Reliability Modeling of Fault-Tolerant FPGA-Based Architectures in Space Applications for Soft and Hard Error Recovery

Abstract

FPGAs are currently being used in many applications due to their flexibility and re-programmability. Some of these applications operate in harsh environments. One such environment is space. Focusing on space applications, these FPGAs are subjected to soft and hard faults. For newer technology nodes, in addition to the harsh space environment, these errors are more severe. This paper investigates several fault-tolerant architectures to mitigate Single Event Upsets (SEUs), Double Event Upsets (DEUs), Triple Event Upsets (TEUs) as well as hard faults. Conventionally, for TEUs, seven copies of a module are required (7MR). Therefore, a modified 7MR architecture is studied along with two other architectures with six redundant modules: a modified 6MR architecture and a modified Triple Duplex architecture. Using Continuous Time Markov Chains (CTMCs), it is proven that, in many of the cases studied in this article, the modified Triple Duplex architecture has a higher reliability than the modified 7MR architecture. This is a counter-intuitive result. It is also proven that the modified 6MR architecture always has a lower reliability than the modified Triple Duplex architecture even though they both require six redundant modules. The ratio between the relative rates of SEUs, DEUs and TEUs plays an important role in determining the most reliable architecture. Furthermore, the Xilinx Vivado tool with the Kintex7, 7k410tfbg676 device is used to implement the modified 7MR and modified Triple Duplex voters to estimate the area and power consumed by these techniques.