Advertisement

Comparison of Data Dependence Analysis Tests

  • Miia Viitanen
  • Timo D. Hämäläinen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3133)

Abstract

Comparison of six data dependence analysis algorithms is presented. The algorithms are purposed for a parallel compiler that is being developed for a configurable multi-DSP system PARNEU. The algorithms are implemented in SUIF compiler framework and benchmarked with Perfect Club, Audio Signal Processing, and Media Bench test problems. Proprietary PARNEU programs that have been manually parallelised are also included. Performance in terms of accuracy and execution time of the data dependence algorithms has been measured and compared. The results show that the Omega test is the most accurate but also takes most execution time for benchmarks with for-loop parallelism.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Banerjee, U.: Dependence Analysis, p. 213. Kluwer Academic Publishers, USA (1997)zbMATHGoogle Scholar
  2. 2.
    Banerjee, U., Eigenmann, R., Nicolau, A., Padua, D.A.: Automatic Program Parallelization. Proceedings of the IEEE 81(2), 211–243 (1993)CrossRefGoogle Scholar
  3. 3.
    Berry, M., et al.: The Perfect Club Benchmarks, Effective Performance Evaluation of Supercomputer, Technical Report UIUCSRD Rep. No. 827, University of Illinois Urbana-Champaign, p.48 (1989)Google Scholar
  4. 4.
    Embree, P.M.: C Language Algorithms for Real-Time DSP, p. 256. Prentice-Hall, Englewood Cliffs (1995)Google Scholar
  5. 5.
    Fenlason , Stallman .:GNU gprof, The GNU Profiler , Available at http://www.gnu.org/manual/gprof-2.9.1/html-chapter/gprof-toc.html
  6. 6.
    Gauthier, L., Yoo, S., Jerraya, A.: Automatic Generation and Targeting of Application- Specific Operating Systems and Embedded Systems Software. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 20(11), 1293–1301 (2001)CrossRefGoogle Scholar
  7. 7.
    Haapala, K., Kolinummi, P., Hämäläinen, T., Saarinen, J.: Parallel DSP Implementation of Wavelet Transform in Image Compression. In: IEEE International Symposium on Circuits and Systems, Geneva, Switzerland, May 28-31, vol. 5, pp. 89–92 (2000)Google Scholar
  8. 8.
    Hall, M., Anderson, J., Amarasinghe, S., Murphy, B., Liao, S.W., Bugnion, E., Lam, M.: Maximizing Multiprocessor Performance with the SUIF Compiler. IEEE Computer 29(12), 84–89 (1996)Google Scholar
  9. 9.
    Kolinummi, P., Hämäläinen, P., Hämäläinen, T., Saarinen, J.: PARNEU: General- Purpose Partial Tree Computer. Microprocessors and Microsystems 24(1), 23–42 (2000)CrossRefGoogle Scholar
  10. 10.
    Kolinummi, P., Särkijärvi, J., Hämäläinen, T., Saarinen, J.: Scalable Implementation of H.263 Video Encoder on a Parallel DSP System. In: IEEE International Symposium on Circuits and Systems, Geneva, Switzerland, May 2000, vol. 1, pp. 551–554 (2000)Google Scholar
  11. 11.
    Pugh, W.: A Practical Algorithm for Exact Array Dependence Analysis. Communications of the ACM 35(8), 102–114 (1992)CrossRefGoogle Scholar
  12. 12.
    Pugh, W.: The Omega Test: A Fast and Practical Integer Programming Algorithm for Dependence Analysis. In: Proceedings of the 1991 Confeqrence on Supercomputing, held in Albuquerque, NM , USA, pp. 4–13 (1991)Google Scholar
  13. 13.
    Ramasubramanian, N., Subramanian, R., Pande, S.: Automatic compilation of loops to exploit operator parallelism on configurable arithmetic logic units. IEEE Transactions on Parallel and Distributed Systems 13(1), 45–66q (2002)CrossRefGoogle Scholar
  14. 14.
    Sungdo, M., Byoungro, S., Hall, M.W.: Evaluating automatic parallelization in SUIF. IEEE Transactions on Parallel and Distributed Systems 11(1), 36–49 (2000)CrossRefGoogle Scholar
  15. 15.
    Thoen, P., Catthoor, F.: Modeling, Verification and Exploration of Task-Level Concurrency in Real-Time Embedded Systems, p. 438. Kluwer Academic Publishers, Dordrecht (2000)zbMATHGoogle Scholar
  16. 16.
    Viitanen, M., Kolinummi, P., Hämäläinen, T., Saarinen, J.: Scalable DSP Implementation of DCT-based Motion Estimation Algorithm. In: Proceedings of EUSIPCO 2000, the X European Signal Processing Conference, Tampere, Finland, September 4-8, vol. 1 (2000)Google Scholar
  17. 17.
    Wolfe, M., Tseng, C.: The Power Test for Data Dependence. IEEE Transactions on Parallel and Distributed Systems 3(5), 591–601 (1992)CrossRefGoogle Scholar
  18. 18.
    Wolfe, M.: High Performance Compiler for Parallel Computing, p. 570. Addison-Wesley, Reading (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Miia Viitanen
    • 1
  • Timo D. Hämäläinen
    • 1
  1. 1.Institute of Digital and Computer SystemsTampere University of TechnologyTampereFinland

Personalised recommendations