hardware acceleration. Core Capabilities
The EyeQ4 was engineered to support a "safety cocoon" around the vehicle, enabling features essential for semi-autonomous and autonomous driving: The Evolution of EyeQ - Mobileye
The Mobileye EyeQ4 is a high-performance vision processor designed specifically for Advanced Driver Assistance Systems (ADAS) and semi-autonomous driving. Launched in 2018, it represented a significant leap in computational efficiency, providing approximately 10 times the processing power of its predecessor, the EyeQ3, while maintaining a very low power envelope. Core Technical Specifications
The EyeQ4 is built on a heterogeneous architecture that utilizes specialized cores for different computer vision tasks to maximize efficiency.
Process Technology: Manufactured using STMicroelectronics' 28nm FD-SOI (Fully Depleted Silicon On Insulator) process, which is optimized for low power consumption.
Performance: Capable of reaching 2.5 Tera Operations Per Second (TOPS) (or 2.5 TFLOPS).
Power Consumption: Typically draws only 3 Watts, making it suitable for windshield-mounted camera systems without specialized cooling.
Input Capability: Supports simultaneous processing for up to 8 cameras at 36 frames per second (fps). Processor Architecture The EyeQ4 integrates several types of programmable cores: The Evolution of EyeQ
The Mobileye EyeQ4 Go to product viewer dialog for this item.
is a high-performance System-on-Chip (SoC) designed for Advanced Driver Assistance Systems (ADAS) and autonomous driving. Manufactured by STMicroelectronics using 28nm FD-SOI technology, it provides 10x the processing power of its predecessor, the EyeQ3, while maintaining a low power envelope. Technical Specifications
The EyeQ4 architecture utilizes a heterogeneous mix of specialized accelerators to achieve high efficiency. Specification Performance 2.5 TOPS (High variant) / ~1.1 TOPS (Mid variant) Power Consumption ~3 Watts (Automotive grade) CPU Cores 4 multi-threaded MIPS InterAptiv cores (4 threads each) Vision Accelerators
6 Vector Microcode Processors (VMP), 2 Multithreaded Processing Clusters (MPC), 2 Programmable Macro Arrays (PMA) Camera Support Up to 8 cameras simultaneously at 36 fps Safety Standard ISO 26262 compliant; ASIL-B(D) level Package Flip-Chip FBGA 784-pin (22.5 x 22.5 x 1.7mm) Key Capabilities The Evolution of EyeQ - Mobileye
For engineers reading an eyeq4 datasheet, the following electrical and physical parameters are critical:
| Parameter | Specification | | :--- | :--- | | Process Technology | 28nm CMOS (FinFET) | | Maximum Camera Inputs | 8 simultaneous cameras | | Processing Performance | 2.5 TOPS (Trillion Operations Per Second) | | Power Consumption | 3W – 5W (typical thermal design power) | | Operating Temperature | -40°C to +125°C (Automotive Grade) | | Safety Certification | ASIL-B (ISO 26262) | | Package Type | BGA (Ball Grid Array) – 585 pin variant | | Interface Support | CAN-FD, FlexRay, Gigabit Ethernet, LVDS, I2C, SPI, GPIO |
According to reference designs in the EyeQ4 datasheet, the chip is best suited for:
| Parameter | Value | |-----------|-------| | Manufacturing Process | 28nm FD-SOI (Fully Depleted Silicon On Insulator) | | Peak Performance | 2.5 TOPS (Trillions of Operations Per Second) | | Power Consumption | ~3W (typical, automotive grade) | | Camera Inputs | Up to 8 cameras (raw image sensors via MIPI CSI-2) | | CPU Cores | 4× MIPS interAptiv (lockstep for safety) | | Vision Accelerators | 4× Vector Microcode Processors (VMPs) | | Memory Interface | LPDDR4 / DDR3L (up to 4 GB, 64-bit) | | Safety Level | ASIL B (system) / ASIL D (for some safety paths) | | Operating Temp | -40°C to +105°C (Tj) |
