Optimization of high speed pipelining in FPGA-based FIR filter design using genetic algorithm
Uwe H. Meyer-Baese, Guillermo Botella, David Ernesto Troncoso Romero, Martin Kumm · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2012
This paper compares FPGA-based full pipelined multiplierless FIR filter design options. Comparison of Distributed Arithmetic (DA), Common Sub-Expression (CSE) sharing and n-dimensional Reduced Adder Graph (RAG-n) multiplierless filter design methods in term of size, speed, and A*T product are provided. Since DA designs are table-based and CSE/RAG-n designs are adder-based, FPGA synthesis design data are used for a realistic comparison. Superior results of a genetic algorithm based optimization of pipeline registers and non-output fundamental coefficients are shown. FIR filters (posted as open source by Kastner et al.) for filters in the length from 6 to 151 coefficients are used.