Abstract
This paper discusses low-error, high-speed evaluation of two elementary functions: square-root (which is required in IEEE-754 standard on computer arithmetic) and exponential (which is common in scientific calculations). The basis of the proposed implementations is piecewise-linear interpolation but with the constants chosen in a way that minimizes relative error. We show that by placing certain constraints on the errors at three points within each interpolation interval, relative errors are greatly reduced. The implementation-targets are large FPGAs that have in-built multipliers, adders, and distributed memory.
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
Muller, J.M.: Elementary Functions: Algorithms and Implementation. Birkhäuser, Boston (1997)
Omondi, A.R.: Computer Arithmetic Systems: Algorithms, Architecture, and Implementations. Prentice-Hall, UK (1994)
Mencer, O., Luk, W.: Parameterized high throughput function evaluation for FPGAs. Journal of VLSI Signal Processing 36, 17–25 (2004)
Pizer, S.M., Wallace, V.L.: To compute numerically: concepts and strategies. Little. Brown, Boston (1983)
Xilinx, Virtex-4 User Guide (2004)
Xilinx, XtremeDSP Design Considerations: User Guide (2004)
Ito, M., Takagi, N., Yajima, S.: Efficient Initial Approximation for Multiplicative Division and Square Root by a Multiplication with Operand Modification. IEEE Trans. Computers 46(4), 495–498 (1997)
Waterloo Maple Inc.: Maple 8 Programming Guide (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bajger, M., Omondi, A.R. (2006). Implementations of Square-Root and Exponential Functions for Large FPGAs. In: Jesshope, C., Egan, C. (eds) Advances in Computer Systems Architecture. ACSAC 2006. Lecture Notes in Computer Science, vol 4186. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11859802_3
Download citation
DOI: https://doi.org/10.1007/11859802_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40056-1
Online ISBN: 978-3-540-40058-5
eBook Packages: Computer ScienceComputer Science (R0)