摘要
Having the advantage of simplicity, robustness and low computational costs, the particle swarm optimization (PSO) algorithm is a powerful evolutionary computation tool for synthesis and optimization of Reed- Muller logic based circuits. Exploring discrete PSO and probabilistic transition rules, the discrete ternary particle swarm optimization (DTPSO) is proposed for mixed polarity Reed-Muller (MPRM) circuits. According to the characteristics of mixed polarity OR/XNOR expression, a tabular technique is improved, and it is applied in the polarity conversion of MPRM functions. DTPSO is introduced to search the best polarity for an area of MPRM circuits by building parameter mapping relationships between particles and polarities. The computational results show that the proposed DTPSO outperforms the reported method using maxterm conversion starting from POS Boolean functions. The average saving in the number of terms is about 11.5%; the algorithm is quite efficient in terms of CPU time and achieves 12.2% improvement on average.
Having the advantage of simplicity, robustness and low computational costs, the particle swarm optimization (PSO) algorithm is a powerful evolutionary computation tool for synthesis and optimization of Reed- Muller logic based circuits. Exploring discrete PSO and probabilistic transition rules, the discrete ternary particle swarm optimization (DTPSO) is proposed for mixed polarity Reed-Muller (MPRM) circuits. According to the characteristics of mixed polarity OR/XNOR expression, a tabular technique is improved, and it is applied in the polarity conversion of MPRM functions. DTPSO is introduced to search the best polarity for an area of MPRM circuits by building parameter mapping relationships between particles and polarities. The computational results show that the proposed DTPSO outperforms the reported method using maxterm conversion starting from POS Boolean functions. The average saving in the number of terms is about 11.5%; the algorithm is quite efficient in terms of CPU time and achieves 12.2% improvement on average.
基金
Project supported by the National Natural Science Foundation of China(No.61076032)
the S&T Plan of Zhejiang Provincial Science and Technology Department(No.2010C31012)
the S&T Plan of Zhejiang Provincial Education Department(No.Y201016317)
the S&T Plan of Ningbo University(No.xk1089)
the K.C.Wong Magna Fund in Ningbo University