A Tool for Unbiased Comparison between Logarithmic and Floating-point Arithmetic

Article

Abstract

For applications requiring a large dynamic, real numbers may be represented either in floating-point, or in the logarithm number system (LNS). Which system is best for a given application is difficult to know in advance, because the cost and performance of LNS operators depend on the target accuracy in a highly non linear way. Therefore, a comparison of the pros and cons of both number systems in terms of cost, performance and overall accuracy is only relevant on a per-application basis. To make such a comparison possible, two concurrent libraries of parameterized arithmetic operators, targeting recent field-programmable gate arrays, are presented. They are unbiased in the sense that they strive to reflect the state-of-the-art for both number systems. These libraries are freely available at http://www.ens-lyon.fr/LIP/Arenaire/.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    ANSI/IEEE, Standard 754-1985 for Binary Floating-point Arithmetic (also IEC 60559), 1985.Google Scholar
  2. 2.
    M. Arnold, T. Bailey, J. Cowles, and M. Winkel, “Arithmetic Co-transformations in the Real and Complex Logarithmic Number Systems,” IEEE Trans. Comput., vol. 47, no. 7, (July) 1998, pp. 777–786.MathSciNetCrossRefGoogle Scholar
  3. 3.
    P. Belanović and M. Leeser, “A Library of Parameterized Floating-point Modules and Their Use,” in Field Programmable Logic and Applications (LNCS, vol. 2438), Springer, (Sept.) 2002, pp. 657–666.Google Scholar
  4. 4.
    J.-L. Beuchat and A. Tisserand, “Small Multiplier-based Multiplication and Division Operators for Virtex-II Devices,” in Field-programmable Logic and Applications (LNCS, vol. 2438), Springer, (Sept.) 2002.Google Scholar
  5. 5.
    J. N. Coleman and E. I. Chester, “Arithmetic on the European Logarithmic Microprocessor,” IEEE Trans. Comput., vol. 49, no. 7, (July) 2000, pp. 702–715.CrossRefGoogle Scholar
  6. 6.
    F. de Dinechin and A. Tisserand, “Some Improvements on Multipartite Table Methods,” in 15th IEEE Symposium on Computer Arithmetic, N. Burgess and L. Ciminiera (Eds.), June 2001, pp. 128–135. (Updated version of LIP research report 2000-38.)Google Scholar
  7. 7.
    M. deLorimier and A. DeHon, “Floating-point Sparse Matrix–vector Multiply for FPGAs,” in ACM/SIGDA Field-programmable Gate Arrays, ACM Press, 2005, pp. 75–85.Google Scholar
  8. 8.
    J. Detrey and F. de Dinechin, “A VHDL Library of LNS Operators,” in 37th Asilomar Conference on Signals, Systems and Computers, Oct. 2003.Google Scholar
  9. 9.
    J. Detrey and F. de Dinechin, “Second Order Function Approximation Using a Single Multiplication on FPGAs,” in 14th Intl Conference on Field-Programmable Logic and Applications (LNCS, vol. 3203), Springer, Aug. 2004, pp. 221–230.Google Scholar
  10. 10.
    J. Dido, N. Geraudie, L. Loiseau, O. Payeur, Y. Savaria, and D. Poirier, “A Flexible Floating-point Format for Optimizing Data-paths and Operators in FPGA Based DSPs,” in ACM/SIGDA Field-programmable Gate Arrays, (Feb.) 2002, pp. 50–55.Google Scholar
  11. 11.
    C. Doss and R. Riley, “FPGA-based Implementation of a Robust IEEE-754 Exponential Unit,” in FPGAs for Custom Computing Machines, IEEE, 2004.Google Scholar
  12. 12.
    Y. Dou, S. Vassiliadis, G. K. Kuzmanov, and G. N. Gaydadjiev, “64-bit Floating-point FPGA Matrix Multiplication,” in ACM/SIGDA Field-programmable Gate Arrays, ACM Press, 2005.Google Scholar
  13. 13.
    M. D. Ercegovac and T. Lang, Division and Square Root: Digit-recurrence Algorithms and Implementations, Kluwer, Boston, MA, 1994.MATHGoogle Scholar
  14. 14.
    M. D. Ercegovac and T. Lang, Digital Arithmetic, Morgan Kaufmann, San Mateo, CA, 2003.Google Scholar
  15. 15.
    M. J. Flynn and S. F. Oberman, Advanced Computer Arithmetic Design, Wiley-Interscience, New York, 2001.Google Scholar
  16. 16.
    A. A. Gaffar, W. Luk, P. Y. K. Cheung, N. Shirazi, and J. Hwang, “Automating Customisation of Floating-point Designs,” in Field Programmable Logic and Applications(LNCS, vol. 2438), Springer, (Sept.) 2002, pp. 523–533.Google Scholar
  17. 17.
    D. Goldberg, “What Every Computer Scientist Should Know about Floating-point Arithmetic,” ACM Comput. Surv., vol. 23, no. 1, (Mar.) 1991, pp. 5–47.CrossRefGoogle Scholar
  18. 18.
    M. Haselman, M. Beauchamp, K. Underwood, and K. S. Hemmert, “A Comparison of Floating-point and Logarithmic Number Systems for FPGAs,” in FPGAs for Custom Computing Machines, 2005.Google Scholar
  19. 19.
    B. Lee and N. Burgess, “Parameterisable Floating-point Operators on FPGAs,” in 36th Asilomar Conference on Signals, Systems, and Computers, 2002, pp. 1064–1068.Google Scholar
  20. 20.
    B. Lee and N. Burgess, “A Dual-path Logarithmic Number System Addition/Subtraction Scheme for FPGA,” in Field-programmable Logic and Applications, (Sept.) 2003, Lisbon.Google Scholar
  21. 21.
    D. M. Lewis, “An Architecture for Addition and Subtraction of Long Word Length Numbers in the Logarithmic Number System,” IEEE Trans. Comput., vol. 39, no. 11, (Nov.) 1990.Google Scholar
  22. 22.
    G. Lienhart, A. Kugel, and R. Männer, “Using Floating-point Arithmetic on FPGAs to Accelerate Scientific N-body Simulations,” in FPGAs for Custom Computing Machines, IEEE, 2002.Google Scholar
  23. 23.
    R. Matoušek, M. Tichý, Z. Pohl, J. Kadlec, C. Softley, and N. Coleman, “Logarithmic Number System and Floating-point Arithmetics on FPGA,” in Field-programmable Logic and Applications, Montpellier, (Sept.) 2002, pp. 627–636.Google Scholar
  24. 24.
    F. Ortiz, J. Humphrey, J. Durbano, and D. Prather, “A Study on the Design of Floating-point Functions in FPGAs,” in Field Programmable Logic and Applications (LNCS, vol. 2778), Springer, (Sept.) 2003, pp. 1131–1135.Google Scholar
  25. 25.
    V. Paliouras and T. Stouraitis, “A Novel Algorithm for Accurate Logarithmic Number System Subtraction,” in International Symposium on Circuits and Systems, volume 4, IEEE, (May) 1996, pp. 268–271.Google Scholar
  26. 26.
    E. Roesler and B. Nelson, “Novel Optimizations for Hardware Floating-point Units in a Modern FPGA Architecture,” in Field Programmable Logic and Applications (LNCS, vol. 2438) Springer, (Sept.) 2002, pp. 637–646.Google Scholar
  27. 27.
    F. J. Taylor, R. Gill, J. Joseph, and J. Radke, “A 20 Bit Logarithmic Number System Processor,” IEEE Trans. Comput., vol. 37, no. 2, (Feb.) 1988Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Laboratoire de l’Informatique du ParallélismeÉcole Normale Supérieure de LyonLyon cedex 07France

Personalised recommendations