Implementation of Non Restoring Interval Divider unit

Interval arithmetic provides a general methodology for bounding errors. Interval arithmetic provides reliability and accuracy by computing a lower and upper bound in which each result is guaranteed to reside. An interval’s width ensures the maximum possible error. The approaches consisted on developing hardware support for interval arithmetic division unit by incorporating existing conventional floating point units. This unit requires slightly more area than a conventional floating point divider. It provides a significant performance improvement over software implementations of interval divider. This paper presents the implementation of non restoring interval division algorithm for double precision binary data.