ParaRMS algorithm: A parallel implementation of rate monotonic scheduling algorithm using OpenMP

Abstract

With the evolution of multi-core Systems, the computing performance has been improved and these processors with more than one processing cores has found there application in the fields where high performance and complex computation is required like supercomputing, remote monitoring systems, data mining, data communication and processing systems etc. Multi-core processors can be utilized to improve the performance of embedded and real time systems. As the scheduling capability of the Real Time Operating System (RTOS) determines its efficiency and performance when dealing with real-time critical tasks, use of more than one processing units speeds up the task processing. This paper presents an algorithm called ParaRMS, which is a Rate Monotonic Scheduling (RMS) algorithm in parallel on multi-core architecture and has been scheduled on a multi-core system. This improves the scalability and responsiveness of the Rate monotonic scheduling algorithm which will also help scheduling the dynamic tasks effectively and offers good CPU utilization for given task set. In support of this work, analysis of ParaRMS has been carried out on Intel VTune Amplifier XE 2013 with positive results.