论文信息 - Hardware implementation of the exponential function using Taylor series

Hardware implementation of the exponential function using Taylor series

This paper presents hardware implementations of Taylor series. The focus will be on the exponential function but the methodology is applicable on any unary function. Two different architectures are investigated, one, original, straight forward and one modified structure. The outcomes are higher performance, lower area, and lower power consumption for the modified architecture compared to the original.

Peter Nilsson | Rakesh Gangarajaiah | Erik Hertz | Ateeq Ur Rahman Shaik

[1] Jack E. Volder. The CORDIC Trigonometric Computing Technique , 1959, IRE Trans. Electron. Comput..

[2] Ping Tak Peter Tang,et al. Table-lookup algorithms for elementary functions and their error analysis , 1991, [1991] Proceedings 10th IEEE Symposium on Computer Arithmetic.

[3] Peter Nilsson,et al. Parabolic synthesis methodology implemented on the sine function , 2009, 2009 IEEE International Symposium on Circuits and Systems.

[4] Peter Nilsson. Architectures and Arithmetic for Low Static Power Consumption in Nanoscale CMOS , 2009, VLSI Design.

[5] Peter Nilsson. Approaching green electronics: Power efficient arithmetic in nano-scale CMOS , 2010, The 2010 International Conference on Green Circuits and Systems.

[6] Rakesh Gangarajaiah,et al. Hardware Implementation of the Logarithm Function , 2013 .

[7] Erik Hertz,et al. A Methodology for Parabolic Synthesis , 2010 .

[8] G. Muntingh. Topics in Polynomial Interpolation Theory , 2011 .

[9] Tomos Wyn Roberts. Non-oscillatory interpolation for the Semi-Lagrangian scheme , 2009 .