Abstract
This paper discusses some programming issues involved in the implementation of task parallelism on distributed-memory MIMD computers. In particular, we separate those issues that are application-independent and so can be part of a library from those that should be controlled by the user to maximize the performance.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Crivelli S.A.: A Programming Paradigm and Library for Distributed-Memory Computers. Ph.D. Thesis, Tech. Report CU-CS-787-95, Dept. of Comp. Science, Univ. of Colorado, Boulder, (1995).
Crivelli S.A. and Jessup E.R.: A User's Manual for the PMESC Library. Dept. of Comp. Science, Univ. of Colorado, Boulder, (1995).
Gursoy A. and Kale L.: Charm 4.3 Programming Language Manual. Dept. of Comp. Science, Univ. of Illinois, Urbana-Champaign (1994).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Crivelli, S.A., Jessup, E.R. (1996). Task parallelism: What a tool can provide and what should be left to the user. In: Bougé, L., Fraigniaud, P., Mignotte, A., Robert, Y. (eds) Euro-Par'96 Parallel Processing. Euro-Par 1996. Lecture Notes in Computer Science, vol 1123. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61626-8_19
Download citation
DOI: https://doi.org/10.1007/3-540-61626-8_19
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61626-9
Online ISBN: 978-3-540-70633-5
eBook Packages: Springer Book Archive