Adaptive Communication Algorithms for Distributed Heterogeneous Systems

Heterogeneous network-based systems are emerging as attractive computing platforms for HPC applications. This paper discusses fundamental research issues that must be addressed to enable network-aware communication at the application level. We present a uniform framework for developing adaptive communicationschedules for various collective communication patterns. Schedules are developed at run-time, based on network performance information obtained from a directory service. We illustrate our framework by developing communication schedules for total exchange. Our first algorithm develops a schedule by computing a series of matchings in a bipartite graph. We also present a heuristic algorithm, whose completion time is within twice the optimal. This algorithm is based on the open shop scheduling problem. Simulation results show performance improvements of a factor of 5 over well known homogeneous scheduling techniques.