Neural network based estimation of VLSI building block dimensions from schematics

The estimation of the height and width of a custom cell layout (CCL) from schematics is an important task in integrated circuit computer aided design and can be of direct assistance to designers. In this paper, we describe and report results on two CCL dimension estimation techniques. In the first, a neural network is trained to predict the width (or height) of a cell given its schematics and its height (or width). The results show that knowledge of one dimension significantly improves the prediction accuracy of the other. In the second, we explore improvements to previous work (see IEEE Trans. on Neural Networks, vol. 3, no. 1, p. 146-153, 1992) on simultaneous CCL dimension prediction by replacing the neural network that estimates the width and height simultaneously by cascaded neural networks.