Optimisation techniques based on the use of genetic algorithms (GAs) for logic implementation on FPGAs

The work described in this paper began some time ago as an investigation into two problems associated with logic minimisation or optimisation. These are respectively, the state assignment problem in the design of finite state machines, and the optimisation of combinational logic circuits using Reed-Muller (RM) techniques. When faced with such designs, the use of FPGAs to implement circuits is clearly appropriate. However, because of the limited resources available on FPGA parts, in terms of the number of available CLBs, and the increased difficulty that place and route software will experience in the layout of increasingly complex designs, it is felt that some form of optimisation of the design before implementation is still a necessary stage in the design process. This paper describes the implementation of algorithms which attempt to provide this type of optimisation for the two previously mentioned problems. The resultant software uses genetic algorithms to select, breed and test the fitness of potential solutions, and thereby recommend a near-optimal solution. In practice, these recommended solutions represent a considerable saving (in terms of gate count) on many circuit implementations, as experimental results demonstrate.