Floating point processor with high speed rounding circuit

摘要

A floating point processor comprises a first arithmetic unit that adds to or substracts from a first fraction of a first floating point member, a second fraction of a second floating point member. The second number has a weight of corresponding bits equal to that of the first floating point number by being right shifted. The exponent of the second number is less than that of the first number. A second arithmetic unit performs the same adding or substracting operation that the first arithmetic unit performs on the first fraction and the sum of the second fraction and adds the resultant to "1". An inverter reverses every bit derived by the second arithmetic unit. Outputs of the first and second arithmetic units and inverter are supplied to a selector.