A Clustering Method for Modeling the Communication Requirements of Message-Passing Applications

Abstract

Clusters have become a very cost-effective platform for high-performance computing. Usually these systems become heterogeneous as they grow, due to their incremental capabilities. Many research activities have focused on the problem of task scheduling in heterogeneous systems from the computational point of view. However, an ideal scheduling strategy would also take into account the communication requirements of the applications and the communication bandwidth available in the network. One of the key issues in this strategy is the measurement of the communication requirements for each application.
In this paper, we propose a clustering-based method to characterize the communications between processes generated by message-passing applications. This technique provides a model consisting of several partitions of the processes generated by the application. Also, we propose a criterion to measure the quality of the obtained partitions. This approach can be used when a given application is repeatedly executed with different input data. Results show that the proposed method can provide a partition with the highest ratio between the intracluster and the intercluster required communication bandwidth. This partition can be used to map groups of processes to processors in the heterogeneous system.