Case Study of Finite Resource Optimization in FPGA using Genetic Algorithm'

Modem Field-Programmable Gate Arrays (FPGAs) are becoming very popular in embedded systems and high perfonnance appl ications. FPGA has benefited from the shrinking of transistor featurc size, which allows more on-chip reconfigurable (e.g., memories and look-up tab les) and routing resourccs available. Unf011unately, the amount of reconfigurable resources in a FPGA is fixed and limited. This paper investigates the mapping scheme of the applications in a FPGA by utilizing sequent ial processing (e.g., Altera Nios II or Xilinx Microblaze, Ilsing C programming language) and task specific hardware (using hardware description language). Genetic Algorithm is used in this study. We found thaI plac ing sequential processor cores into FPGA can improve the resource utilization efficiency and achieve acceptable system perfonnancc. ln this paper, three cases were studied to detennine the trade-off between resource optimization and system performance. Key Words: FI'GA, resource utilization, genetic algorithm, scheduling