Key points are not available for this paper at this time.
A sub-nanosecond 64 b adder in 0.5 /spl mu/m CMOS forms the basis for the integer and floating point execution units. Integrating dual-rail dynamic CMOS and use of Ling's equations, the adder is composed of 7k FETs in 0.246 mm/sup 2/ and performs a full 64 b add, operands to result in <1 ns (7 fanout of 4 inverter delays) under nominal conditions.
Samuel Naffziger (Mon,) studied this question.