Optimization of a self-converging algorithm at assembly level to improve SEU fault-tolerance

Abstract

The robustness with respect to SEUs (SingleEvent Upset) of a self-converging algorithm is improved by fault-tolerance techniques implemented at software level. SEU-sensitivity evaluation was done by fault injection campaigns performed using a devoted test platform. Experimental results show that implementing faulttolerance by modifying the assembly code leads to significant improvements of the fault tolerance.