List Based Scheduling Algorithm for Heterogeneous Sysytem

In this paper, we present a novel listbased scheduling algorithm called Predict Earliest Finish Time (PEFT) for heterogeneous computing systems. The algorithm has the same time complexity as the state-of-the-art algorithm for the same purpose, that is, Oðv2: pÞ for v tasks and p processors, but offers significant makes pan improvements by introducing a look-ahead Feature without increasing the time complexity associated with computation of an optimistic cost table (OCT). The calculated value is an optimistic cost because processor availability is not considered in the computation. Our algorithm is only based on an OCT that is used to rank tasks and for processor selection. The analysis and experiments based on randomly generated graphs with various characteristics and graphs of realworld applications show that the PEFT algorithm outperforms the state-of-the-art list-based algorithms for heterogeneous systems in terms of schedule length ratio, efficiency, and frequency of best results. The efficiency of executing parallel applications on heterogeneous systems critically depends on the methods used to schedule the tasks of a parallel application. The objective is to minimize the overall completion time or make span. The task scheduling problem for heterogeneous systems is more complex than that for homogeneous computing systems because of the different execution rates among processors and possibly different communication rates among different processors.