Abstract
This paper presents a hardware approach to performing accurate floating point addition and multiplication using the idea of error-free transformations. Specialized iterative algorithms are implemented for computing arbitrarily accurate sums and dot products. The results of a Xilinx Virtex 6 implementation are given, area and performance are compared against standard floating point units and it is shown that the timeĆarea product can be improved by a factor of 4 and 6 over software error-free addition and multiplication. Furthermore, it is illustrated that a number of area and performance trade-offs can be made when calculating vector sums and dot products.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
VFLOAT, http://www.ece.neu.edu/groups/rpl/projects/floatingpoint/
Flopoco project, http://www.ens-lyon.fr/LIP/Arenaire/Ware/FloPoCo/
Muller, J., Brisebarre, N., de Dinechin, F., Jeannerod, C.P., Vincent, L., Melquiond, G., Revol, N., StehlƩ, D., Torres, S.: Handbook of Floating-Point Arithmetic. Springer, Heidelberg (2010)
Kulisch, U.W.: Circuitry for generating scalar products and sums of floating-point numbers with maximum accuracy. United States Patent 4622650 (1986)
Kulisch, U.W.: Advanced Arithmetic for the Digital Computer: Design of Arithmetic Units. Springer, New York (2002)
Dekker, T.J.: A floating-point technique for extending the available precision. Numerische MathematikĀ 18, 224ā242 (1971); 10.1007/BF01397083
Shewchuk, J.R.: Adaptive precision fp arithmetic and fast robust geometric predicates. Discrete and Computational GeometryĀ 18 (1996)
Rump, S.M.: Error-free transformations and ill-conditioned problems. In: International Workshop on Verified Computations and Related Topics (2009)
MĆøller, O.: Quasi double-precision in floating point addition. BIT Numerical MathematicsĀ 5, 37ā50 (1965); 10.1007/BF01975722
Knuth, D.: The Art of Computer Programming: Seminumerical Algorithms, vol.Ā 2. Addison Wesley, Reading (1969)
Kahan, W.: Pracniques: further remarks on reducing truncation errors. Commun. ACMĀ 8(1), 40 (1965)
Dieter, W.R., Kaveti, A., Dietz, H.G.: Low-cost microarchitectural support for improved floating-point accuracy. IEEE Comput. Archit. Lett.Ā 6 (2007)
Ogita, T., Rump, S.M., Oishi, S.: Accurate sum and dot product. SIAM J. Sci. Comput.Ā 26(6), 1955ā1988 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Manoukian, M.V., Constantinides, G.A. (2011). Accurate Floating Point Arithmetic through Hardware Error-Free Transformations. In: Koch, A., Krishnamurthy, R., McAllister, J., Woods, R., El-Ghazawi, T. (eds) Reconfigurable Computing: Architectures, Tools and Applications. ARC 2011. Lecture Notes in Computer Science, vol 6578. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19475-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-19475-7_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19474-0
Online ISBN: 978-3-642-19475-7
eBook Packages: Computer ScienceComputer Science (R0)