Application of a Novel Evolutionary Neural Network for Macro-cell Placement Optimization in VLSI Physical Design
As operation frequencies and integration densities of modern very large-scale integration (VLSI) circuits increase while device sizes shrink, the quest for high-speed VLSI applications has highlighted the negligible effects of interconnects. It is important to minimize the interconnect wire lengths during VLSI physical design stage. This paper focuses on the minimization process of the total wire length after placement, that is, macro-cell orientation. A novel evolutionary neural network approach based on the concept of evolutionary programming (EPENN) is proposed to address this combinatorial optimization problem. Numerical experiments and simulation results have shown that the presented approach can obtain high quality solutions with low computational complexity.
KeywordsCombinatorial Optimization Problem Versus Versus Versus Versus High Quality Solution Wire Length Orientation Problem
Unable to display preview. Download preview PDF.
- 2.Nakhla, M., Ushida, A.: Special Issue on Simulation, Modeling, and Electrical Design of High-Speed Interconnects. IEEE Trans, Circuits Syst. 47, 44–45 (2000)Google Scholar
- 4.Cong, J.: An Interconnect-Centric Design Flow for Nanometer Technologies. In: Proc. of Int’l Symp. on VLSI Technology, System, and Applications, pp. 54–57 (1999)Google Scholar
- 6.Nan, G.F., Li, M.Q.: Application of Evolutionary Algorithm to Three Key Problems in VLSI Layout. In: Proceedings of the 4th ICMLC, Guangzhou (2005)Google Scholar
- 7.Mazumder, P.: Genetic Algorithms for VLSI Design, Layout & Test Automation. Prentice-Hall, Englewood Cliffs (1999)Google Scholar
- 8.Yao, B., Hou, W.T., Hong, X.L., Cai, Y.C.: FAME: A Fast Detailed Placement Algorithm for Standard Cell Layout Based on Mixed Min-cut and Enumeration. Chinese Journal of Semiconductors 21, 744–753 (2005)Google Scholar
- 9.Gao, W.: Study on New Evolutionary Neural Network. In: Proc. of 3rd ICMLC, Xi’an (2003)Google Scholar
- 10.Fang, J., Xi, Y.G.: Neural Network Design Based on Evolutionary Programming. Artificial Intelligence in Engineering, pp. 155–161. Elsevier, Amsterdam (1997)Google Scholar
- 11.Yamada, M., Liu, C.L.: An Analytical Method for Optimal Module Orientation. In: Proc. Int. Symp. Circuits and Systems, pp. 1679–1682 (1988)Google Scholar
- 12.Libeskind-Hadas, R., Liu, C.L.: Solutions to the Module Orientation and Rotation Problems by Neural Computation Networks. In: Proc. 26th ACM/IEEE Design Automation Conf., pp. 400–405 (1989)Google Scholar