FT-EALU: fault-tolerant arithmetic and logic unit for critical embedded and real-time systems

Abstract

This paper presents a fault-tolerant ALU (“FT-EALU”) based on time redundancy and reward/punishment-based learning approaches for real-time embedded systems that face limitations in hardware and power consumption budgets. In this method, operations are diversified to three versions in order to correct permanent faults along with the transient ones. The diversities of versions considered in FT-EALU are provided by lightweight modifications to differentiate them and clear the effect of permanent faults. Selecting lightweight modifications such as shift and swap would avoid high timing overhead in computation while providing significant differences which are necessary for fault detection. Next, the replicated versions are executed serially in time, and their corresponding results are voted based on the derived learned weights. The proposed weighted voting module generates the final output based on the results and their weights. In the proposed weighted voting module, a reward/punishment strategy is employed to provide the weight of each version of execution indicating its effectiveness in the final output. To this aim, in the method defined for each version of execution, a weight is defined according to its correction capability confronting several faulty scenarios. Thus, this weight defines the reliability of the temporal results as well as their effect on the final result. The final result is generated bit by bit based on the weight of each version of execution and its computed result. Based on the proposed learning scheme, positive or negative weights are assigned to execution versions. These weights are derived in bit level based on the capability of execution versions in mitigating permanent faults in several fault injection scenarios. Thus, our proposed method is low cost and more efficient compared to related research which are mainly based on information and hardware redundancy due to employing time redundancy and static learning approach in correcting permanent faults. Several experiments are performed to reveal the efficiency of our proposed approach based on which FT-EALU is capable of correcting about \(84.93\%\) and \(69.71\%\) of permanent injected faults on single and double bits of input data.