Article

Free access

Accurate modeling of parallel scientific computations

Authors:

SIGMETRICS '89: Proceedings of the 1989 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

Pages 165 - 170

https://doi.org/10.1145/75108.75390

Published: 01 April 1989 Publication History

PDF eReader

Abstract

Scientific codes are usually parallelized by partitioning a grid among processors. To achieve top performance it is necessary to partition the grid so as to balance workload and minimize communication/synchronization costs. This problem is particularly acute when the grid is irregular, changes over the course of the computation, and is not known until load-time. Critical mapping and remapping decisions rest on our ability to accurately predict performance, given a description of a grid and its partition. This paper discusses one approach to this problem, and illustrates its use on a one-dimensional fluids code. The models we construct are shown empirically to be accurate, and are used to find optimal remapping schedules.

References

[1]

S. B. Baden. Run-Time Partitioning of Scientific Continuum Calculations Running on Multiprocessors. Technical Report LBL- 23635, Lawerence Berkley Laboratory, June 1987.

Google Scholar

[2]

M.J. Berger and S. H. Bokhari. A partitioning strategy for nonuniform problems on multiprocessors. IEEE Trans. on Computers, C-36(5):570-580, May 1987.

Digital Library

Google Scholar

[3]

G. Cybenko and T.G. Allen. Parallel algorithms for classification and clustering. In Proceedings of the 31st Annual Int'l Tech. Symposium on Optical and Optoelectronic Applied Science and Engineering, San Diego, CA, August 1987.

Google Scholar

[4]

G. Fox, M. Johnson, G. Lyzenga, S. Otto, J. Salmon, and D. Walker. Solving Problems on Concurrent Computers. Prentice-Hall, Englewood Cliffs, New Jersey, 1988.

Digital Library

Google Scholar

[5]

N. Matelan. The Flex/32 multicomputer. In Proceedings of the 12th International Symposium on Computer Architecture, pages 209- 213, Computer Society Press, June 1985.

Digital Library

Google Scholar

[6]

D. M. Nicol and F. H. Willard. Problem size, parallel architecture, and optimal speedup. Journal of Parallel and Distributed Computing, 5:404-420, August 1988.

Digital Library

Google Scholar

[7]

D.M. Nicol and J.H. Saltz. Dynamic remapping of parallel computations with varying resource demands. IEEE Trans. on Computers, 37(9):1073-1087, September 1988.

Digital Library

Google Scholar

[8]

W.H. Press, B.P. Flannery, S.A. Teukolsky, and W.T. Vettering. Numerical Recipes. Cambridge University Press, New York, 1986.

Google Scholar

[9]

D. A. Reed, L. M. Adams, and M. L. Patrick. Stencils and problem partitionings: their influence on the performance of multiple processor systems. IEEE Trans. on Computers, C-36(7):845-858, July 1987.

Digital Library

Google Scholar

Cited By

View all

Shu-Ling Lee Chao-Tung Yang Shian-Shyong Tseng Chang-Jiun Tsai (2000)A cost-effective scheduling with load balancing for multiprocessor systemsProceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region10.1109/HPC.2000.846566(302-309 vol.1)Online publication date: 2000
https://doi.org/10.1109/HPC.2000.846566
McCann CZahorjan J(1994)Processor allocation policies for message-passing parallel computersACM SIGMETRICS Performance Evaluation Review10.1145/183019.18302222:1(19-32)Online publication date: 1-May-1994
https://dl.acm.org/doi/10.1145/183019.183022
McCann CZahorjan JDowdy LBunt R(1994)Processor allocation policies for message-passing parallel computersProceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems10.1145/183018.183022(19-32)Online publication date: 1-May-1994
https://dl.acm.org/doi/10.1145/183018.183022
Show More Cited By

Index Terms

Accurate modeling of parallel scientific computations

Recommendations

Accurate modeling of parallel scientific computations

Scientific codes are usually parallelized by partitioning a grid among processors. To achieve top performance it is necessary to partition the grid so as to balance workload and minimize communication/synchronization costs. This problem is particularly ...
Analytical Modelling in Parallel and Distributed Computing
Exploiting parallel processing in large scientific applications

Comments

Information & Contributors

Information

Published In

SIGMETRICS '89: Proceedings of the 1989 ACM SIGMETRICS international conference on Measurement and modeling of computer systems

April 1989

242 pages

ISBN:0897913159

DOI:10.1145/75108

Chairman:
Domenico Ferrari
Univ. of California, Berkeley

ACM SIGMETRICS Performance Evaluation Review Volume 17, Issue 1
May 1989
209 pages
ISSN:0163-5999
DOI:10.1145/75372
Editor:
Blaine D. Gaither
Gould Inc., San Diego, CA
Issue’s Table of Contents

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 April 1989

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

SIGMETRICS89

Sponsor:

SIGMETRICS

SIGMETRICS89: Performance 89 Intl Conference on Measurement & Modeling of Computer Systems

May 23 - 26, 1989

California, Oakland, USA

Acceptance Rates

Overall Acceptance Rate 459 of 2,691 submissions, 17%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
75
Total Downloads

Downloads (Last 12 months)51
Downloads (Last 6 weeks)10

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Shu-Ling Lee Chao-Tung Yang Shian-Shyong Tseng Chang-Jiun Tsai (2000)A cost-effective scheduling with load balancing for multiprocessor systemsProceedings Fourth International Conference/Exhibition on High Performance Computing in the Asia-Pacific Region10.1109/HPC.2000.846566(302-309 vol.1)Online publication date: 2000
https://doi.org/10.1109/HPC.2000.846566
McCann CZahorjan J(1994)Processor allocation policies for message-passing parallel computersACM SIGMETRICS Performance Evaluation Review10.1145/183019.18302222:1(19-32)Online publication date: 1-May-1994
https://dl.acm.org/doi/10.1145/183019.183022
McCann CZahorjan JDowdy LBunt R(1994)Processor allocation policies for message-passing parallel computersProceedings of the 1994 ACM SIGMETRICS conference on Measurement and modeling of computer systems10.1145/183018.183022(19-32)Online publication date: 1-May-1994
https://dl.acm.org/doi/10.1145/183018.183022
Nicol DReynolds P(1990)Optimal Dynamic Remapping of Data Parallel ComputationsIEEE Transactions on Computers10.1109/12.4520639:2(206-219)Online publication date: 1-Feb-1990
https://dl.acm.org/doi/10.1109/12.45206
Nicol DSaltz JTownsend J(1990)Delay point schedules for irregular parallel computationsInternational Journal of Parallel Programming10.1007/BF0140974618:1(69-90)Online publication date: 1-Jan-1990
https://dl.acm.org/doi/10.1007/BF01409746
Wikstrom MGustafson J(1993)The twin bottleneck effects (parallel algorithms)[1993] Proceedings of the Twenty-sixth Hawaii International Conference on System Sciences10.1109/HICSS.1993.284068(574-583)Online publication date: 1993
https://doi.org/10.1109/HICSS.1993.284068

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Accurate modeling of parallel scientific computations

Analytical Modelling in Parallel and Distributed Computing

Exploiting parallel processing in large scientific applications