Robustness with respect to SEUs of a self-converging algorithm

Abstract

Self-convergence is a property of distributed systems, allowing a system, when it was perturbed or badly initialised, to recover a correct operation in a finite number of calculation steps. In this paper is explored the intrinsic robustness of a self converging algorithm with respect to soft errors resulting from SEU (Single Event Upset) phenomena. This study was performed by fault injection using a devoted test platform. A self-converging benchmark program was executed by a LEON3 processor implemented in an FPGA. The low number of observed errors puts in evidence the fault tolerance of the tested algorithm.