Volume 734 of the series Lecture Notes in Computer Science pp 219232
Generating parallel code from equations in the ObjectMath programming environments
 Peter FritzsonAffiliated withDepartment of Computer and Information Science, Linköping University
 , Niclas AnderssonAffiliated withDepartment of Computer and Information Science, Linköping University
Abstract
For a long time efficient use of massively parallel computers has been hindered by dependencies introduced in software through lowlevel implementation practice. This paper presents a programming environment and language called ObjectMath (Object oriented Mathematical language for scientific computing), which aims at eliminating this problem by allowing the user to represent mathematical equational models directly in the system. The system performs dependency analysis of equations to extract parallelism and automatically generates parallel code for numerical solution.
The system is currently being used for industrial applications in advanced mechanical analysis, but is generally applicable to other areas. Using ObjectMath, it is possible to model classes of equation objects, to support inheritance of equations, and to solve systems of equations.
 Title
 Generating parallel code from equations in the ObjectMath programming environments
 Book Title
 Parallel Computation
 Book Subtitle
 Second International ACPC Conference Gmunden, Austria, October 4–6, 1993 Proceedings
 Pages
 pp 219232
 Copyright
 1993
 DOI
 10.1007/3540573143_18
 Print ISBN
 9783540573142
 Online ISBN
 9783540480556
 Series Title
 Lecture Notes in Computer Science
 Series Volume
 734
 Series ISSN
 03029743
 Publisher
 Springer Berlin Heidelberg
 Copyright Holder
 SpringerVerlag
 Additional Links
 Topics
 Industry Sectors
 eBook Packages
 Editors
 Authors

 Peter Fritzson ^{(1)}
 Niclas Andersson ^{(1)}
 Author Affiliations

 1. Department of Computer and Information Science, Linköping University, S581 83, Linköping, Sweden
Continue reading...
To view the rest of this content please follow the download PDF link above.