Abstract
The SCOOPP (Scalable Object Oriented Parallel Programming) system is an hybrid compile and run-time system. SCOOPP dynamically scales OO applications on a wide range of target platforms, including a novel feature to perform a run-time packing of excess parallel tasks. This communication details the methodology and policies to pack parallel objects into grains and method calls into messages. The SCOOPP evaluation focus on a pipelined parallel algorithm - the Eratosthenes sieve - which may dynamically generate a large number of fine-grained parallel tasks and messages. This case study shows how the parallelism grain-size - both computational and communication - has a strong impact on performance and on the programmer burden. The presented performance results show that the SCOOPP methodology is feasible and the proposed policies achieve efficient portability results across several target platforms.
This work was partially supported by the SETNA-ParComp project (Scalable Environments, Tools and Numerical Algorithms in Parallel Computing), under PRAXIS XXI funding (Ref. 2/2.1/TIT/1557/95).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kruatrachue, B., Lewis, T.: Grain Size Determination for Parallel Processing, IEEE Software, Vol. 5(1), January (1988)
Gresoulis, A., Yang, T.: On the Granularity and Clustering of Direct Acyclic Graphs, IEEE Transactions on Parallel and Distributed Systems, Vol. 4(6), June (1993)
High Performance Fortran Forum: HPF language specification, Technical Report CPRPC-TR92225, Center for Research on Parallel Computation, Rice University, Tex., (1993)
Beckman, P., Gannon, D., Johnson, E.: HPC++ and the HPC++ Lib. Toolkit, White Paper, www.extreme.indiana.edu/hpc++, (1997)
Andersen, A.: A General, Fine-Grained, Machine Independent, Object-Oriented Language, ACM SIGPLAN Notices, Vol. 29(5), May (1994)
Sobral, J., Proença, A.: Dynamic Grain-Size Adaptation on Object-Oriented Parallel Programming-The SCOOPP Approach, Proceedings of the 2nd Merged IPPS/SPDP 1999, Puerto Rico, April (1999)
Sobral, J., Proença, A.: ParC++: A Simple Extension of C++ to Parallel Systems, Proceedings of the 6th Euromicro Workshop on Parallel and Distributed Applications (PDP.98), Madrid, Spain, January (1998)
Sobral, J., Proença, A.: A Run-time System for Dynamic Grain Packing, Proceedings of the 5th International EuroPar Conference (Euro-Par’99), Toulouse, France, September (1999)
Mohr, E., Kranz, A., Halstead, R.: Lazy Task Creation: A Technique for Increasing the Granularity of Parallel Programs, IEEE Transactions on Parallel and Distributed Processing, Vol. 2(3), July (1991)
Goldstien, S., Schauser, K., Culler, D: Lazy Threads: Implementing a Fast Parallel Call, Journal of Parallel and Distributed Computing, Vol. 37(1), August (1996)
Karamcheti, V., Plevyak, J., Chien, A.: Runtime Mechanisms for Efficient Dynamic Multithreading, Journal of Parallel and Distributed Computing, Vol. 37(1), August (1996)
Taura, K., Yonezawa, A.: Fine-Grained Multithreading with Minimal Compiler Support. A Cost Effective Approach to Implementing Efficient Multithreading Languages, Proceedings of the ACM SIGPLAN Conference on Programming Language Design & Implementation (CPLDI.97), Las Vegas, July (1997)
Lopez, P., Hermenegildo, M., Debray, S.: A Methodology for Granularity Based Control of Parallelism in Logic Programs, Journal of Symbolic Computation, Vol. 22, (1998)
Pritchard, P.: Linear Prime-Number Sieves: A Family Tree, Science of Computer Programming, Vol. 9, (1987)
Xuedong, L.: A Practical Sieve Algorithm Finding Prime Numbers, Communications of the ACM, Vol. 32(3), (1989)
Dunten, B., Jones, J., Sorenson, J.: A Space-Efficient Fast Prime Number Sieve, Information Processing Letters, Vol. 59, (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sobral, J.L., Proença, A.J. (2001). A SCOOPP Evaluation on Packing Parallel Objects in Run-Time. In: Palma, J.M.L.M., Dongarra, J., Hernández, V. (eds) Vector and Parallel Processing — VECPAR 2000. VECPAR 2000. Lecture Notes in Computer Science, vol 1981. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44942-6_9
Download citation
DOI: https://doi.org/10.1007/3-540-44942-6_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41999-0
Online ISBN: 978-3-540-44942-3
eBook Packages: Springer Book Archive