Speculation Meets Checkpointing

  • Arkadiusz Danilecki
  • Michał Szychowiak
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3991)


This paper describes a checkpointing mechanism destined for Distributed Shared Memory (DSM) systems with speculative prefetching. Speculation is a general technique involving prediction of the future of a computation, namely accesses to shared objects unavailable on the accessing node (read faults). Thanks to such predictions objects can be fetched before the actual access operation is performed, resulting, at least potentially, in considerable performance improvement. The proposed mechanism is based on independent incremental checkpointing integrated with a coherence protocol introducing little overhead. It ensures the consistency of checkpoints, allowing fast recovery from failures.


Version Number Shared Object Distribute Share Memory Checkpointing Mechanism Distribute Share Memory System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Bianchini, R., Pinto, R., Amorim, C.L.: Data Prefetching for Software DSMs. In: Int. Conf. on Supercomputing, Melbourne, Australia (1998)Google Scholar
  2. 2.
    Brzeziski, J., Szychowiak, M.: Replication of Checkpoints in Recoverable DSM Systems. In: 21st Int. Conf. on Parallel and Distributed Computing and Networks PDCN 2003, Innsbruck, Austria (2003)Google Scholar
  3. 3.
    Danilecki, A., Szychowiak, M.: Checkpointing Speculative DSM Systems. Technical Report RA-021/05, Institute of Computing Science, Poznań University of Technology, Poznań, Poland (2005)Google Scholar
  4. 4.
    Lai, A.-C., Babak Falsafi, B.: Memory Sharing Predictor: The Key to a Speculative Coherent DSM. In: 26th Int. Symp. on Computer Architecture (ISCA 26), Atlanta, Georgia, pp. 172–183 (1999)Google Scholar
  5. 5.
    Lai, A.-C., Babak Falsafi, B.: Selective, Accurate, and Timely Self-Invalidation Using Last-Touch Prediction. In: 27th Int. Symp. on Computer Architecture (ISCA 27), Vancouver, BC, Canada, pp. 139–148 (2000)Google Scholar
  6. 6.
    Park, T., Yeom, H.Y.: A Low Overhead Logging Scheme for Fast Recovery in Distributed Shared Memory Systems. Journal of Supercomputing 15(3), 295–320 (2002)CrossRefGoogle Scholar
  7. 7.
    Rajwar, R., Kagi, A., Goodman, J.R.: Inferential Queueing and Speculative Push. Int. Journal of Parallel Programming (IJPP) 32(3), 273–284 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Arkadiusz Danilecki
    • 1
  • Michał Szychowiak
    • 1
  1. 1.Institute of Computing SciencePoznań University of TechnologyPoznańPoland

Personalised recommendations