Self-Adapting Resource Escalation for Resilient Signal Processing Architectures

Abstract

To deal with susceptibility to aging and process variation in the deep submicron era, signal processing systems are sought to maintain quality and throughput requirements despite the vulnerabilities of the underlying computational devices. The Priority Using Resource Escalation (PURE) online resiliency approach is developed herein to maintain throughput quality based on the output Peak Signal-to-Noise Ratio (PSNR) or other health metric. PURE is evaluated using an H.263 video encoder and shown to maintain signal processing throughput despite hardware faults. Its performance is compared to two alternative reconfiguration algorithms which prioritize the optimization of the number of reconfiguration occurrences and the fault detection latency, respectively. For a typical benchmark video sequence, PURE is shown to maintain a PSNR baseline near 32dB. Compared to the alternatives, PURE maintains a PSNR within a difference of 4.02dB to 6.67dB from the fault-free baseline by escalating healthy resources to higher-priority signal processing functions. The diagnosability, reconfiguration latency, and resource overhead of each approach is analyzed. The results indicate the benefits of priority-aware resiliency over conventional redundancy in terms of fault-recovery, power consumption, and resource-area requirements.