Advertisement

Load Balancing Design Issues on Prefetch-Based DSM Systems

  • Hsiao-Hsi Wang
  • Kuan-Ching Li
  • Kuo-Jen Wang
  • Ssu-Hsuan Lu
  • Chun-Chieh Yang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3756)

Abstract

In recent years, the cluster computing technology has become a cost-effective computing infrastructure, because it aggregates resources of computational power, communication and storage. It is also considered a very attractive platform for low-cost supercomputing. Software distributed shared memory (DSM) provides a convenient and effective solution for programming parallel applications. However, both page faults and communication are major sources of overheads in DSM systems. Prefetching strategy can overlap data transporting time with computation time, as also reducing page faults. Unfortunately, it conducts load imbalance during barrier synchronization. For solving such inconveniences, this research paper discusses the load balancing for barrier synchronization in DSM systems. We discuss that, leaving the loop when half of hosts have finished prefetching is the best method, and therefore, we modify the threshold of leaving loop. Experiments show that, by incorporating load balancing into DSM systems, the barrier synchronization has been improved.

Keywords

DSM system prefetching strategy home-based 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cheung, B.W.-L., Wang, C.-L., LAU, F.C.-M.: Migrating-Home Protocol for Software Distributed Shared Memory. Journal of Information Science and Engineering 18, 929–957 (2002)Google Scholar
  2. 2.
    Crawford, J.A., Mobarry, C.M.: Hrunting: A Distributed Shared Memory System for the BEOWULF Parallel Workstation. In: The Proceedings of Aerospace Conference, vol. 4 (1998)Google Scholar
  3. 3.
    Eskicioglu, M.R., Marsland, T.A., Hu, W., Shi, W.: Evaluation of the JIAJIA Software DSM System on High Performance Computer Architectures. In: The Proceedings of the Hawaii’s International Conference On System Sciences, January 5–8 (1999)Google Scholar
  4. 4.
    Hu, W., Shi, W., Tang, Z.: Optimizing Home-Based Software DSM Protocols. Journal of Networks, Software Tools and Applications, Baltzer Science Publishers 4(3), 235–242 (2001)Google Scholar
  5. 5.
    Hu, W., Zhang, F., Ren, L., Shi, W., Tang, Z.: Running Real Applications on Software DSMs. The Proceedings of High Performance Computing in the Asia-Pacific Region 1, 148–153 (2000)Google Scholar
  6. 6.
    Hu, W., Shi, W., Tang, Z.: Reducing System Overheads in Home-Based Software DSMs. In: The Proceedings of 13th International and 10th Symposium on Parallel and Distributed Processing, April 12-16, pp. 167–173 (1999)Google Scholar
  7. 7.
    Liu, H., Hu, W.: A Comparison of Two Strategies Dynamic Data Prefetching in software DSM. In: The Proceedings of 15th International Parallel and Distributed Processing Symposium, April 23-27, p. 62 (2001)Google Scholar
  8. 8.
    Roh, Y., Seong, B.H., Park, D.: Hiding Latency Through Bulk Transfer and Prefetching in Distributed Shared Memory Multiprocessors. In: The Proceedings of The Fourth International High Performance Computing in the Asia-Pacific Region, vol. 1, pp. 164–166 (2000)Google Scholar
  9. 9.
    Shi, W., Tang, Z.: Dynamic Computation Scheduling for Load Balancing in Home-based Software DSMs. In: Proceedings of the 1999 International Symposium on Parallel Architectures, Algorithms and Networks (I-SPAN 1999), June 1999, pp. 248–253. IEEE CS Press, Perth (1999)Google Scholar
  10. 10.
    Shi, W., Tang, Z.: Load Balancing in Home-based Software DSMs. In: Special Issue of International Journal of Foundations of Computer Science, USA, June, 2001, vol. 12(3), pp. 307–324. World Scientic Publishing Co. Inc, Singapore (2001)Google Scholar
  11. 11.
    Tanenbaum, A.S.: Distributed Operating System. Prentice Hall International Editions, Englewood Cliffs (1995)Google Scholar
  12. 12.
    Wang, K.J., Wang, H.H., Li, K.C.: On Design of a Prefetching Strategy for DSM System. In: The Proceedings of PDPTA 2004 International Conference on Parallel and Distributed Processing Techniques and Applications, Las Vegas, USA (2004)Google Scholar
  13. 13.
    Wilkinson, B., Allen, M.: Parallel Programming Techniques and Applications Using Networked Workstations and Parallel Computers. Prentice Hall, Upper Saddle River (1999)Google Scholar
  14. 14.
    Yu, B., Huang, Z., Cranefield, S., Purvis, M.: Homeless and home-based Lazy Release Consistency protocols on Distributed Shared Memory. In: The Proceedings of the 27th conference on Australasian computer science, January 2004, vol. 26, pp. 117–123 (2004)Google Scholar
  15. 15.
  16. 16.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Hsiao-Hsi Wang
    • 1
  • Kuan-Ching Li
    • 1
  • Kuo-Jen Wang
    • 1
  • Ssu-Hsuan Lu
    • 1
  • Chun-Chieh Yang
    • 1
  1. 1.Parallel and Distributed Processing Center (PDPC), Dept. of Computer Science and Information ManagementProvidence UniversityShaluTaiwan

Personalised recommendations