Architecture and performance of a new arithmetic unit for the computation of elementary functions

The design of a recursive arithmetic unit for evaluation of elementary functions is discussed. Two distinct classes of binary algorithms are implemented. One class is based on a generalization of the compensated CORDIC method. The other class, which replaces the linear CORDIC case, is based on the convergence transformations in connection with multiple bit encoding techniques. The proposed hardware solution provides a significant speed advantage over software calculations and more flexibility than special units designed only for a subset of these functions