Proceedings of the First Workshop on Cluster-Based Computing

Sunday 20 June 1999
Rhodes, Greece


Preface

We take great pleasure in introducing these papers presented at the First ACM ICS Workshop on Cluster-Based Computing, held on 20 June 1999 on the island of Rhodes in Greece in conjunction with the 13th ACM-SIGARCH International Conference on Supercomputing.

The popularity of cluster platforms for scalable, high-performance computing has grown rapidly in the last few years, and it is now clear that clusters will play a critical role in defining the future of supercomputing. The focus of this workshop is thus a timely one, and we hope that the workshop will be a productive forum both for exchanging knowledge and for fostering collaborations between leaders in cluster-based research.

We were excited to receive many good submissions on a wide variety of topics, particularly given that this workshop is the first. We accepted a total of twelve of these submissions in order to allow adequate time for the presentations. The papers chosen cover the full range of topics, from low-level cluster design issues through library support and resource management to programming models and applications. We hope that you find them as enjoyable and as useful as have we.

We wish to thank the people that helped to make this workshop possible. First, we thank Constantine Polychronopoulos, who encouraged us to organize the workshop and who gave freely of his help and advice throughout the process. We next thank the authors for contributing their work and for their cooperation and patience with the process. Finally, Peter Kalogiannis helped to put together the proceedings, for which we are grateful.

Nicholas P. Carter
Assistant Professor
Steven S. Lumetta
Assistant Professor
Department of Electrical and Computer Engineering
Coordinated Science Laboratory
University of Illinois at Urbana-Champaign
npcarter@uiuc.edu
lumetta@uiuc.edu


Table of Contents

Session I:Software Infrastructure
  "Scalable Load Distribution and Load Balancing for Dynamic Parallel Programs"
Emery Berger and James C. Browne
University of Texas at Austin
  "Global and Integrated Processor, Memory and Disk Management in a Cluster of SMP's"
Christine Morin
IRISA/INRIA
  "Algorithms for Collective Communication Operations on SMP Clusters"
Maciej Golebiewski, Rolf Hempel, and Jesper L. Träff
NEC Europe
Session II:High-Performance Communication
  "A Stream Protocol Implementation for an SCI-Based Cluster of Workstations"
Jørgen S. Hansen, Povl T. Koch, and Eric Jul
University of Copenhagen
  "Exploiting Clusters of Shared Memory Multiprocessors with BIP-SMP: The Parallel Simulation Application"
P. Geoffray, CongDuc Pham, and Bernard Tourancheau
Université Claude Bernard Lyon
  "An Improved NIC Program for High-Performance MPI"
Loïc Prylli, Ecole Normale Supérieure de Lyon
Bernard Tourancheau and Roland Westrelin, Université Claude Bernard Lyon
Session III:Applications
  "Managing High Volume Astronomical Data with Heterogeneous Beowulf Clusters"
John Salmon, Daniel F. Savarese, and Thomas Sterling
California Institute of Technology
  "Topos - Manager for Computing in Distributed Computer Environment"
Sergey S. Kosyakov and Lev N. Shchur
Landau Institute
  "MuSA: A Scalable Multimedia Server Based on Clusters of SMP's"
Roberto Canonico, Giuseppe Capuozzo, Giulio Iannello, and Giorgio Ventre
Universita di Napoli v. Claudio
Session IV:Large Clusters and Irregularity
  "Scalability Issues in Cluster Computing Operating Systems"
Srinivas Nimmagadda and Ilan Harari
Intel Corporation
  "Cluster-Based High-Performance Computing at LANL"
Peter Beckman, Susan Coghlan, and Rod Oldehoeft
Los Alamos National Laboratory