Skip to main content
SpringerLink
Log in

OpenMP on networks of workstations for software DSMs

  • Correspondence
  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

This paper describes the implementation of a sizable subset of OpenMP on networks of workstations (NOWs) and the source-to-source OpenMP compiler (AutoPar) is used for the JIAJIA home-based shared virtual memory system (SVM). The paper suggests some simple modifications and extensions to the OpenMP standard for the difference between SVM and SMP (symetric multi processor), at which the OpenMP specification is aimed. The OpenMP translator is based on an automatic parallelization compiler, so it is possible to check the correctness of the semantics of OpenMP programs which is not required in an OpenMP-compliant implementation.

AutoPar is measured for five applications including both programs from NAS Parallel Benchmarks and real applications on a cluster of eight Pentium II PCs connected by a 100Mbps switched Ethernet. The evaluation shows that the parallelization by annotating OpenMP directives in simple and the performance of generated JIAJIA code is still acceptable on NOWs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. The OpenMP Forum. OpenMP FORTRAN Application Program Interface, Version 1.0, October, 1997 and OpenMP FORTRAN interpretations, Version 1.0, OpenMP Architecture Review Board, Apr., 1999, available at http://www.openmp.org.

  2. Lam M S. SPEC95 and parallelizing compilers. Presented at the SPEC Committee Meeting, Jan., 1997, available at http://suif.standford.edu/.

  3. Feng X. Global Optimizing technologies of data distribution [dissertation]. Institute of Computing Technology, Chinese Academy of Sciences, May, 1999.

  4. Hu W, Shi W, Tang Z, Li M. A lock-based cache coherence for scope consistency.Journal of Computer Science and Technology, 1998, 13(2): 97–110.

    Article  Google Scholar 

  5. Hu W, Ren L, Zhang Fet al. Running real applications on software DSMs. HPC-Asia 2000 Technical Sessions, May, 2000, Beijing, pp. 148–153.

  6. Hu W, Shi W, Tang Z. Reducing system overheads in home-based software DSMs. In13th International Parallel Processing Symposium & 10th Symposium on Parallel and Distributed Processing (IPPS/SPDP’99), IEEE CS Press, April, 1999, pp. 167–173.

  7. Keleher P, Tseng C. Enhancing software DSM for compiler-parallelized applications. InProc. the 11th International Parallel Processing Symposium, Apr., 1997.

  8. Brieger L. HPF to OpenMP on the origin 2000: A case study. InThe First European Workshop on OpenMP, Sweden, Oct., 1999.

  9. Nieken G, Berrendorf R. Performance characteristics for OpenMP constructs on different parallel computer architectures. InThe First European Workshop on OpenMP, Sweden, Oct., 1999.

  10. Tseng C. Data layout optimizations for high-performance architectures. Technical Report CS-TR-3818, Dept. of Computer Science, University of Maryland, Feb., 1997.

  11. Chandra R, Chen D, Cox R.et al. Data distribution support on distributed shared memory multiprocessor. InProc. the ACM SIGPLAN’97 Conference on Programming Language Design and Implementation (PLDI), pp. 334–345, Las Vegas, Nevada, Jun. 15–18, 1997.SIGPLAN Notices, May, 1997, 32(5).

  12. Jeremiassen T, Eggers S. Reducing false sharing on shared memory multiprocessors through compile time data transformations. InProc. the Fifth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 179–188, Santa Barbara, CA, Jul., 1995.

  13. Shi W, Tang Z, Hu W. Affinity-based self scheduling for software shared memory system. Technical Report TR990001, Institute of Computing Technology, Chinese Academy of Science, Jan., 1999.

  14. MIPSpro FORTRAN77 Programmer’s Guide, Silicon Graphics (http://techpubs.sgi.com/library/dynaweb_bin/0640/bin/nph-dynaweb/SGL.Developer/MproF77_PG /@Generic_BookView).

  15. Varadarajan V, Mittra R. Finite-difference time-domain analysis using distributed computing.IEEE Microwave Guided Wave Letters, 1994, 4(5): 144–145.

    Article  Google Scholar 

  16. Lu H, Hu Y C, Zwaenepoel W. OpenMP on networks of workstations. InProc. Supercomputing’98, Orlando, Florida, Nov., 1998.

  17. Dwarkadas S, Lu H, Cox Aet al. Combining compile-time and run-time support for efficient software distributed shared memory. InProc. IEEE, Special Issue on Distributed Shared Memory, Mar., 1999, pp. 476–486.

  18. Cox A, Hu Y, Lu Het al. OpenMP on networks of SMPs. InProc. the Thirteenth International Parallel Processing Symposium, Apr. 1999, pp. 302–310.

  19. Cox A, Dwarkadas S, Lu Het al. Evaluating the performance of software distributed shared memory as a target for parallelizing compilers. InProc. International Parallel Processing Symposium, Apr., 1997, pp. 474–482.

  20. Lu H, Cox A L, Dwarkadas Set al. Compiler and software distributed shared memory support for irregular applications. InProc. the Sixth Symposium on Principles and Practice of Parallel Programming, Jun., 1997, pp. 48–56.

  21. Scherer A, Lu H, Gross T, Zwaenepoel W. Transparent adaptive parallelism on NOWs using OpenMP. InProc. the 7th Conference on Principles and Practice of Parallel Programming, May, 1999, pp. 96–106.

  22. Hahad M, Erhel J, Priol T. Irregular Loop Patterns Compilation on Distributed Shared Memory Multiprocessors. Technical Report RR-2361, INRIA, France, September, 1994, available at ftp://ftp.inria.fr/INRIA/publication/publips-gz/RR/RR-2361.ps.gz.

    Google Scholar 

  23. Mattson T. The OpenMP Architecture review board and the future of OpenMP. Inthe First European Workshop on OpenMP, Sweden, Oct., 1999.

  24. Hisley D, Satya-narayana P, Agrawal G, Pollock L. Porting and performance evaluation of irregular codes using OpenMP. Inthe First European Workshop on OpenMP, Sweden, Oct., 1999.

Download references

Author information

Authors and Affiliations

  1. University of Science and Technology of China, 230027, Hefei, P.R. China

    Feng Zhang & Guoliang Chen

  2. Institute of Computing Technology, The Chinese Academy of Sciences, 100080, Beijing, P.R. China

    Zhaoqing Zhang

Authors
  1. Feng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guoliang Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhaoqing Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Feng Zhang.

Additional information

The work is supported by the National ‘863’ High-Tech Programme of China under grant No.863-306-ZD01-02-5.

ZHANG Feng received his B.S. degree and Ph.D. degree both from the University of Science and Technology of China in 1996 and 2001, respectively. He is currently a postdoctor at the Institute of Automation, The Chinese Academy of Sciences. His research interests include distributed and metacomputing, realtime and embedded system.

CHEN Guoliang received his B.S. degree in computer science from Xi’an JiaoTong University in 1961. He is currently a professor of the University of Science and Technology of China and director of the Center of National High Performance Computing (Hefei). His research interests include parallel algorithm, computer architecture, computer network and neutral network.

ZHANG Zhaoqing received her B.S. degree in computer science from Beijing University in 1960. She is currently a professor of the Institute of Computing Technology and the Graduate School of University of Science and Technology of China. Her research interests include parallel compiler and its related tools.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zhang, F., Chen, G. & Zhang, Z. OpenMP on networks of workstations for software DSMs. J. Comput. Sci. & Technol. 17, 90–100 (2002). https://doi.org/10.1007/BF02949829

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02949829

Keywords

Search

Navigation