Journal of Computer Science and Technology

, Volume 15, Issue 5, pp 453–460 | Cite as

Limited multiple-writer: An approach to dealing with false sharing in software DSMs

  • Xie Xianghui Email author
  • Han Chengde 


False sharing is one of the most important factors impacting the performance of DSM (distributed shared memory) systems. The single-writer approach is simple, but it cannot avoid the ping-pong effect of the data page thrashing, while the multiple-writer approach is effective for false sharing but with high cost. This paper proposes a new approach, called limited multiple-writer (LMW) to handling multiple writers in software DSM. It distinguishes two kinds of multiple-writer as lock-based form and barrier-based form, and handles them with different policies. It discards theTwin andDiff in traditional multiple-writer approach, and simplifies the implementation of multiple-writer in software DSM systems. The implementation of LMW in a CVM (Coherent Virtual Machine) software DSM system, which is based on a network of workstations, is introduced. Evaluation results show that for some applications such as SOR (Successive Over-Relaxation), LU (Lower triangular and Upper triangular), FFT (Fast Fourier Transformation), and IS (Integer Sorting), LMW provides a significant reduction in execution time (11%, 16%, 33% and 46%) compared with the traditional multiple-writer approach on the platform.


memory consistency false sharing single-writer multiple-writer multiple protocols migration and replication 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Amza C, Cox A L, Dwarkadas Set al. Software DSM protocols that adapt between single writer and multiple writer. InProceedings of HPCA’97, 1997, pp.261–271.Google Scholar
  2. [2]
    Keleher P J. The relative importance of concurrent writers and weak consistency models. InProceedings of the 16th ICDCS, 1996, Hong Kong.Google Scholar
  3. [3]
    Carter J B, Bennett J K, Zwaenepoel W. Techniques for reducing consistency-related information in distributed shared memory systems.ACM Transactions on Comput. Systems, 1995, 13(3): 205–243.CrossRefGoogle Scholar
  4. [4]
    Keleher P J, Cox A L, Zwaenepoel W. Lazy Release consistency for software distributed shared memory. InProceedings of the 19th Annual International Symposium on Computer Architecture, 1992, Queensland Australia, pp.13–21.Google Scholar
  5. [5]
    Keleher P J, Cox A L, Dwarkadas Set al. TreadMarks: Distributed shared memory on standard workstations and operating systems. InProceedings of the USENIX Winter 1994 Conference, 1994, San Francisco, California.Google Scholar
  6. [6]
    Keleher P J. The coherent virtual machine. Technical Report Maryland TR93-215, Department of Computer Science University of Maryland, Sept. 1995.Google Scholar
  7. [7]
    Carter J B, Bennett J K, Zwaenepoel W. Implementation and performance of Munin. InProceedings of the 13th ACM SOSP, October 1991, Pacific Grove, California, pp. 152–164.Google Scholar
  8. [8]
    Gharachorloo Ket al. Memory consistency and event ordering in scalable shared-memory multiprocessors. InProceedings of the 17th Annual ISCA, 1990, Seattle, Washington, pp. 15–26.Google Scholar
  9. [9]
    Singh J P, Weber W D, Gupta A. SPLASH: Stanford parallel applications for shared-memory.Computer Architecture News, March 1992, 20(1): 5–44.CrossRefGoogle Scholar
  10. [10]
    Woo S C, Ohara M, Torrie Eet al. The SPLASH-2 programs: Characterization and methodological considerations. InProceedings of the 22nd ISCA, June 1995, Santa Margherita Ligure, Italy, pp.24–36.Google Scholar
  11. [11]
    Amza C, Cox A L, Rajamani Ket al. Tradeoffs between false sharing and aggregation in software distributed shared memory. InProceedings of PPOPP’97, 1997, Las Vegas, Nevada, pp.90–99.Google Scholar
  12. [12]
    Monnerat L R, Bianchini R. Efficiently adapting to sharing patterns in software DSMs. InProceedings of HPCA’98, Las Vegas, Nevada.Google Scholar

Copyright information

© Science Press, Beijing China and Allerton Press Inc. 2000

Authors and Affiliations

  1. 1.Institute of Computing TechnologyChinese Academy of SciencesBeijingP.R. China

Personalised recommendations