李夏青

博士、副教授

基本信息

办公电话： 电子邮件： research_xq@sina.com
通讯地址： 邮编：

个人简介



  • 副教授（硕导），现就职于北京交通大学计算机学院交通大数据与人工智能教育部重点实验室。博士毕业于清华大学计算机系高性能计算研究所（师从 郑纬民院士和 张广艳副教授）。曾先后就职于中科院计算所处理器芯片全国重点实验室（助理研究员/博士后，导师 陈云霁研究员和 郭崎研究员）、联想研究院（北京）和香港浸会大学等；
  • 近年主要研究方向为高性能计算、计算机体系结构、大数据与大模型计算系统，相关研究成果均发表在本领域顶级国际会议和期刊上，如ISCA、ASPLOS、MICRO、DAC、TPDS、TC、SCIS、ICPP、ICCAD、ICML和ICLR等。共发表CCF A类国际会议和期刊论文10余篇，其中Google学术引用单篇180余次（第一作者）；
  • 获得ACM SIGHPC CHINA新星奖、ACM SIGHPC CHINA优秀博士论文奖和MICRO'22最佳论文Runner-up奖等多个奖项；
  • 曾参与国家重点研发计划、973、863和国家自然基金等项目，并主持国家自然科学基金委面上项目一项；
  • 现担任IEEE ICPADS、HPC China和Super Computing (SC)的程序委员会成员，以及IEEE TPDS、IEEE TCC、JPDC、TMC、SCIENCE CHINA和Super Computing（SC）等期刊和会议的审稿人。同时，他还担任了IEEE ICPADS 2023的程序分会主席。


【欢迎加入我们的研究小组】： 欢迎对计算机系统结构 、大模型推理和调优系统以及并行算法与系统等感兴趣，且有志解决业界真实的问题，做实用而有趣的研究，发表高水平文章的同学（本科生、及准备报考/推免硕士研究生）发送邮件给我。


研究方向

  • 先进计算与高性能计算
  • 大数据技术与工程
  • 计算机技术
  • 生成式人工智能与安全
  • 人工智能
  • 软件工程
  • 新一代电子信息技术

招生专业

  • 计算机科学与技术硕士
  • 新一代电子信息技术（含量子技术等）硕士
  • 计算机技术硕士
  • 人工智能硕士
  • 软件工程硕士
  • 大数据技术与工程硕士

科研项目


  • 国家自然基金委面上项目, 大模型自动化超参数调优的扩展性研究，主持
  • 北交大人才基金项目，面向高效自动化机器学习的关键技术研究， 主持
  • 中国工程院战略研究与咨询项目，xxxx战略研究，参与
  • 国家任务，xxxx设计，参与
  • 战略性先导，xxxx关键技术，参与
  • 国家自然基金委面上项目，资源全局共享的存储阵列关键技术研究，参与
  • 科技部973课题，网络大数据计算系统架构体系与评价方法研究，参与




论文/期刊

代表性论文（体系结构和高性能计算领域）：


  • [TPDS]    Xiaqing Li, Qi Guo, Guangyan Zhang, Siwei Ye, Guanhua He, Yiheng Yao, Yifan Hao, Zidong Du, Wei min Zheng.  FastTuning: Enabling Fast and Efficient Hyper-Parameter Tuning with Partitioning and Parallelism of Search Space,  IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume:35, Issue:7, Pages:1174 - 1188, July 2024. ( CCF-A类)
  • [TPDS]    Xiaqing Li, Guangyan Zhang, Weimin Zheng. SmartTuning: Selecting HyperParameters of a ConvNet System for Fast Training and Small Working Memory.  IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume: 32, Issue: 7, Pages: 1690-1701. July 2021.  ( CCF-A类)
  • [TPDS]   Xiaqing Li, Guangyan Zhang, Zhufan Wang, Weimin Zheng. HyConv: Accelerating Multi-phase CNN Computation by Fine-grained Policy Selection. IEEE Transactions on Parallel and Distributed Systems (TPDS), Volume: 30, Issue: 2, Pages: 388 - 399. Feb. 2019.  ( CCF-A类)
  • [ICPP]    Xiaqing Li, Guangyan Zhang, H. Howie Huang, Zhufan Wang and Weimin Zheng. "Performance Analysis of GPU-based Convolutional Neural Networks," in the Proceedings of the 45th International Conference on Parallel Processing (ICPP-2016), Philadelphia, PA USA, August 2016.  ( CCF-B类)
  • [ICCAD] Zhengyang Lv, Xiaqing Li, Zidong Du, Qi Guo. "Explainable and Layout-Aware Timing Prediction," 2024 ACM/IEEE International Conference on Computer-Aided Design (ICCAD-2024), Volume: 35, July 2024. ( CCF-B类)
  • [SCIS] Wenkai He, Xiaqing Li, Xinkai Song, Yifan Hao, Rui Zhang, Zidong Du, Yunji Chen. "Chip design with machine learning: a survey from algorithm perspective," Science China Information Science (SCIS), Oct 19, 2023. ( CCF-A类)
  • [ICLR] Jun Bi, Xiaqing Li, Qi Guo, Rui Zhang, Yuanbo Wen, Xing Hu, Zidong Du, Xinkai Song, Yifan Hao, Yunji Chen. "BALTO: Efficient Tensor Program Optimization with Diversity-Based Active Learning," International Conference on Learning Representations (ICLR 2023).  （TH-CPL(清华计算机学科群)推荐A类国际会议)
  • [TC] Jun Bi, Yuanbo Wen, Xiaqing Li, Yongwei Zhao, Yuxuan Guo, Enshuai Zhou, Zidong Du, Ling Li, Huaping Chen, Tianshi Chen, Qi Guo. Efficient and Fast High-performance Library Generation for Deep Learning Accelerators. IEEE Transactions on Computers (TC).  Pages: 1-14, October 2024.  ( CCF-A类) 
  • [ASPLOS] Bi Jun, Qi Guo, Xiaqing Li, Yongwei Zhao, Yuanbo Wen, Yuxuan Guo, Enshuai Zhou, Xing Hu, Zidong Du, Ling Li, Huaping Chen, Tianshi Chen. "Heron: Automatically Constrained High-performance Library Generation for Deep Learning Accelerators," Proceedings of the 28th Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'23), in Canada, Volume 3: 314-328.  ( CCF-A类)
  • [JCST] Zhen-Xing Zhang, Yuan-Bo Wen, Han-Qi Lv, Chang Liu, Rui Zhang, Xia-Qing Li, Chao Wang, Zi-Dong Du, Qi Guo, Ling Li, Xue-Hai Zhou, Yun-Ji Chen. AI computing systems for LLMs training: a review[J]. Journal of Computer Science and Technology.  ( CCF-B类)
  • [MICRO] Yi Chen, Yongwei Zhao, Yifan Hao, Yuntao Dai, Yang Liu, Rui Zhang, Mo Zou, Yuanbo Wen, Xinkai Song, Xiaqing Li, Xing Hu, Zidong Du, Huaping Chen, Qi Guo, Tianshi Chen. "EMP: Efficient 4-bit Matrix Unit via Primitivization," The 57th ACM/IEEE International Symposium on Microarchitecture (MICRO 2024). ( CCF-A类)
  • [ASPLOS] Husheng Han, Xinyao Zheng, Yifan Hao, Ling Liang, Erhu Feng, Jianan Mu, Xiaqing Li, Tianyun Ma, Pengwei Jin, Yuanbo Wen, Xinkai Song, Zidong Du, Qi Guo, Xing Hu. "TensorTEE: Unified Granularity Heterogeneous TEE for Efficient Secure Collaborative Computing," Proceedings of the 28th Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS'24). ( CCF-A类)
  • [DAC] Shuyao Cheng, Chongxiao Li, Zidong Du, Rui Zhang, Xing Hu, Xiaqing Li, Guanglin Xu, Yuanbo Wen, Qi Guo. "Revisiting Automatic Pipelining: Gate-level Forwarding and Speculation," Design Automation Conference 2024 (DAC'24), July 2024. ( CCF-A类)
  • [ISCA] Weihao Kong, Yifan Hao, Yongwei Zhao, Xinkai Song, Xiaqing Li, Mo Zou, Rui Zhang, Xing Hu, Wei Li, Zidong Du, Qi Guo, Zhiwei Xu, Tianshi Chen. "DiffBoost: Full-Network Differential Acceleration for Diffusion Models," The 51st Annual International Symposium on Computer Architecture 2024 (ISCA '24). ( CCF-A类)
  • [MICRO] Hongrui Guo, Yongwei Zhao, Zhangmai Li, Yifan Hao, Chang Liu, Xinkai Song, Xiaqing Li, Zidong Du, Rui Zhang, Qi Guo, Tianshi Chen, Zhiwei Xu. "Cambricon-U: A Systolic Random Increment Memory Architecture for Unary Computing," The 56th ACM/IEEE International Symposium on Microarchitecture (MICRO 2023). ( CCF-A类)
  • [MICRO] Yifan Hao, Yongwei Zhao, Chenxiao Liu, Zidong Du, Shuyao Cheng, Xiaqing Li, Xing Hu, Qi Guo, Zhiwei Xu, Tianshi Chen. "Cambricon-P: A Bitflow Architecture for Arbitrary Precision Computing," The 55th ACM/IEEE International Symposium on Microarchitecture (MICRO 2022).  ( CCF-A类)
  • [ICML] Yuanbo Wen, Qi Guo, Qiang Fu, Xiaqing Li, Jianxing Xu, Yanlin Tang, Yongwei Zhao, Xing Hu, Zidong Du, Ling Li, Chao Wang, Xuehai Zhou, Yunji Chen. "BabelTower: Learning to Auto-parallelized Program Translation," International Conference on Machine Learning (ICML), July 2022. ( CCF-A类)
  • [MCSoC] Bao Zhenshan, Guo Junnan, Xiaqing Li, and Zhang Wenbo. "MSCU: Accelerating CNN Inference with Multiple Sizes of Compute Unit on FPGAs," IEEE MCSoC, 2021.     



专利

  • 张广艳, 李夏青, 郑纬民; 一种卷积神经网络的计算方法及系统, 2021-1-5, ZL201810646058.1. 

软件著作权

获奖与荣誉

  • 中国科学院计算技术研究所2023年度优秀研究人员                     2024年
  • ACM SIGHPC CHINA新星奖                                                  2023年
  • Best Paper Award (Runner Up) of MICRO 2022                      2022年
  • ACM SIGHPC CHINA优秀博士论文奖                                      2021年
  • 华为云与计算先锋教师                                                          2021年

社会兼职

Session Chair:


  • Theory and Protocols, IEEE ICPADS


TPC Member:

  • IEEE ICPADS
  • HPC China
  • SuperComputing (SC)

Reviewer for journals：
  •  IEEE Transactions on Parallel and Distributed Systems (TPDS)
  •  IEEE Transactions on Cloud Computing (TCC)
  •  Parallel Computing (PC)
  •  Journal of Parallel and Distributed Computing (JPDC)
  •  SCIENCE CHINA Information Sciences
  •  Transactions on Mobile Computing (TMC)
  •  软件学报