How to cope with SEU/SET at system level?

COTS – Harsh Condition Effects Considerations from Technology to User Level

“…In the system level, the duplication or triplication of programmable COTS devices is the most usual technique [32]. BiModular Redundancy (Bi-MR) architectures are mainly used in fail-stop systems, since a duplex mechanism cannot intrinsically correct failures, requiring extra mechanisms that use time redundancy at the application level for diagnostic and recovery.…”

Particle swarm optimisation driven low cost single event transient fault secured design during architectural synthesis

“…Considering worst possible value (strength) of transient fault in temporal domain ( k c ) and spatial domain ( k m ) as design specification/constraint during HLS (at behavioral level) in conjunction with an advanced design space exploration (DSE) framework, enables generation of a low‐cost design solution that is concurrently multiple transient and multi‐cycle transient fault secured. This paper presents a novel low‐cost security to the dual problem (multi‐unit transient and multi‐cycle transient fault) through HLS [12, 18–23].…”

A Hardware-Software Approach for On-Line Soft Error Mitigation in Interrupt-Driven Applications

“…However, this fine-grain redundancy does not fit in COTS components because the impossibility to modify their internal hardware. Coarsegrain alternatives, as duplication or triplication of components [5], have also been explored and even used in real systems, obtaining very good results. These approaches increase the complexity, cost and power consumption; hiding the benefits of COTS components and limiting their use in low-cost and small systems.…”