A hardware method for functional unit assignment is presented, based on the principle that a functional unit?s power consumption is approximated by the switching activity of its inputs. Since computing the Hamming distance of the inputs in hardware is expensive, only a portion of the inputs are examined. Integers often have many identical top bits, due to sign extension, and floating points often have many zeros in the least significant digits, due to the casting of integer values into floating point. The accuracy of these approximations is studied and the results are used to develop a simple, but effective, hardware scheme.