Adaptive single-event effect mitigation for dependable processing systems based on FPGAs

Abstract

For FPGA-based applications in harsh radiation environments, designers apply mitigation techniques according the worst-case (solar) condition to achieve a dependable design. This results in a resource overhead, which is most of the time unnecessary. To overcome this problem, an adaptive mitigation technique is used, which is a trade-off between two parameters, such as performance and reliability. We propose an Adaptive Single-Event Effect Mitigation (ASEEM) method, based on FPGA reconfiguration between a performance mode and a reliability mode. The performance mode offers high processing power and the reliability mode offers a high dependability. We evaluate ASEEM by calculating results using particle flux data from 2010 until 2017 for one space-grade and two commercial-grade FPGAs. Based on radiation data, we calculate upset rates, availability, performance, and performability. We optimize the performability, which is the benchmark parameter, in dependence of the Mean Time to Repair (MTTR) and time configured in the performance mode. We conclude that the performability of ideal ASEEM (without implementation losses) maximizes with an improvement of 132% over the compared static modes (performance and reliability) at an MTTR of 19.8 h and 91% of the time in the performance mode for the space-grade FPGA. ASEEM is implemented as FPGA design to determine the implementation impact.