A static task scheduling heuristic for homogeneous computing environments

Abstract

List-based scheduling is generally accepted as an attractive approach to static task scheduling in a homogeneous environment, since it pairs low complexity with good results. We present a low complexity algorithm based on list-scheduling and task-duplication on a bounded number of fully connected homogeneous machines. The algorithm is called critical unlisted parents with fast duplicator (CUPFD). The CUPFD algorithm consists of two phases: the listing phase, which is a simple listing heuristic based on list-scheduling, and a low complexity machine assigning phase based on task-duplication. The experimental work has shown that CUPFD outperformed on average all other higher complexity algorithms.