Toward Fully Automated Machine Learning for Routability Estimator Development
- 7 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (3) , 970-982
Abstract
The rise of machine learning technology inspires a boom of its applications in electronic design automation (EDA) and helps improve the degree of automation in chip designs. However, manually crafting machine learning models remains a complex and time-consuming process because it requires extensive human expertise and tremendous engineering efforts to carefully extract features and design model architectures. In this work, we leverage automated machine learning techniques to automate the machine learning (ML) model development for routability prediction, a well-established technique that can help to guide cell placement toward routable solutions. We present an automated feature selection method to identify suitable features for model inputs.We develop a neural architecture search method to search for high-quality neural architectures without human interference. Our search method supports various operations and highly flexible connections, leading to architectures significantly different from all previous human-crafted models. Our experimental results demonstrate that our automatically generated models clearly outperform multiple representative manually crafted solutions with a superior 9.9% improvement. Moreover, compared with human-crafted models, which easily take weeks or months to develop, our efficient AutoML framework completes the whole model development process with only 1 day.Keywords
Funding Information
- SRC GRC-CADT (3103.001/3104.001)
- NSF (CCF-2106725/2106828)
This publication has 20 references indexed in Scilit:
- Automatic Routability Predictor Development Using Neural Architecture Search2021
- AutoML: A survey of the state-of-the-artKnowledge-Based Systems, 2021
- High-Definition Routing Congestion Prediction for Large-Scale FPGAs2020
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation2019
- Learning Transferable Architectures for Scalable Image Recognition2018
- A Machine Learning Framework to Identify Detailed Routing Short Violations from a Placed Netlist2018
- BEOL stack-aware routability prediction from placement using data mining techniques2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Accurate prediction of detailed routing congestion using supervised data learning2014
- RT-level ITC'99 benchmarks and first ATPG resultsIEEE Design & Test of Computers, 2000