Fuzzy inference for the initial population of genetic algorithms applied to VLSI floorplanning design

Abstract

VLSI floorplanning design automation based on soft computing is discussed. A novel approach based on the fusion of genetic algorithms and fuzzy inference for the automation of VLSI floorplanning design is proposed. The fuzzy rules are used to infer the initial position of the on-chip blocks based on analysis of the accumulated knowledge of the expert design engineer. Only the dominant combinations of place and block are inferred. Blocks deemed suitable candidates for placement at the center, relative to the four-corners of the chip, are inferred. These inferences are then reflected in the initial population of the genetic algorithms. The rest of the block placement phase is entrusted to the genetic algorithms. Experimental software to implement the proposed approach was developed. This was in turn used to perform computer-based experiments. The results of the experiments showed a level and quality of placement close to that of the expert design engineer.