Evidences of stochastic Bayesian machines robustness against SEUs and SETs
Alexandre Coelho, M. Solinas, Raphaël Laurent, Juan A. Fraire, Emmanuel Mazer, Nacer-Eddine Zergainoh, Said Karaoui, Raoul Velazco · 2016
This work revisits the stochastic computation paradigm as a way to implement architectures dedicated to Bayesian computation. It is assumed that Stochastic Bayesian Machines (SMBs) are intrinsically tolerant to the effects of radiation. However, practical assessment is mandatory before considering SBMs in hazardous environments. Results of fault-injection campaigns performed at the RTL level provide the first evidences of SBMs robustness with respect to SEUs and SETs.