A game-based genetic algorithm approach for evolutionary hardware design

To improve the speed and efficiency of evolutionary hardware design, with off-line gate-level samples, this paper presented a game based genetic algorithm (GGA). GGA transformed the circuit design problem to an optimal game decision-making one. Each output of the circuit was regarded as a player. For each output of a circuit, there was a date path from inputs to it which contains some logic gates, the various routings of these gates and these gates were regarded as strategy. The choice of policy was realized by genetic algorithm. As such, the game model was built. Simulation results show that the method is effective.