A division architecture combining Newton-Raphson approximations and direct methods iterations

The authors consider the possibility of designing architectures which combine in the best possible way the convergence with the square advantages of the Newton-Raphson method with the precision characteristics of the digit-by-digit algorithms so as to obtain units which satisfy the IEEE 754 floating point standard requirements. This is a general method which can be extended with simple and minor changes also to square root. Attention is focused on a possible implementation of this design methodology for division. The evaluation shows that the proposed unit offers an alternative architecture for division which provides interesting performances