Application of a novel evolutionary neural network for macro-cell placement optimization in VLSI physical design

Authors:
Wei Zhou;Gaofeng Wang;Xi Chen
Affiliations:
Institute of Micro-Electronics & Information Tech., Wuhan University, Wuhan, Hubei, China;Institute of Micro-Electronics & Information Tech., Wuhan University, Wuhan, Hubei, China;Institute of Micro-Electronics & Information Tech., Wuhan University, Wuhan, Hubei, China
Venue:
ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I
Year:
2006

Citing 5
Cited 0

Solutions to the module orientation and rotation problems by neural computation networks

DAC '89 Proceedings of the 26th ACM/IEEE Design Automation Conference
Genetic algorithms for VLSI design, layout & test automation

Genetic algorithms for VLSI design, layout & test automation
An evolutionary neural network approach for module orientationproblems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Fundamental CAD algorithms

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Design and analysis of maximum Hopfield networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.