A software fix towards fault-tolerant computing

Abstract

This article describes a low cost software technique for transient fault detection and fault tolerance in a processing system. The random errors caused by potential transients, Electrical Fast Transients (EFT) can be controlled by this proposed technique. Transient errors, if present, are detected and then necessary recovery action can be taken for attaining higher system reliability and tolerance thereof. It is a very cost effective tool for the application design engineers than the traditional expensive hardware fixes, or N-Version programming.