Artificial neural network application in analog layout placement design

In this paper, we propose a method using mean-field neural networks to solve the placement problem for the layout design of analog integrated circuits. By means of the energy function, our method can not only meet the basic requirements of placement, but also handle the symmetry and proximity constraints that are special for analog layouts. Compared with other work, our experimental results show this proposed optimization scheme can achieve more efficient performance and obtain optimal solutions.

[1]  Alessandro De Gloria,et al.  Block placement with a Boltzmann Machine , 1994, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[2]  Hajime Kita,et al.  Solving a placement problem by means of an analog neural network , 1992, IEEE Trans. Ind. Electron..

[3]  Evangeline F. Y. Young,et al.  Analog Placement with Symmetry and Other Placement Constraints , 2006, 2006 IEEE/ACM International Conference on Computer Aided Design.

[4]  Vijay Pitchumani,et al.  Quadrisectioning based placement with a normalized mean field neural network , 1993, 1993 IEEE International Symposium on Circuits and Systems.

[5]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[6]  Carsten Peterson,et al.  Neural Networks and NP-complete Optimization Problems; A Performance Study on the Graph Bisection Problem , 1988, Complex Syst..

[7]  Dieter A. Mlynski,et al.  Mapping and hierarchical self-organizing neural networks for VLSI placement , 1997, IEEE Trans. Neural Networks.

[8]  Dana S. Richards,et al.  Distributed genetic algorithms for the floorplan design problem , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..