Coprocessing Image Data with CPU and FPGA
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing integrated circuit inspection systems face challenges with flexibility, reliability, and cost due to reliance on customized hardware and switched fabric topologies, which lead to high nonrecurring engineering costs, limited versatility, and inadequate support for algorithm changes.
Innovation Solution
An inspection system utilizing a sensor array with a commercially available central processing unit and field programmable gate array to coprocess image data, leveraging a general-purpose computer architecture with a high-speed bus for efficient image data processing and analysis, reducing custom hardware reliance and enhancing flexibility and cost-effectiveness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If customized hardware is used for inspection systems, then processing speed and accuracy can be optimized, but nonrecurring engineering costs increase significantly
Solution Approach 1:
The patent applies universality by using commercially available general-purpose computers and standard hardware components that can serve multiple inspection functions through software configuration rather than dedicated customized hardware. This allows the same physical infrastructure to handle different inspection algorithms and requirements, eliminating the need for expensive custom hardware development while maintaining processing capability.
Solution Approach 2:
The patent employs copying by using standard commercial computer architectures that replicate the necessary processing functions through software and standard hardware rather than creating unique customized hardware designs. This allows leveraging existing proven technologies and distributing development costs across many units through commercial manufacturing.
2Productivity
If customized hardware is used for inspection systems, then processing performance can be enhanced, but system reliability decreases
Solution Approach 1:
The patent uses commercially available general-purpose computers with standardized components that benefit from extensive testing, proven reliability, and continuous improvement by major manufacturers. These universal platforms provide consistent performance while maintaining high reliability through established quality control and support infrastructure.
Solution Approach 2:
The system employs commercially available hardware and software that come with built-in support, updates, and maintenance services from the manufacturers. This self-service model ensures continuous improvement and bug fixes are provided at no additional cost to the user, enhancing both reliability and performance over time without requiring custom hardware support teams.
3Manufacturing precision
If customized hardware is used for inspection systems, then specific processing requirements can be met, but flexibility and versatility are reduced
Solution Approach 1:
The patent implements dynamics by using programmable software-based processing on general-purpose computers rather than fixed customized hardware. This allows the inspection system to dynamically adapt to different algorithms, processing requirements, and inspection types by loading different software modules, providing both precision for specific tasks and flexibility for future adaptations.
Solution Approach 2:
The system uses commercially available computers with standard architectures that can be configured through software to perform multiple inspection functions. This universal approach maintains manufacturing precision for specific requirements while preserving the ability to adapt to new inspection methods and algorithms without hardware changes.
4Productivity
If switched fabric topology is used for networking inspection systems, then data communication can be achieved, but system cost and complexity increase
Solution Approach 1:
The patent applies universality by using standard commercial networking components and protocols rather than proprietary switched fabric topologies. This allows data communication to be achieved using off-the-shelf hardware and software that follow industry standards, reducing system complexity while maintaining communication capability through proven commercial solutions.
Data Source
AI summary
An inspection system having a sensor array that provides image data. A process node includes a memory to receive the image data, a commercially available central processing unit to receive and coprocess at least a first portion of the image data within the memory, and a field programmable gate array to receive and coprocess at least a second portion of the image data within the memory. In this manner, there are two elements in the process node that are used to simultaneously process the image data, and the image data analysis thereby proceeds at a much faster rate than it would with just a single processor in a commercially available computer. However, the system as described has very little custom hardware, and thus is relatively inexpensive, and highly versatile.