An ising computing to solve combinatorial optimization problems

An Ising computing that is specialized to solve combinatorial optimization problems is proposed. The computing maps problems to an Ising model and solves the optimization problems by its own convergence property. We proposed a CMOS implementation of Ising computing and fabricated two prototypes of the computer. The 1st generation prototype confirmed the power efficiency is 1800-times higher than that of the conventional vonNeumann computers. The 2nd generation prototype is organized by FPGA, and used to explore its applications.