High efficient logarithm convertor for graphics physics simulation

In this paper, we propose an efficient algorithm to piecewise linear approximation of logarithm for the possible application to graphics physics simulation. Compared to the traditional approximation of logarithm methods, our algorithm produce a maximum relative error flatten distribution in all intervals, the maximum relative error can be set according to our difference accuracy needs. Simulations of our methods have been conducted in Matlab to verify correctness. Besides, we further present the hardware implement. Comparison simulation showed that our algorithm is superior to state-of-art logarithm conversion for stimulation accuracy.