Research

AI (Large Language Model) for EDA 人工智能（大模型）辅助电子设计自动化

As the technology node of integrated circuits rapidly scales down to 5nm and beyond, the electronic design automation (EDA) in Very Large Scale Integration (VLSI) which has been developed over the last few decades, is challenged by the ever-increasing VLSI design complexity. Artificial Intelligence has shown great potential in various fields, including EDA. Our major achievements are proposing and customizing machine learning and artificial intelligence techniques, especially the emerging large language model techniques, in many EDA applications. Our research topics include design optimization, performance modeling, co-optimization, IC manufacturing, etc.

随着集成电路工艺节点快速推进至5纳米及更先进水平，超大规模集成（VLSI）设计的复杂度日益上升，传统电子设计自动化（EDA）方法面临严峻挑战。人工智能技术在多个领域展现出强大潜力，正在成为EDA发展的重要推动力量。我们团队聚焦于将机器学习与人工智能方法，特别是近年来快速发展的大语言模型（Large Language Models, LLMs）技术，深入应用于EDA各类关键任务中，并取得了一系列重要成果。研究方向涵盖设计优化、性能建模、协同优化、集成电路制造等核心领域。

Selected publications:

  • Qian Jin, Yuqi Jiang, Xudong Lu, Yumeng Liu, Yining Chen, Dawei Gao, Qi Sun#, Cheng Zhuo#,“SEM-CLIP: Precise Few-Shot Learning for Nanoscale Defect Detection in Scanning Electron Microscope Image”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), New Jersey, Oct. 27–31, 2024.

  • Yuanhang Gao*, Donger Luo*, Chen Bai, Bei Yu, Hao Geng, Qi Sun#, Cheng Zhuo#, ‘‘Is Vanilla Bayesian Optimization Enough for High-Dimensional Architecture Design Optimization?’’, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), New Jersey, Oct. 27–31, 2024.

  • Lvcheng Chen, Ying Wu, Chenyi Wen, Shizhang Wang, Li Zhang, Bei Yu, Qi Sun#, Cheng Zhuo#,‘‘An Agile Framework for Efficient LLM Accelerator Development and Model Inference’’, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), New Jersey, Oct. 27–31, 2024.

  • Yuqi Jiang, Xudong Lu, Qian Jin, Qi Sun#, Hanming Wu, Cheng Zhuo#, “FabGPT: An Efficient Large Multimodal Model for Complex Wafer Defect Knowledge Queries”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), New Jersey, Oct. 27–31, 2024. (arxiV)

  • Donger Luo*, Qi Sun*, Xinheng Li, Chen Bai, Bei Yu, Hao Geng, “Knowing The Spec to Explore The Design via Transformed Bayesian Optimization”, ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

  • Yibo Qiao, Weiping Xie, Shunyuan Lou, Qian Jin, Lichao Zeng, Yining Chen#, Qi Sun#, Cheng Zhuo#, “Minimizing Labeling, Maximizing Performance: A Novel Approach to Nanoscale Scanning Electron Microscope (SEM) Defect Segmentation”, ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

  • Hongquan He, Guowen Kuang, Qi Sun, Hao Geng, “Point Cloud and Large Pre-trained Model Catch Mixed-type Wafer Defect Pattern Recognition”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Valencia, Spain, Mar. 25-27, 2024.

  • Donger Luo, Qi Sun, Qi Xu, Tinghuan Chen, Hao Geng, “Attention-Based EDA Tool Parameter Explorer: From Hybrid Parameters to Multi-QoR metrics”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Valencia, Spain, Mar. 25-27, 2024.

  • Tinghuan Chen, Hao Geng, Qi Sun, Sanping Wan, Yongsheng Sun, Huatao Yu, Bei Yu, “Wages: The Worst Transistor Aging Analysis for Large-scale Analog Integrated Circuits via Domain Generalization”, accepted by ACM Transactions on Design Automation of Electronic Systems (TODAES).

  • Chen Bai, Qi Sun#, Jianwang Zhai, Yuzhe Ma, Bei Yu, Martin D.F. Wong, “BOOM-Explorer: RISC-V BOOM Microarchitecture Design Space Exploration”, ACM Transactions on Design Automation of Electronic Systems (TODAES), vol. 29, no. 01, pp. 1–23, 2024.

  • Guojin Chen, Wanli Chen, Qi Sun, Yuzhe Ma, Haoyu Yang, Bei Yu, “DAMO: Deep Agile Mask Optimization for Full Chip Scale”, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), vol. 41, no. 9, pp. 3118-3131, Sept. 2022.

  • Qi Sun, Tinghuan Chen, Siting Liu, Jianli Chen, Hao Yu, Bei Yu, “Correlated Multi-objective Multi-fidelity Optimization for HLS Directives Design”, ACM Transactions on Design Automation of Electronic Systems (TODAES), vol. 27, no. 4, 2022.

  • Tinghuan Chen, Qi Sun, Canhui Zhan, Changze Liu, Huatao Yu, Bei Yu, “Deep H-GCN: Fast Analog IC Aging-induced Degradation Estimation”, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), vol. 41, no. 7, pp. 1990-2003, 2022.

  • Tinghuan Chen, Qi Sun, Canhui Zhan, Changze Liu, Huatao Yu, Bei Yu, “Analog IC Aging-induced Degradation Estimation via Heterogeneous Graph Convolutional Networks”, IEEE/ACM Asia and South Pacific Design Automation Conference (ASPDAC), Tokyo, Jan. 18–21, 2021.

  • Chen Bai, Qi Sun, Jianwang Zhai, Yuzhe Ma, Bei Yu, Martin D.F. Wong, “BOOM-Explorer: RISC-V BOOM Microarchitecture Design Space Exploration Framework”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Nov. 1–4, 2021. (William J. McCalla Best Paper Award)

  • Siting Liu, Qi Sun, Peiyu Liao, Yibo Lin, Bei Yu, “Global Placement with Deep Learning-Enabled Explicit Routability Optimization”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Feb. 01–05, 2021.

  • Qi Sun, Tinghuan Chen, Siting Liu, Jin Miao, Jianli Chen, Hao Yu, Bei Yu, “Correlated Multi-objective Multi-fidelity Optimization for HLS Directives Design”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Feb. 01–05, 2021. (Best Paper Award Nomination)

Deep Learning Algorithms

Deep learning algorithms have driven progress in many fields, and with the development of large language models, they have revolutionized traditional development paradigms. We are exploring improvements and advancements in deep learning and large models.

深度学习算法在多个领域持续推动技术革新，伴随大语言模型的迅猛发展，传统研发范式正经历深刻变革。我们专注于深度学习与大模型方法的优化与创新，积极探索其在前沿应用中的突破性进展与广阔潜力。

  • Xudong Lu, Yuqi Jiang, Haiwen Hong, Qi Sun#, Cheng Zhuo#, “DCAFuse: Dual-Branch Diffusion-CNN Complementary Feature Aggregation Network for Multi-Modality Image Fusion”, ACM International Conference on Multimedia (MM), Melbourne, Australia, Oct. 28-Nov. 01, 2024.

  • Xianting Lu, Yunong Wang, Yu Fu, Qi Sun, Xuhua Ma, Xudong Zheng, Cheng Zhuo, “MISP: A Multimodal-based Intelligent Server Failure Prediction Model for Cloud Computing Systems”, ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Barcelona, Spain, Aug. 25-29, 2024.

  • Yuqi Jiang, Qian Jin, Xudong Lu, Qi Sun#, Cheng Zhuo, “FabSage: A Large Multimodal Model for IC Defect Detection, Analysis, and Knowledge Querying”, IEEE International Workshop on LLM-Aided Design (LAD), San Jose, Jun. 28-29, 2024.

  • Yibo Qiao, Weiping Xie, Shunyuan Lou, Qian Jin, Lichao Zeng, Yining Chen#, Qi Sun#, Cheng Zhuo#, “Minimizing Labeling, Maximizing Performance: A Novel Approach to Nanoscale Scanning Electron Microscope (SEM) Defect Segmentation”, ACM/IEEE Design Automation Conference (DAC), San Francisco, Jun. 23–27, 2024.

  • Hongquan He, Guowen Kuang, Qi Sun, Hao Geng, “Point Cloud and Large Pre-trained Model Catch Mixed-type Wafer Defect Pattern Recognition”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Valencia, Spain, Mar. 25-27, 2024.

  • Xufeng Yao, Yang Bai, Xinyun Zhang, Yuechen Zhang, Qi Sun, Ran Chen, Ruiyu Li, Bei Yu, “PCL: Proxy-based Contrastive Learning for Domain Generalization”, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, Jun. 19–24, 2022.

  • Xinyun Zhang, Binwu Zhu, Xufeng Yao, Qi Sun, Ruiyu Li, Bei Yu, “Context-based Contrastive Learning for Scene Text Recognition”, AAAI Conference on Artificial Intelligence (AAAI), Feb. 22–Mar. 1, 2022.

  • Qi Sun, Xufeng Yao, Arjun Ashok Rao, Bei Yu, Shiyan Hu, “Counteracting Adversarial Attacks in Autonomous Driving”, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), vol. 41, no. 12, pp. 5193–5206, 2022.

  • Qi Sun, Arjun Ashok Rao, Xufeng Yao, Bei Yu, Shiyan Hu, “Counteracting Adversarial Attacks in Autonomous Driving”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Nov. 2–5, 2020.

Deep Learning Inference Acceleration

Deep learning has achieved significant success in a variety of real-world applications. However, most of the existing deep learning models are still by manual design, and how to achieve an automatic and efficient model design is still an open problem. To address this problem, our major achievements are proposing hardware-friendly deep learning models and deployment optimization techniques.

深度学习在众多实际应用中取得了显著成就，然而当前主流模型仍高度依赖人工设计，实现模型设计的自动化与高效化仍是亟待突破的关键难题。针对这一挑战，我们提出了多种面向硬件友好的深度学习模型，并开发了高效的部署优化技术，显著提升了模型在实际系统中的性能与适应性。

Selected publications:

  • Shangran Lin, Xinrui Zhu, Baohui Xie, Tinghuan Chen#, Cheng Zhuo, Qi Sun#, Bei Yu, “RISCSparse: Point Cloud Inference Engine on RISC-V Processor”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), New Jersey, Oct. 27–31, 2024.

  • Yang Bai, Xufeng Yao, Qi Sun, Wenqian Zhao, Shixin Chen, Zixiao Wang, Bei Yu, “GTCO: Graph and Tensor Co-Design for Transformer-based Image Recognition on Tensor Cores”, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), vol. 43, no. 02, pp. 586–599, 2024.

  • Yuxuan Zhao, Qi Sun#, Zhuolun He, Yang Bai, Bei Yu, “AutoGraph: Optimizing DNN Computation Graph for Parallel GPU Kernel Execution”, AAAI Conference on Artificial Intelligence (AAAI), Feb. 7–14, 2023.

  • Wenqian Zhao, Yang Bai, Qi Sun, Wenbo Li, Haisheng Zheng, Nianjuan Jiang, Jiangbo Lu, Bei Yu, Martin D.F. Wong, “A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU”, accepted by IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD).

  • Qi Sun, Xinyun Zhang, Hao Geng, Yuxuan Zhao, Yang Bai, Haisheng Zheng, Bei Yu, “GTuner: Tuning DNN Computations on GPU via Graph Attention Network”, ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, Jul. 10–14, 2022.

  • Qi Sun, Chen Bai, Tinghuan Chen, Hao Geng, Xinyun Zhang, Yang Bai, Bei Yu, “Fast and Efficient DNN Deployment via Deep Gaussian Transfer Learning”, IEEE International Conference on Computer Vision (ICCV), Oct. 11-17, 2021.

  • Wenqian Zhao, Qi Sun, Yang Bai, Haisheng Zheng, Wenbo Li, Bei Yu, Martin D.F. Wong, “A High-Performance Accelerator for Super-Resolution Processing on Embedded GPU”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Nov. 1–4, 2021.

  • Yang Bai, Xufeng Yao, Qi Sun, Bei Yu, “AutoGTCO: Graph and Tensor Co-Optimize for Image Recognition with Transformers on GPU”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Nov. 1–4, 2021.

  • Qi Sun, Chen Bai, Hao Geng, Bei Yu, “Deep Neural Network Hardware Deployment Optimization via Advanced Active Learning”, IEEE/ACM Proceedings Design, Automation and Test in Europe (DATE), Feb. 01–05, 2021.

  • Qi Sun, Tinghuan Chen, Jin Miao, Bei Yu, “Power-Driven DNN Dataflow Optimization on FPGA”, IEEE/ACM International Conference on Computer-Aided Design (ICCAD), Westminster, CO, Nov. 4–7, 2019.