Guided Prefetching Based on Runtime Access Patterns

  • Jie Tao
  • Georges Kneip
  • Wolfgang Karl
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5103)


Cache prefetching is a basic technique for removing cache misses and the resulting access penalty. This work proposes a kind of guided prefetching which uses the access pattern of an application to prohibit from loading data which are not required. The access pattern is achieved with a data analyzer capable of discovering the affinity and regularity of data accesses. Initial results depict a performance improvement of up to 20%.


Discrete Wavelet Transform Access Pattern Memory Reference Prefetching Instruction Prefetched Data 
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.
    Baer, J.-L., Chen, T.-F.: Effective Hardware-Based Data Prefetching for High-Performance Processors. IEEE Transactions on Computers 44(5), 609–623 (1995)CrossRefzbMATHGoogle Scholar
  2. 2.
    Berg, S.G.: Cache prefetching. Technical Report UW-CSE 02-02-04, Department of Computer Science & Engineering, University of Washington (February 2004)Google Scholar
  3. 3.
    Chaver, D., Tenllado, C., Pinuel, L., Prieto, M., Tirado, F.: 2-D Wavelet Transform Enhancement on General-Purpose Microprocessors: Memory Hierarchy and SIMD Parallelism Exploitation. In: Proc. Int. Conf. on the High Performance Computing (December 2002)Google Scholar
  4. 4.
    Inagaki, T., et al.: Stride Prefetching by Dynamically Inspecting Objects. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 269–277 (June 2003)Google Scholar
  5. 5.
    Mohan, T., et al.: Identifying and Exploiting Spatial Regularity in Data Memory References. In: Supercomputing 2003 (November 2003)Google Scholar
  6. 6.
    Joseph, D., Grunwald, D.: Prefetching using markov predictors. IEEE Transactions on Computers 48(2), 121–133 (1999)CrossRefGoogle Scholar
  7. 7.
    Jouppi, N.P.: Improving Direc-mapped Cache Performance by the Addition of a Small Fully-associative Cache and Prefetch Buffers. In: Proceedings of the 17th Annual International Symposium on Computer Architectures, May 1990, pp. 364–373 (1990)Google Scholar
  8. 8.
    Lin, W., Reinhardt, S., Burger, D.: Reducing DRAM Latencies with an Integrated Memory Hierarchy Design. In: Proceedings of the 7th International symposium on High-Performance Computer Architecture, January 2001, pp. 301–312 (2001)Google Scholar
  9. 9.
    Luk, C., Mowry, T.C.: Compiler-Based Prefetching for Recursive Data Structures. In: Proceedings of the Seventh International Conference on Architectural Support for Programming Languages and Operating Systems, October 1996, pp. 222–233 (1996)Google Scholar
  10. 10.
    Marathe, J., Mueller, F., de Supinski, B.: A Hybrid Hardware/Software Approach to Efficiently Determine Cache Coherence Bottlenecks. In: Proceedings of the International Conference on Supercomputing, June 2005, pp. 21–30 (2005)Google Scholar
  11. 11.
    Nguyen, A.-T., Michael, M., Sharma, A., Torrellas, J.: The augmint multiprocessor simulation toolkit for intel x86 architectures. In: Proceedings of 1996 International Conference on Computer Design (October 1996)Google Scholar
  12. 12.
    Rigoutsos, I., Floratos, A.: Combinatorial Pattern Discovery in Biological Sequences: the TEIRESIAS Algorithm. Bioinformatics 14(1), 55–67 (1998)CrossRefGoogle Scholar
  13. 13.
    Smith, J.E.: Decoubled Access/Execute Computer Architectures. In: Proceedings of the 9th Annual International Symposium on Computer Architectures, July 1982, pp. 112–119 (1982)Google Scholar
  14. 14.
    Tao, J., Schloissnig, S., Karl, W.: Analysis of the Spatial and Temporal Locality in Data Accesses. In: Alexandrov, V.N., van Albada, G.D., Sloot, P.M.A., Dongarra, J. (eds.) ICCS 2006. LNCS, vol. 3992, pp. 502–509. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Jie Tao
    • 1
  • Georges Kneip
    • 2
  • Wolfgang Karl
    • 2
  1. 1.Steinbuch Center for Computing, Forschungszentrum KarlsruheKarlsruhe Institute of TechnologyGermany
  2. 2.Institut für Technische InformatikUniversität Karlsruhe (TH), Karlsruhe Institute of TechnologyGermany

Personalised recommendations