Implementation of genetic algorithm based on hardware optimization
Jin Jung Kim, Daek Jin Chung · 2003
The genetic algorithm (GA) has been known as a method of solving large-scale optimization problems with complex constraints in various applications. Since a major drawback of the GA is that it needs a long computation time, the hardware implementations of GA processors (GAP) have been focused on in recent studies. We propose a more efficient GAP based on steady-state GA, modified survival-based GA, and modified tournament selection. In addition, by employing the efficient pipeline parallelization and handshaking protocol in our GAP, almost 50% of the computation speed-up can be achieved over survival-based GA which runs one million crossovers per second (1 MHz).