Advertisement

Multiple-Precision Residue-Based Arithmetic Library for Parallel CPU-GPU Architectures: Data Types and Features

  • Konstantin IsupovEmail author
  • Alexander Kuvaev
  • Mikhail Popov
  • Anton Zaviyalov
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10421)

Abstract

In this paper a new software library for multiple-precision (integer and floating-point) and extended-range computations is considered. The library is targeted at heterogeneous CPU-GPU architectures. The use of residue number system (RNS), enabling effective parallelization of arithmetic operations, lies in the basis of library multiple-precision modules. The paper deals with the supported number formats and the library features. An algorithm for the selection of an RNS moduli set for a given precision of computations are also presented.

Keywords

Multiple-precision computations Extended-range computations Parallel processing GPGPU Residue number system 

Notes

Acknowledgement

This work is supported by the Russian Foundation for Basic Research (project no. 16-37-60003 mol_a_dk) and FASIE UMNIK grant.

References

  1. 1.
    Albicocco, P., Cardarilli, G., Nannarelli, A., Re, M.: Twenty years of research on RNS for DSP: lessons learned and future perspectives. In: Proceedings of 14th International Symposium on Integrated Circuits (ISIC), Singapore, pp. 436–439, December 2014Google Scholar
  2. 2.
    Brent, R., Zimmermann, P.: Modern Computer Arithmetic. Cambridge University Press, New York (2010)CrossRefzbMATHGoogle Scholar
  3. 3.
    Brzeziński, D.W., Ostalczyk, P.: Numerical calculations accuracy comparison of the inverse Laplace transform algorithms for solutions of fractional order differential equations. Nonlinear Dyn. 84(1), 65–77 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Chang, C.H., Low, J.Y.S.: Simple, fast, and exact RNS scaler for the three-moduli set \(\{2^{n} - 1, 2^{n}, 2^{n} + 1\}\). IEEE Trans. Circ. Syst. I Regul. Pap. 58(11), 2686–2697 (2011)CrossRefGoogle Scholar
  5. 5.
    Defour, D., de Dinechin, F.: Software carry-safe for fast multiple-precision algorithms. In: Proceedings of 1st International Congress of Mathematical Software, Beijing, China, pp. 29–39, August 2002Google Scholar
  6. 6.
    Esmaeildoust, M., Schinianakis, D., Javashi, H., Stouraitis, T., Navi, K.: Efficient RNS implementation of elliptic curve point multiplication over \(\rm {GF}(p)\). IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 21(8), 1545–1549 (2013)CrossRefGoogle Scholar
  7. 7.
    Hauser, J.R.: Handling floating-point exceptions in numeric programs. ACM Trans. Program. Lang. Syst. 18(2), 139–174 (1996)CrossRefGoogle Scholar
  8. 8.
    He, K., Zhou, X., Lin, Q.: High accuracy complete elliptic integrals for solving the Hertzian elliptical contact problems. Comput. Math. Appl. 73(1), 122–128 (2017)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Hemenway, B., Lu, S., Ostrovsky, R., Welser IV, W.: High-precision secure computation of satellite collision probabilities. In: Zikas, V., De Prisco, R. (eds.) SCN 2016. LNCS, vol. 9841, pp. 169–187. Springer, Cham (2016). doi: 10.1007/978-3-319-44618-9_9 Google Scholar
  10. 10.
    Isupov, K., Knyazkov, V.: Non-modular Computations in Residue Number Systems Using Interval Floating-Point Characteristics. Deposited in VINITI, No. 61-B2015 (2015). (in Russian)Google Scholar
  11. 11.
    Isupov, K., Knyazkov, V.: Parallel multiple-precision arithmetic based on residue number system. Program Syst. Theor. Appl. 7(1), 61–97 (2016). (in Russian)Google Scholar
  12. 12.
    Isupov, K., Knyazkov, V.: RNS-based data representation for handling multiple-precision integers on parallel architectures. In: Proceedings of the 2016 International Conference on Engineering and Telecommunication (EnT 2016), Moscow, pp. 76–79, November 2016Google Scholar
  13. 13.
    Isupov, K., Knyazkov, V., Kuvaev, A., Popov, M.: Development of high-precision arithmetic package for supercomputers with graphics processing units. Programmnaya Ingeneria 7(9), 387–394 (2016). (in Russian)CrossRefGoogle Scholar
  14. 14.
    Isupov, K., Knyazkov, V., Kuvaev, A., Popov, M.: Parallel computation of normalized legendre polynomials using graphics processors. In: Voevodin, V. (ed.) Russian Supercomputing Days 2016. CCIS, vol. 687. Springer International Publishing, Cham (2017)Google Scholar
  15. 15.
    Mohan, P.V.A.: Residue Number Systems: Theory and Applications. Birkhäuser, Basel (2016)CrossRefzbMATHGoogle Scholar
  16. 16.
    Szabo, N.S., Tanaka, R.I.: Residue Arithmetic and its Application to Computer Technology. McGraw-Hill, New York (1967)zbMATHGoogle Scholar
  17. 17.
    Tomczak, T.: Fast sign detection for RNS \(\{2^{n} - 1, 2^{n}, 2^{n} + 1\}\). IEEE Trans. Circ. Syst. I Regul. Pap. 55(6), 1502–1511 (2008)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Konstantin Isupov
    • 1
    Email author
  • Alexander Kuvaev
    • 1
  • Mikhail Popov
    • 1
  • Anton Zaviyalov
    • 1
  1. 1.Department of Electronic Computing MachinesVyatka State UniversityKirovRussia

Personalised recommendations