Anhang Li

Anhang Li

Auto-generated profile, based on publicly available information

Anhang Li

University of Michigan, Ann Arbor, MI, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 September 2024
Verified
Conference Paper
Open access
AHAli Hammoud
Ali Hammoud
CGChetanya Goyal
Chetanya Goyal
SPSakib Pathen
Sakib Pathen
ADArlene Dai
Arlene Dai
ALAnhang Li
Anhang Li
MSMehdi Saligane
Mehdi Saligane
Current approaches to Analog Layout Automation apply ML techniques such as Graph Convolutional Neural Networks (GCN) to translate netlist to layout. While these ML approaches have proven to be effective, they lack the powerful reasoning capabilities, an intuitive human interface, and standard evaluation benchmarks that have been improving at a rapid development pace in Large Language Models (LLMs). The GLayout framework introduced in this work translates analog layout into an expressive, technology generic, compact text representation. Then, an LLM is taught to understand analog layout through fine-tuning and in-context learning using Retrieval Augmented Generation (RAG). The LLM is able to successfully layout unseen circuits based on new information provided in-context. We train 3.8, 7, and 22 Billion parameter quantized LLMs on a dataset of less than 50 unique circuits, and text documents providing layout knowledge. The 22B parameter model is tuned in 2 hours on a single NVIDIA A100 GPU. The open-source evaluation set is proposed as an automation benchmark for LLM layout automation tasks, and ranges from 2-transistor circuits to a ΔΣ ADC. The 22B model completes 70% of the tasks in the evaluation set, and passes DRC and LVS verification on 44% of evaluations with verified correct blocks up to 4 transistors in size.

3 July 2024 in IEEE Solid-State Circuits Magazine
Verified
Journal Article
Closed access
ALAnhang Li
Anhang Li
TZTuohang Zeng
Tuohang Zeng
LZLei Zhang
Lei Zhang
JRJoseph Riem
Joseph Riem
GAGina C. Adam
Gina C. Adam
MSMehdi Saligane
Mehdi Saligane
On recent years, researchers across diverse disciplines have become increasingly interested in low-temperature electronics, which encompasses electronic engineering, material research, sensing, and computing. Among the myriad applications, notable domains include liquid nitrogen-cooled high-performance computing, quantum computing, and deep space exploration [1] . This dynamic landscape has witnessed the culmination of numerous research studies, as evidenced by the rich array of findings outlined in references [2] , [3] , [4] , [5] , and [6] . This field is particularly fascinating due to its multifaceted applications, requiring a comprehensive understanding of knowledge, data, and tools that operate across varying temperature ranges, as detailed in [7] , where the goal is to move the control logic closer to the cryogenic device being tested. This task highlights the significant obstacles that arise when dealing with cryogenic circuitry. As temperatures drop below a certain threshold, the behavior of transistors and passive devices undergoes a significant transformation. Designers must carefully measure and model these devices internally, adjusting circuit scaling based on basic models. This process demands significantly more man-hours compared with conventional circuit design methodologies. The task could be streamlined with the presence of a shared metrology device modeling database among institutions. Such a resource would alleviate the need for redundant efforts and foster efficiency in cryogenic circuit design.

1 January 2024 in IEEE Solid-State Circuits Letters
Verified
Journal Article
Closed access
ALAnhang Li
Anhang Li
JLJeongsup Lee
Jeongsup Lee
PMPrashansa Mukim
Prashansa Mukim
BHBrian D. Hoskins
Brian D. Hoskins
PSPragya Shrestha
Pragya Shrestha
MSMehdi Saligane
Mehdi Saligane
This letter presents a fully integrated recursive successive-approximation switched capacitor (RSC) DC–DC converter implemented using an automatic cell-based layout generation in 12-nm FinFET technology. A novel design methodology is demonstrated based on the theoretical analyses of the optimal energy operation of the switched-capacitor (SC) DC–DC converter and directly finds the optimal design parameters from the given input specifications. The converter maintains >75% efficiency across a vast range of output currents and temperatures. Our design targets voltage scaling for applications, such as cryo-computing, cryo-sensing, and parts of quantum computing, to achieve high-system power efficiency.


3 July 2024 in IEEE Solid-State Circuits Magazine
Verified
Journal Article
Closed access
ALAnhang Li
Anhang Li
HWHongyi Wu
Hongyi Wu
MLMadhulika Lingamguntla
Madhulika Lingamguntla
AFAshbir Aviat Fadila
Ashbir Aviat Fadila
CKChan-Ho Kye
Chan-Ho Kye
MSMehdi Saligane
Mehdi Saligane
The open source hardware movement has made significant progress over the past few years. Increasingly, more individuals are engaging with and participating in the open source chip design community, not only to design their chips with available open source tools but also to have their designs physically fabricated and returned to them for practical use. Companies like Google have sponsored physical chip fabrication runs over the past few years, such as OpenMPW, through semiconductor CMOS processes provided by Skywater (SKY130) and GlobalFoundries (GF180) [1] . When we consider the availability of open source chip design tools, a supportive community, reliable fabrication partners, financial sponsors, and a growing infrastructure of suppliers and educators, it becomes clear that a revolution in chip design is an inevitable outcome. By leveraging existing resources provided by the open source community, this article presents the joint development of a new laser-induced graphene (LIG)-based sensor platform. The effort includes the design, fabrication, and testing of an AFE ASIC using open tools and the design and in-house fabrication of LIG sensors. The article presents the ASIC’s design process and the fabricated chip’s testing results. It demonstrates testing a wearable strain gauge LIG sensor and a temperature-sensitive LIG sensor using our AFE chip. The demonstration serves as an example of the potential to develop the sensing system into a multimodal flexible sensing platform.

23 January 2023 in IEEE Solid-State Circuits Magazine
Verified
Journal Article
Closed access
ALAnhang Li
Anhang Li
WZWenting Zhang
Wenting Zhang
MSMehdi Saligane
Mehdi Saligane
Presents information on the above named conference.