Mapping and load-balancing iterative computations

• Published in: IEEE transactions on parallel and distributed systems Vol. 15; no. 6; pp. 546 - 558
• Main Authors: Legrand, A., Renard, H., Robert, Y., Vivien, F.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2004; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bandwidth; Clustering algorithms; Clusters; Communication networks; Computer networks; Convolution; Design engineering; heterogeneous clusters; Image processing; Iterative algorithms; iterative computations; Iterative methods; load-balancing; Mapping; Mathematical analysis; Partitioning algorithms; Processors; Resource management; Routing; Routing (telecommunications); Scheduling; Signal processing algorithms
• ISSN: 1045-9219; 1558-2183
• DOI: 10.1109/TPDS.2004.10

We consider the mapping of iterative algorithms onto heterogeneous clusters. The application data is partitioned over the processors, which are arranged along a virtual ring. At each iteration, independent calculations are carried out in parallel, and some communications take place between consecutive processors in the ring. The aim is to determine how to slice the application data into chunks, and to assign these chunks to the processors, so that the total execution time is minimized. One major difficulty is to embed a processor ring into a network that typically is not fully connected, so that some communication links have to be shared by several processor pairs. We establish a complexity result that assesses the difficulty of this problem, and we design a practical heuristic that provides efficient mapping, routing, link- sharing, and data distribution schemes.