On-line high-radix exponential with selection by rounding

An on-line high-radix algorithm for computing the exponential function (e/sup x/) with arbitrary precision n is presented. Selection by rounding and a redundant digit-set for the digits e/sub j/ are used, with selection by table in the first iteration to guarantee the convergence of the algorithm, and the on-line delay is /spl delta/ = 2 cycles. A sequential architecture implementing the algorithm is proposed, and the execution times and hardware requirements are estimated for 32-bit and 64-bit computations for several radix values. An analysis of the tradeoff between area and speed shows that the most efficient implementations are obtained for radix values from r = 32 to 256, depending on the precision.

[1]  Joseph R. Cavallaro,et al.  On-line arithmetic for detection in digital communication receivers , 2001, Proceedings 15th IEEE Symposium on Computer Arithmetic. ARITH-15 2001.

[2]  Arnaud Tisserand,et al.  On-line arithmetic-based reprogrammable hardware implementation of multilayer perceptron back-propagation , 1996, Proceedings of Fifth International Conference on Microelectronics for Neural Networks.

[3]  Javier D. Bruguera,et al.  High-radix logarithm with selection by rounding , 2002, Proceedings IEEE International Conference on Application- Specific Systems, Architectures, and Processors.

[4]  Weng-Fai Wong,et al.  Fast Hardware-Based Algorithms for Elementary Function Computations Using Rectangular Multipliers , 1994, IEEE Trans. Computers.

[5]  Jean-Michel Muller,et al.  New algorithms for on-line computation of elementary functions , 1991, Optics & Photonics.

[6]  Javier D. Bruguera,et al.  2-D DCT using on-line arithmetic , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.