MAPPING ARBITRARY HETEROGENEOUS TASK GRAPHS ONTO ARBITRARY HETEROGENEOUS SYSTEM GRAPH

Abstract

In this paper, a generic technique for mapping arbitrary heterogeneous task graphs onto arbitrary heterogeneous system graphs is presented. The heterogeneous task and system graphs studied in this paper have nonuniform computation and communication weights associated with the nodes and the edges. Two clustering algorithms have been proposed that can be used to obtain a multilayer clustered graph called a Spec graph from a given task graph and a multilayer clustered graph called a Rep graph from a given system graph. We present a mapping algorithm that produces a suboptimal matching of a given Spec graph containing M task modules onto a Rep graph of N processors, in O(M2) time, where N ≤ M. Our experimental results indicate that our mapping algorithm is the fastest one and generates results that are better than, or similar to, those of other leading techniques, some of which work only for restricted task or system graphs.