Articles

Based on semantics of an application processing logic, we find out the most critical and sensitive parts of an application and we derive set of conditions or assertions among the various diagnostic checkpoint variables and we enhance the processing logic to enable it to detect run-time various operational or environmental faults toward fault tolerant computing. This paper examines how a single-version algorithm can establish software based fault tolerance by designing in thoughtful software based execution-time checks in a computing application. The algorithm developed here relies on various assertions that are derived from the semantics of an application. Various diagnostic assertive checkpoints have been derived based on an application's semantics. This work is not intended to correct bit-errors using conventional error correction codes. Errors have been detected through checkpoints and periodical execution of an application with known test data and verification of observed result with known result thereof. Electrical transients or small particles hitting the circuit, often cause random errors or faults in data and program flow. The manuscript describes an algorithm that allows the detection and recovery of transient or operational failures in software on a specific problem, just by using one version of a software program running on just one machine. This approach does not aim to tolerate software design bugs. This algorithmic approach uses various run-time signatures and validation thereof in order to detect faults.