Non-linear partitioning for decimal logarithm approximation

This work presents a systematic approach for the implementation of decimal logarithmic converter. In this approach the decimal logarithm is divided into different regions and linear approximation is applied to each of them. The novelty of this algorithm lies in the selection of regions for linear approximation. The regions are selected in such a way that only a minimum number of coefficients is to be stored. All the other coefficients for linear approximation can be generated from the stored coefficients. A 10-region linear approximation method is explained in detail. Simulation results show that this method achieves a maximum positive and negative error of 0.0044 and 0.0015 respectively. It can also be applied to a 20-region approximation, which has a maximum positive and negative error of 0.000811 and 0.000948 respectively.