Eyeq4 Datasheet Better
Overview
. Launched in 2018, it offers approximately 10 times the processing power of its predecessor, the EyeQ3, while maintaining high energy efficiency. Yole Group Core Technical Specifications Architecture eyeq4 datasheet
The EyeQ4 datasheet highlights several key features that make it an attractive solution for ADAS and autonomous driving applications: Overview
- The EyeQ4 is engineered around three primary goals: high compute efficiency for vision/DNN workloads, functional safety readiness for automotive requirements, and power and thermal efficiency appropriate for in-vehicle integration.
- It typically combines multiple heterogeneous compute elements: fixed-function hardware accelerators for vision primitives, vector DSPs and CPU cores for control and general-purpose tasks, and dedicated neural network accelerators for deep learning inference.
- The architecture emphasizes parallelism and deterministic latency to satisfy real-time perception and control loops in ADAS stacks.
Key Features
-
8. Ordering Information (Example)
| Part Number | Description | |------------------|------------------------------------| | EYQ4-8C2-1 | EyeQ4, 8GB LPDDR4, industrial temp | | EYQ4-4C1-A | EyeQ4, 4GB LPDDR4, automotive temp | (Note: Check official pricing/ordering with Intel/Mobileye representatives) The EyeQ4 is engineered around three primary goals:
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