Multimedia Tools and Applications

, Volume 20, Issue 2, pp 159–178 | Cite as

Improving Data Prefetching Efficacy in Multimedia Applications

  • Rita Cucchiara
  • Andrea Prati
  • Massimo Piccardi


The workload of multimedia applications has a strong impact on cache memory performance, since the locality of memory references embedded in multimedia programs differs from that of traditional programs. In many cases, standard cache memory organization achieves poorer performance when used for multimedia. A widely-explored approach to improve cache performance is hardware prefetching, which allows the pre-loading of data in the cache before they are referenced. However, existing hardware prefetching approaches are unable to exploit the potential improvement in performance, since they are not tailored to multimedia locality. In this paper we propose novel effective approaches to hardware prefetching to be used in image processing programs for multimedia. Experimental results are reported for a suite of multimedia image processing programs including MPEG-2 decoding and encoding, convolution, thresholding, and edge chain coding.

cache performance hardware prefetching techniques multimedia benchmark MPEG decode image processing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    P. Baglietto, M. Maresca, M. Migliardi, and N. Zingirian, “Image processing on high performance RISC systems,” Proceedings of the IEEE, Vol. 84, No. 7, pp. 917–925, 1996.Google Scholar
  2. 2.
    T.F. Chen and J.L. Baer, “Effective hardware-based data prefetching for high-performance processors.” IEEE Transactions on Computers, Vol. 44, No. 5, pp. 609–623, 1995.Google Scholar
  3. 3.
    T.F. Chen and J.L. Baer, “A performance study of hardware and software data prefetching schemes,” in Proc. of the 21th Intl. Symp. on Computer Architecture (ISCA), pp. 223–232, 1996.Google Scholar
  4. 4.
    L. Chiariglione, “Impact of multimedia standards on multimedia industry,” Proceedings of the IEEE, Vol. 86, No. 16, pp. 1222–1227, 1998.Google Scholar
  5. 5.
    Coding of audio-visual objects—Part 2: Visual. ISO/IEC DIS 14496-2 Information technology.Google Scholar
  6. 6.
    R. Cucchiara and M. Piccardi, “Exploiting image processing locality in cache pre-fetching,” in Proc. of the 5th Intl. Conf. on High Performance Computing (HiPC), pp. 466–472, 1998.Google Scholar
  7. 7.
    R. Cucchiara, M. Piccardi, and A. Prati, “Exploiting cache in multimedia,” in Proc. of IEEE Intl. Conf. on Multimedia Computing and Systems (ICMCS), Vol. 1, pp. 345–350, 1999.Google Scholar
  8. 8.
    R. Cucchiara, M. Piccardi, and A. Prati, Temporal Analysis of Cache Prefetching Strategies for Multimedia Applications. Tech. Rep.—Dipartimento di Ingegneria, Università di Ferrara, 2000.Google Scholar
  9. 9.
    K. Diefendorff and P.K. Dubey, “How multimedia workloads will change processor design,” IEEE Computer, pp. 43–45, 1997.Google Scholar
  10. 10.
    R.J. Eickemeyer and S. Vassiliadis, “A load instruction unit for pipelined processor,” IBM Journal of Research and Development, Vol. 37, pp. 547–564, 1993.Google Scholar
  11. 11.
    D. Gall, “MPEG: A video compression standard for multimedia application,” Communications of the ACM, Vol. 34, No. 4, pp. 46–58, 1991.Google Scholar
  12. 12.
    A. Gonzales, C. Aliagas, and M. Valero, “A data cache with multiple caching strategies tuned to different types of locality,” in Proc. of ACM Intl. Conf. on Supercomputing, 1995, pp. 338–347.Google Scholar
  13. 13.
    J. Hennessy and D. Patterson, Computer Architecture: A Quantitative Approach. Morgan Kaufmann, 1990.Google Scholar
  14. 14.
    ACME Cache Simulator. http: //ãcme/acs.html.Google Scholar
  15. 15.
    G. Irlam, Spa. Personal Communication, 1992.Google Scholar
  16. 16.
    D. Joseph and D. Grunwald, “Prefetching using markov predictors,” IEEE Transactions on Computers, Special Issue on Cache Memory and Related Problems, Vol. 48, No. 2, pp. 121–134, 1999.Google Scholar
  17. 17.
    N. Jouppi, “Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffers,” in Proc. of 17th Intl. Symp. on Computer Architecture (ISCA), 1990, pp. 364–373.Google Scholar
  18. 18.
    T. Kanedo and M. Okudaira, “Encoding of arbitrary curves based on the chain code representation,” IEEE Transactions on Communications, COM-33, pp. 697–707, 1985.Google Scholar
  19. 19.
    A.K. Katsaggelos, P.K. Lisimachos, F.W. Meier, J. Ostermann, and G.M. Schuster, “Mpeg-4 and ratedistortion-based shape-coding techniques,” Proceedings of the IEEE, Vol. 86, No. 6, pp. 1126–1154, 1998.Google Scholar
  20. 20.
    I. Kuroda and T. Niscitani, “Multimedia processors,” Proceedings of the IEEE, Vol. 86, No. 6, pp. 1203–1221, 1998.Google Scholar
  21. 21.
    C. Lee, M. Potkonjak, and W. Mangione-Smith, “Mediabench: A tool for evaluating multimedia and communications systems,” in Proc. of MICRO30, pp. 330–337, 1997.Google Scholar
  22. 22.
    V. Milutinovic, B. Markovic, M. Tomasevic, and M. Tremblay, “The split temporal/spatial cache: Initial performance analysis,” in Proc. of the SCIzzL-5, Santa Clara, CA, USA, pp. 72–78, 1996.Google Scholar
  23. 23.
    A.J. Smith, “Cache memories,” ACM Computing Surveys, Vol. 14, No. 3, pp. 473–530, 1982.Google Scholar
  24. 24.
    P. Soderquist and M. Lesser, “Memory traffic and data cache behavior of an mpeg-2 software decoder,” preprint for ICCD '97, 1997.Google Scholar
  25. 25.
    J. Tse and A.J. Smith, “Cpu cache prefetching: timing evaluation of hardware implementation,” IEEE Computer, Vol. 47, No. 5, pp. 509–526, 1995.Google Scholar
  26. 26.
    Z. Wu and W. Wolf, “Study of cache system in video signal processors,” in Proc. IEEE Workshop on Signal Processing Systems (SiPS), pp. 23–32, 1998.Google Scholar
  27. 27.
    D. Zucker, M.J. Flynn, and R. Lee, “A comparison of hardware prefetching techniques for multimedia benchmark,” in Proc. of IEEE Multimedia 96, pp. 236–244, 1996.Google Scholar

Copyright information

© Kluwer Academic Publishers 2003

Authors and Affiliations

  • Rita Cucchiara
  • Andrea Prati
  • Massimo Piccardi

There are no affiliations available

Personalised recommendations