基于神经网络模型的优化布图技术综述

SURVEY ON NEURAL NETWORKS FOR PHYSICAL DESIGN OF ICS

本文对可用于集成电路布图的神经网络模型和神经优化计算方法作了概括和总结,比较了它们的优缺点及其在IC布图中的应用前景;分析了神经网络在集成电路布图中的应用现状和存在的问题;提出了各类优化计算神经网络模型求解集成电路布图问题的一些网络映射方法和应用方法;提出了基于神经网络的布图算法在串行机上模拟的几种速度提高方法。

This paper systematically summarizes the merits, defects and perspectives of the neural network approaches being able to solve the physical design tasks, analyzes the present research situation of applying neural networks to physical design, proposes some approaches for mapping physical design problems to neural networks, and presents some methods to raise running speed of the neural network based the algorithm, which is executed in sequential computer.