Prioritized Configuration Memory Corruption Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing programmable integrated circuits (ICs) face challenges in detecting and mitigating corruption of configuration memory cells due to single event upsets (SEUs) and radiation, leading to delays in error detection and correction, especially in critical modules where timely intervention is crucial.
Innovation Solution
Implementing a method where configuration memory cells of different modules are checked for corruption at varying frequencies based on priority, with critical modules checked more frequently to reduce the window of vulnerability and enable faster error detection and mitigation, using techniques such as checksum calculation, error correction codes, and comparison with redundant copies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If triple modular redundancy (TMR) is used to mitigate SEUs, then reliability is improved, but device complexity and hardware cost increase significantly
Solution Approach 1:
The patent applies local quality by implementing prioritized corruption detection where different modules are checked at different frequencies based on their criticality. Critical modules (e.g., control logic, safety functions) are monitored more frequently than non-critical modules, optimizing the balance between reliability and resource usage without requiring full TMR across the entire system.
Solution Approach 2:
The system segments the circuit into multiple modules with assigned priority levels. By dividing the system into prioritized groups, the patent enables selective monitoring strategies where high-priority modules receive more intensive detection resources, reducing the overall hardware overhead compared to uniform TMR implementation.
2Reliability
If sequential checking of all configuration memory cells is performed, then corruption detection is achieved, but detection delay increases for non-immediate memory frames
Solution Approach 1:
The patent implements dynamic corruption detection by adjusting the checking frequency of different modules based on their priority assignments. Critical modules are checked more frequently than non-critical ones, creating a dynamic monitoring strategy that reduces detection delay for important functions while maintaining acceptable detection capabilities across the entire system.
Solution Approach 2:
The system employs periodic corruption checking with varying periods for different modules. High-priority modules undergo more frequent periodic checks, ensuring timely detection of corruptions in critical areas, while lower-priority modules are checked less frequently, optimizing the overall detection timeline.
3Ease of operation
If uniform corruption checking frequency is applied to all modules, then implementation simplicity is maintained, but detection effectiveness for critical modules is reduced
Solution Approach 1:
The patent assigns different checking frequencies to different modules based on their criticality, with critical modules receiving more intensive monitoring. This localized quality approach ensures that resources are concentrated where they are most needed, improving reliability for safety-critical functions without requiring uniform high-frequency checking across the entire system.
Data Source
AI summary
In one embodiment, a method of detecting corruption of configuration memory is provided. A bitstream of a circuit design that includes at least a first module and a second module is generated. Configuration memory cells used to implement each of the first and second modules are determined. The configuration memory cells are programmed with the bitstream. After programming, configuration memory cells used to implement the first module are checked for corruption at a first frequency, and configuration memory cells used to implement the second module are checked for corruption at a second frequency, with the first frequency being different from the second frequency.