Title: Automation in Analog/RF IC Design

Time: 15:30–16:30, April 17, 2025

Location: B1-e310 Meeting Room, International Campus

Speaker: Xiangyu Meng

Speaker Biography:Xiangyu Meng is an Associate Professor and Doctoral Supervisor in the School of Electronics and Information Engineering at Sun Yat-sen University, and a talent recruited under the university’s “Hundred Talents Program.” He received his bachelor’s degree from Tsinghua University in 2011 and his Ph.D. from Tsinghua University in early 2017, after which he conducted postdoctoral research at the Hong Kong University of Science and Technology. In November 2018, he joined the School of Electronics and Information Engineering at Sun Yat-sen University. His main research areas include silicon-based millimeter-wave integrated circuit technology and integrated circuit EDA technology, supported by funding from the National Natural Science Foundation of China and the National Key Research and Development Program. He has published over 40 papers as first author or corresponding author in top-tier journals (such as TMTT and TCAS-I) and internationally renowned conferences (such as VLSI and ASSCC), and holds 8 authorized invention patents. In terms of technology transfer and industrialization, he has led multiple industry-sponsored research projects for defense and industrial applications, successfully developed several millimeter-wave chip prototypes, and launched the independently developed RF IC automated design software platform RFI Pro, which provides generalized support for automatic optimization of RF layouts.

Abstract:In today's era of great-power competition, analog/RF IC design serves as the foundation of the electronics and information industry and is a core technological component in fields such as communications, radar, and artificial intelligence. Automation in analog/RF IC design, through the modeling and optimization of complex circuit design processes, can simultaneously enhance both design efficiency and precision while also enabling the exploration of higher-performance circuit architectures. With the growing demand across various fields for high-performance, low-power, and rapidly iterative IC design, design automation technology has broken through the limitations of traditional manual design workflows, emerging as a key breakthrough technology for intelligent IC development. Automation in analog/RF IC design faces two critical challenges: 1) How to ensure circuit performance while improving design efficiency and significantly shortening design cycles; and 2) How to effectively explore the design space to optimize design outcomes and reduce risks arising from model uncertainties. This presentation will discuss the application of machine learning methods in analog/RF IC design automation, as well as practical considerations in the development workflow, including the team’s independently developed automated design platform and optimization practices in circuit modules such as OTA, Bandgap, PLL, and LNA. It is hoped that this talk will provide valuable insights for experts and scholars engaged in analog and RF IC design research.