Health Management for Self-Aware SoCs Based on IEEE 1687 Infrastructure

Motivated by the need to tolerate faults, this paper presents a complete fault management solution that includes fault detection and categorization, maintaining a map of faults, and modified scheduling and application algorithms for using healthy resources only. As the system maintains fairly sophisticated models of itself regarding faulty and healthy resources, it constitutes a good example of specialized self-awareness.
—Axel Jantsch, TU Wien