Dual-SoC Eyewear Architecture for Balanced Vision Workloads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eyewear devices with single System on a Chip (SoC) configurations face inefficiencies in workload distribution and power consumption, limiting their ability to effectively handle multiple processing tasks such as display operation, three-dimensional graphics, and computer vision tasks.
Innovation Solution
The eyewear device employs two SoCs, each with distinct responsibilities, one handling display and operating system functions, and the other managing cameras, computer vision algorithms, and visual odometry, to balance workload and optimize power consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single SoC is used in eyewear devices, then device complexity is reduced, but workload distribution efficiency deteriorates
Solution Approach 1:
The patent divides the processing system into two separate SoCs: a first SoC dedicated to display operations and operating system functions, and a second SoC dedicated to camera operations and computer vision tasks. This segmentation allows each processor to specialize in specific workloads, improving overall processing efficiency and reducing interference between different task types.
2Use of energy by stationary object
If a single SoC handles all tasks, then power consumption management becomes simpler, but overall power consumption efficiency deteriorates
Solution Approach 1:
The patent implements separate power management domains for each SoC, allowing independent optimization of power consumption for display-related tasks and camera/computer vision tasks. This enables the system to power down or reduce clock frequencies of inactive SoCs while maintaining full performance in active domains.
Solution Approach 2:
Each SoC is designed with multi-functional capabilities within its domain - the first SoC handles both display output and operating system management, while the second SoC manages both camera operations and computer vision processing. This multi-functionality reduces the need for additional dedicated processors while maintaining efficient power management.
3Device complexity
If one SoC operates all features, then device architecture is simpler, but ability to handle multiple processing tasks simultaneously deteriorates
Solution Approach 1:
The patent creates distinct processing domains with the first SoC dedicated to display and system operations, and the second SoC dedicated to camera and computer vision operations. This segmentation enables parallel processing of different task types without resource contention, improving real-time performance for both display updates and visual processing.
Solution Approach 2:
The patent introduces an intermediary communication interface between the two SoCs that enables efficient data exchange and task coordination. This mediator layer allows the display SoC to receive processed visual data from the camera SoC and rapidly render it, while maintaining clear separation of processing responsibilities.
Data Source
AI summary
Eyewear devices that include two SoCs that share processing workload. Instead of using a single SoC located either on the left or right side of the eyewear devices, the two SoCs have different assigned responsibilities to operate different devices and perform different processes to balance workload. In one example, the eyewear device utilizes a first SoC to operate displays, and it performs three-dimensional graphics and compositing. A second SoC operates first and second color cameras, first and second computer vision (CV) cameras, an operating system (OS), CV algorithms, and visual odometry (VIO), and it performs hand gesture tracking of the user and provides depth from stereo images. This configuration provides organized logistics to efficiently operate various features, and balanced power consumption.