CAM-Based Array Converter for URR Floating-Point Arithmetic

摘要

In order to lessen overflow or underflow prob- lem in numerical computation, several new floating-point arith- metics have been proposed. The significant advantage of these new arithmetics is that a number can be represented in a wider range since the fields of exponent ad mantissa are changed de- pending on the magnitude of number. The main issues of these arithmetics are how to find the boundary between exponent and mantissa as well as to convert the formats between new floating- point airthmetic and fixed-point arithmetic quickly.