Parallel Scientific Computing in Distributed Systems: The Paralex Approach

Modern distributed systems consisting of powerful workstations and high-speed interconnection networks are an economical alternative to special-purpose parallel machines. Unfortunately, current software support requires users to be experts in distributed computing in order to develop parallel applications for such systems. In this paper, we describe the Paralex system that allows parallel scientific applications to be programmed and executed on distributed systems as if they were uniform, multiprocessor parallel machines. We illustrate the main features of the system by considering the Synthetic Aperture Radar signal processing problem. Some preliminary performance results for the system running on a network of Sun-4 workstations are also reported.

[1]  D. Scott Dyer,et al.  A dataflow toolkit for visualization , 1990, IEEE Computer Graphics and Applications.

[2]  Jack Dongarra,et al.  A User''s Guide to PVM Parallel Virtual Machine , 1991 .

[3]  William B. Ackerman,et al.  Data Flow Languages , 1899, Computer.

[4]  Robert G. Babb,et al.  Parallel Processing with Large-Grain Data Flow Techniques , 1984, Computer.

[5]  Nicholas Carriero,et al.  Parallel Programming in Linda , 1985, ICPP.

[6]  Vito Pascazio,et al.  An efficient SAR parallel processor , 1991 .

[7]  F. Adragna,et al.  Synthetic Aperture Radar : New Processing Concepts , 1990, 10th Annual International Symposium on Geoscience and Remote Sensing.

[8]  Michael Burrows,et al.  Autonet: A High-Speed, Self-Configuring Local Area Network Using Point-to-Point Links , 1991, IEEE J. Sel. Areas Commun..

[9]  R. Davoli,et al.  Mapping parallel computations onto distributed systems in Paralex , 1991, [1991] Proceedings, Advanced Computer Technology, Reliable Systems and Applications.

[10]  Jonathan Schaeffer,et al.  A Template-Based Approach to the Generation of Distributed Applications Using a Network of Workstations , 1991, IEEE Trans. Parallel Distributed Syst..

[11]  James C. Browne,et al.  CODE: a unified approach to parallel programming , 1989, IEEE Software.

[12]  Jeffrey S. Chase,et al.  The Amber system: parallel programming on a network of multiprocessors , 1989, SOSP '89.

[13]  Jack J. Dongarra,et al.  Graphical development tools for network-based concurrent supercomputing , 1991, Proceedings of the 1991 ACM/IEEE Conference on Supercomputing (Supercomputing '91).

[14]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .