A comparison of automatic parallelizing compiler and improvements by compiler directives

  • Kazuhiro Kusano
  • Mitsuhisa Sato
III System Software
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1615)


This paper describes a performance comparison of parallelization using a commerical parallelizing C compiler. Parallelizing compilers are effective to save time and effort to parallelize a sequential program. Recently, C is commonly used in various areas of application on workstations and PCs. We take two compilers, the SUNWspro C compiler and the Apogee with KAP/C on the SparcCenter 1000, and examine automatic parallelization and improvements by compiler directives. Although some programs achieve a good increase in speed, the compiler directives are very important to tell the compiler to how recognize parallelizable parts. This is because automatic parallelization cannot analyze all the data dependence in the program. However, the directives are sometimes not effective, because compilers treat directives as hints for analysis to achieve parallelization. Directives to overcome such limitations are important to increase the efficiency of the parallelizing compiler.


parallelization compiler directive benchmark OpenMP 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    P. Banerjee, J. A. Chandy, M. Gupta, E. W. Hodges IV, J. G. Holm, A. Lain, D. J. Palermo, S. Ramaswamy, and E. Su., “The Paradigm Compiler for Distributed-Memory Multicomputers”, IEEE Computer, Vol. 28, No. 10, pp. 37–47, 1995.Google Scholar
  2. 2.
    W. Blume, R. Doallo, R. Eigenmann, J. Grout, J. Hoeflinger, T. Lawrence, J. Lee, D. Padua, Y. Paek, B. Pottenger, L. Rauchwerger, and P. Tu, “Parallel Programming with Polaris”, IEEE Computer, Vol. 29, No. 12, pp. 78–82, 1996.Google Scholar
  3. 3.
    M. W. Hall, J. M. Anderson, S. P. Amarasinghe, B. R. Murphy, S.-W. Liao, E. Bugnion and M. S. Lam, “Maximizing Multiprocessor Performance with the Suif Compiler”, IEEE Computer, Vol. 29, No. 12, pp. 84–89, 1996.Google Scholar
  4. 4.
    J.-Y. Berthou and L. Colombet, “Which approach to parallelizing scientific codes —That is the question”, Parallel Computing, 23, 165–179, 1997.CrossRefGoogle Scholar
  5. 5.
    M. Frumkin, M. Hribar, H. Jin, A. Waheed and J. Yan, “A Comparison of Automatic Parallelization Tools/Compilers on the SGI Origin2000”, SC'98, Orlando, FL, 1998.Google Scholar
  6. 6.
    C. S. Ierotheou, S. P. Johnson, M. Cross and P. F. Leggett, “Computer aided parallelisation tools(CAPTools)-conceptual overview and performance on the parallelisation of structured mesh codes”, Parallel Computing, Vol. 22, No. 2, pp. 163–195, 1996.CrossRefGoogle Scholar
  7. 7.
    OpenMP Consortium, “OpenMP C and C++ Application Program Interface Ver 1.0”, Oct, 1998.Google Scholar
  8. 8.
    C. Koelbel, D. Loveman, R. Schreiber, G. Steele Jr. and M. Zosel, “The High Performance Fortran handbook”, The MIT Press, Cambridge, MA, USA, 1994.Google Scholar
  9. 9.
    V. Adve, G. Jin, J. Mellor-Crummey and Q. Yi, “High Performance Fortran Compilation Techniques for Parallelizing Scientific Codes”, SC'98, Orlando, FL, 1998.Google Scholar
  10. 10.
    B. Chapman and P. Mehrotra, “OpenMP and HPF: Integrating Two Paradigms”, Euro-Par'98, 650–658, 1998.Google Scholar
  11. 11.
    Standard Performance Evaluation Corporation, http://www.specbenchorg/Google Scholar
  12. 12.
    J. J. Dongarra, “The Complete Linpack Report”, Technical report, U. Tennesse, 1994.Google Scholar
  13. 13.
    Sun Microsystems, Inc., “C User's Guide”, 1995.Google Scholar
  14. 14.
    Sun Microsystems, Inc., “Sun MP C Compiler Technical White Paper”, 1996.Google Scholar
  15. 15.
    Apogee Software Inc., “User's Manual for Apogee compilers Rel. 4.0”, 1996.Google Scholar
  16. 16.
    Kuck and Associates, Inc., “KAP for Apogee-C User's Guide Ver. 3.1”, 1995.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Kazuhiro Kusano
    • 1
  • Mitsuhisa Sato
    • 1
  1. 1.RWCP Tsukuba Research CenterReal World Computing PartnershipTsukuba-shi, IbarakiJapan

Personalised recommendations