| 摘要 |
PURPOSE:To provide the floating point arithmetic unit which can perform floating point operation at a high speed. CONSTITUTION:When a floating point number to be operated is inputted to a floating point data input part 11 through an external bus 2, the kind of the floating point number to be operated is discriminated and the discrimination result is stored in a floating point register 12 together with the floating point number to be operated. At the time of operation, the floating point number to be operated and the discrimination result in the floating point register 12 are taken out and an arithmetic judging circuit 13 judges whether or not floating point operation is actually performed on the basis of the discrimination result. When it is judged that the operation is not performed, a specific value is outputted as an arithmetic result. When it is judged that the floating point operation needs to be performed, a floating point arithmetic circuit 14 actually performs the floating point operation. |
