Artificial intelligence based task mapping and pipelined scheduling for checkpointing on real time systems with imperfect fault detection

Abstract

Fault-tolerance is emerging as one of the important optimization objectives for designs in deep submicron technology nodes. This paper proposes a technique of application mapping and scheduling with checkpointing on a multiprocessor system to maximize the reliability considering transient faults. The proposed model incorporates checkpoints with imperfect fault detection probability, and pipelined execution and cyclic dependency associated with multimedia applications. This is solved using an Artificial Intelligence technique known as Particle Swarm Optimization to determine the number of checkpoints of every task of the application that maximizes the confidence of the output. The proposed approach is validated experimentally with synthetic and real-life application graphs. Results demonstrate the proposed technique improves the probability of correct result by an average 15% with imperfect fault detection. Additionally, even with 100% fault detection, the proposed technique is able to achieve better results (25% higher confidence) as compared to the existing fault-tolerant techniques.