Yuan Ze University

VLSI/CAD Laboratory

Rung-Bin Lin
http://vlsi.cse.yzu.edu.tw/

Research Field

Automation Technology

Introduction

Professor Lin and his students have published more than 100 articles in the areas of electronic design automation and integrated circuit designs. Most of them are archived in IEEE Xplore and ACM Digital Library.

2022~present        Dean, College of Informatics, Yuan Ze University.

2008-present        Professor, Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 320 Taiwan.

2017-2022               Director, International Program in Informatics for Bachelor, Yuan Ze University, Chung-Li, 320 Taiwan

2011-2017                 Head, Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 320 Taiwan

1995-2008              Associate Professor, Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 320 Taiwan.

1994-1995               Research Associate, Application and Research Center of Information Technology, Tatung Institute of Technology, Taipei.

1992-1994               Research and Development Staff, Large Scale Computing Division, IBM, Poughkeepsie, New York, USA. 

1986-1987               Research Assistant, ITRI, Hsin-Chu, Taiwan.

VLSI/CAD Laboratory was established in 1995. It focuses on developing algorithms (software) and design methodologies for Electronic Design Automation (EDA) of integrated circuits (or Computer-Aided VLSI Design). Due to the amazing advancement of semiconductor technologies, billions of transistors can be placed in a single chip. This enables us to design very powerful servers for cloud computing and networking and various products such as desktop PCs, HD TV, mobile phones, tablet PCs, notebooks, video/digital cameras,  and other smart electronic devices. One of the enabling technologies of designing chips for these products is Electronic Design Automation (EDA). EDA software (tools) can be used to solve the problems encountered during synthesizing, analyzing, verifying and testing a circuit. We are seeking more powerful algorithms and design methodologies for solving these problems to minimize chip size and power consumption while optimizing chip performance. Currently, we especially focus on the problems related to standard cell layouts and library development, power minimization, timing performance optimization, manufacturing yield optimization, etc.

To participate in our research work, one should be at least a senior student or preferably a master/Ph.D. student who majors in computer science and engineering or electrical and electronic engineering. 


Research Topics
  1.  Optimizing standard cell layouts designed with sub-10nm process technologies.
  2.  Automating standard cell layout design.
  3.  Developing  standard cell design methodologies for area, power, and performance.
  4.  Quantizing routing resources for global routing of a circuit.
  5. Developing placement and routing algorithms for circuits designed with sub-10nm process technology, leveraging ML-based optimization.
  6. Developing placement and routing algorithms for heterogeneous 3D IC integration.
  7. Applying machine learning and AI methods to improve circuit design efficiency, accuracy, and automation.

Honor
  • Best paper award, International Symposium on Quality Electronic Design, Santa Clara, CA, US,  2021.
  • Best paper candidate, International Symposium on Quality Electronic Design, Santa Clara, CA, US, 2018.
  • Outstanding paper award, Workshop on Synthesis and System Integration of Mixed Information Technologies (SASIMI), Beppu, Oita, Japan, 2012.
  • Technical program committee member, International Conference on Computer-Added Design, 2021~2023
  • Invited Talk, International Conference on Innovations in Engineering and Technology, Hyderabad, India, 2022
  • Technical program committee member, International Symposium on Quality Electronic Design (ISQED), 2016~2024
  • Session chair, International Symposium on Quality Electronic Design (ISQED), 2019
  • Session chair, IEEE Computer Society Annual Symposium on VLSI, 2018
  • Session chair, International Symposium on VLSI Design, Automation and Test (VLSI-DAT), 2017
  • Contest Co-chair, CAD Contest at ICCAD, 2015~2017
  • Technical program committee member, IEEE/ACM Asia and South Pacific Design Automation Conference (ASPDAC), 2012~2014
  • Technical program committee member, IEEE International Conference on Computer Design (ICCD), 2012, 2013
  • Session chair, ASPDAC 2013, 2014
  • Session chair, ACM/IEEE Great Lakes Symposium on VLSI, 2014
  • Organizer, Workshop on Electronic Design Automation, Taiwan, 2011~2013
  • Technical program committee member, Workshop on Synthesis and System Integration of Mixed Information technologies (SASIMI), 2009, 2010, Japan
  • Session chair, International Symposium on VLSI Design, Automation and Test (VLSI-DAT), 2007
  • Workshop co-chair for International Workshop on Computer Architecture, VLSI, and Embedded Systems in conjunction with International Computer Symposium, Taipei, Dec. 4-6, 2006
  • Session chair and program committee member, VLSI Design/CAD Symposium, annually held in Taiwan

Educational Background

1987-1992             Ph.D. Computer and Information Science, University of Minnesota, Minneapolis, Minnesota, USA.

1980-1984             BS., Computer Engineering, National Chiao-Tung University, Hsin-Chu, Taiwan.


Job Description

Develop AI/ML-based models for transistor-level placement and optimization

Apply deep learning and reinforcement learning techniques to placement problems

Analyze placement objectives such as area, power, timing, and congestion

Design and evaluate learning-based optimization strategies

Work with simulation and benchmarking data for VLSI layouts

Write research publications

Preferred Intern Educational Level

Master’s or PhD degree in Electrical Engineering, Computer Engineering, Computer Science, or a related field

Basic understanding of VLSI design basics and digital/analog circuits

Background in machine learning / deep learning

 

 

Skill sets or Qualities

Proficiency in Python (PyTorch / TensorFlow)

 

Job Description

Develop and train deep learning models for medical image analysis

Work with medical imaging datasets for preprocessing, annotation, and evaluation

Implement CNNs and transformer-based architectures

Analyze model performance and prepare technical documentation

Assist in research paper writing and experimentation

Preferred Intern Educational Level

Graduate students in Computer Science, Electrical Engineering, Biomedical Engineering, or related fields

Basic knowledge of machine learning and deep learning

Familiarity with Python and deep learning frameworks (PyTorch / TensorFlow)

Interest in AI for healthcare

Skill sets or Qualities

Understanding of Deep Learning liberaries such as (PyTorch / TensorFlow

Experience with medical imaging datasets

Knowledge of image segmentation or classification

Understanding of model evaluation and interpretability