Efficient algorithm for DAG scheduling on multi-clusters platforms

Modern computation systems are inherently heterogeneous and many of them are characterized by a hierarchical organization. In this paper, we present a novel algorithm for Directed Acyclic Graphs (DAGs) scheduling on heterogeneous platforms composed of a set of processors grouped in a cluster of clusters (multi-clusters environments). Our main objective here is to develop an algorithm taking into account several characteristics of the target platform, including the heterogeneity of both computing powers of processors and communication links. Simulation results, based on both randomly generated graphs and platforms and real configuration based generated platforms, show that the proposed algorithm provides interesting performances.