An evolutionary neural network approach for module orientation problems

A novel neural network approach called "Evolutionary Neural Network (ENN)" is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time.

[1]  Sartaj Sahni,et al.  NP-Hard Module Rotation Problems , 1993, IEEE Trans. Computers.

[2]  Yoshiyasu Takefuji,et al.  A generalized maximum neural network for the module orientation problem , 1992 .

[3]  Chong-Min Kyung,et al.  Finding optimal module orientations in macrocell placement , 1991 .

[4]  C. L. Liu,et al.  A new approach to the pin assignment problem , 1988, DAC '88.

[5]  P.-Y. Hsiao,et al.  Genetic algorithms for the module orientation problem , 1994 .

[6]  Yoshiyasu Takefuji,et al.  A maximum neural network for the max cut problem , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[7]  Nobuo Funabiki,et al.  A neural network model for multilayer topological via minimization in a switchbox , 1996, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[8]  M. Yamada,et al.  An analytical method for optimal module orientation , 1988, 1988., IEEE International Symposium on Circuits and Systems.

[9]  Ran Libeskind-Hadas,et al.  Solutions to the Module Orientation and Rotation Problems by Neural Computation Networks , 1989, 26th ACM/IEEE Design Automation Conference.

[10]  Naveed A. Sherwani,et al.  Algorithms for VLSI Physical Design Automation , 1999, Springer US.

[11]  Seishi Nishikawa,et al.  Comparisons of Energy-Descent Optimization Algorithms for Maximum Clique Problems , 1996 .

[12]  D. E. Goldberg,et al.  Genetic Algorithms in Search, Optimization & Machine Learning , 1989 .

[13]  Nobuo Funabiki,et al.  An Improved Neural Network for Channel Assignment Problems in Cellular Mobile Communication Systems , 1995 .

[14]  Yoshiyasu Takefuji,et al.  A parallel algorithm for channel routing problems [VLSI] , 1992, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[15]  Yoshiyasu Takefuji,et al.  A neural network approach to topological via-minimization problems , 1993, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[16]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[17]  Chong-Min Kyung,et al.  Module orientation algorithm using reconstruction of nets and mean field annealing , 1991 .