A Deep Transfer Learning Design Rule Checker With Synthetic Training
- 28 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Design & Test
- Vol. 40 (1) , 77-84
Abstract
The number of design rules is drastically increasing as technology nodes scale down. This increase makes the creation of the design rule decks and the checking process complex and time-consuming. This work presents a design rule checking approach using deep learning. The core of the work consists of a framework to generate convolutional neural networks and a parametrized synthetic data generator for training. The models incorporate incremental transfer learning to reduce the training time when adding new rules. The results show that we can capture most of the checks from a design kit rule manual with less than 1% error and up to 7.5x faster than traditional design rule checkers.Keywords
This publication has 10 references indexed in Scilit:
- Partial Sharing Neural Networks for Multi-Target Regression on Power and Performance of Embedded Memories2020
- Design Rule Checking with a CNN Based Feature Extractor2020
- Accelerating Chip Design With Machine LearningIEEE Micro, 2020
- DRC Hotspot Prediction at Sub-10nm Process Nodes Using Customized Convolutional Network2020
- Incremental Learning in Deep Convolutional Neural Networks Using Partial Network SharingIEEE Access, 2019
- Machine Learning-Based Hotspot Detection: Fallacies, Pitfalls and Marching Orders2019
- Soft Voting-Based Ensemble Approach to Predict Early Stage DRC Violations2019
- RouteNet2018
- Machine learning in physical design2016
- FreePDK152015