Combining CBR and GA for Designing FPGAs

• Venue: ICCIMA '99 Proceedings of the 3rd International Conference on Computational Intelligence and Multimedia Applications
• Year: 1999

Field Programmable Gate Arrays (FPGAs) are a recent form of user programmable logic devices that contain an array of logic gates. As there is no complete set of techniques for designing any FPGA program, researchers have been successful in evolving program designs using genetic algorithms (GAs). However, using GAs to generate software programs for FPGAs is faced with two main problems namely scaling and errors. In this paper we present our on-going research towards overcoming these problems by integration of genetic algorithms with Case Based Reasoning. Case Based Reasoning (CBR) is a problem solving method that reuses old solutions to solve new problems. Our research work aims to apply case based reasoning to reuse genetically evolved FPGA programs in order to develop larger programs at reasonable computational expense. The paper describes our preliminary experiments and their results that are encouraging.