Optimization Algorithm for Divisible Load Scheduling on Heterogeneous Star Networks
Divisible loads are parallel tasks which can be divided into arbitrary number of fractions. There are no precedence relationships among fractions, thus they can be processed independently on the processors in parallel. Such workload model is useful in many real world applications, e.g., signal processing, image processing, experimental data processing and so on. Divisible load theory has emerged as a powerful tool for modeling data-intensive computational problems, and a great amount of research on divisible load scheduling has been made in the last decades.