Xueqi Li

Beijing, China lixueqi@ict.ac.cn

Xueqi Li is currently an Associate Professor at the Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS). He is the founder of URSA (XPU-driven Research on System and Architecture) research group in ICT, CAS. He received his Ph.D. degree from ICT, CAS under the supervision of Prof. Ninghui Sun (Member of CAE). From 2018-2020, he was also co-advised by Prof. Yuan Xie as a joint Ph.D. student in SEAL Lab in the Department of Electrical and Computer Engineering at UC Santa Barbara. His current research focuses on Emerging Computer Architecture for Physical AI and AI4S, including Process-in-Memory (PIM) accelerators and systems (存算一体), RISC-V AI ISA-extension for XPU/PIM (RISC-V PIM指令扩展), Algorithm-Architecture-Technology Cross layer Optimization (跨层优化).

During his research on genomic alignment acceleration, he found emerging workloads increasingly combine compute- and memory-intensive operators—e.g., PIM for FM-index and XPU for Smith–Waterman—and observed similar patterns in LLMs, agents, and physical AI. With Prof. Ninghui Sun, he proposed the hyper-heterogeneous computing architecture concept (超异构计算机体系结构：电路-架构-系统), leveraging PIM and 3D integration to evolve CPU-GPU heterogeneous systems for compute-intensive workloads into CPU-XPU-PIM hyper-heterogeneous systems that handle compute-, memory-, and interaction-intensive workloads, accelerating emerging and complex AI workloads end to end. He is currently developing PANDA, a Physical AI Near Data Accelerator.

In Chinese, 在基因组比对加速研究中，他发现新兴工作负载日益融合计算密集型和访存密集型算子，意味着在加速结构中同时需要用于FM-index(访存密集)的PIM和用于Smith–Waterman(计算密集)的XPU，并进一步在大语言模型、智能体和物理AI中观察到类似模式。他与孙凝晖院士一起凝练提出了超异构计算机体系结构概念 (超异构计算机体系结构：电路-架构-系统)，利用PIM和3D集成等变革技术，将适用于计算密集型工作负载的CPU-GPU异构系统演进为可同时适应计算密集型、访存密集型和交互密集型工作负载的CPU-XPU-PIM超异构系统，从而端到端加速新兴且复杂的AI工作负载。目前，他正在开发PANDA，一个面向物理AI近数据处理器与系统.

URSA group is looking for undergraduate interns and graduate students. If you are interested in domain specific accelerator, novel architecture, processing-in-memory, parallel computing and AI for Sciences. Please contact with Xueqi Li via lixueqi@ict.ac.cn.

Education

Institute of Computing Technology, Chinese Academy of Sciences

Ph.D. Student
Computer Architecture, Parallel Programming, Bioinformatics
2014 - 2021

University of California, Santa Barbara

joint Ph.D. Student
Computer Architecture, 3D-Stacked PIM
Oct, 2018 - Apr, 2020

Publication (Selected)

  1. [TCAD'26]FlashAccel: Leveraging High-Bandwidth Flash for High-Throughput LLM Inference
    Xinyu Wang, Yalong Xue, Xiaotian Sun, Xiaoyu Zhang, Xueqi Li, Xiaoming Chen
    TCAD
  2. [ISCA'26]Meridian: In-Memory Acceleration for RAG with Document Attention Decomposition
    Chaoqiang Liu, Yu Huang, Haifeng Liu, Yi Zhang, Qihang Qiu, Xueqi Li, Long Zheng, Xiaofei Liao, Hai Jin, Jingling Xue
    ISCA2026
  3. [DAC'26]Hyperwafer: Communication-Aware Sparse Matrix Multiplication on Wafer-Scale Chips
    Zhongcheng Du, Yu Huang, Yi Zhang, Qihang Qiu, Chencheng Ye, Huanyu Wu, Qie Wang, Xueqi Li, Long Zheng, Xiaofei Liao, Hai Jin
    DAC2026
  4. [DAC'26]Dart: Towards Redundancy-Free RTL Simulation via DAG-Driven Execution
    Jingyi Zhou, Yi Zhang, Yu Huang, Yang Wu, Chunyan Xu, Shaofei Li, Xueqi Li, Long Zheng, Xiaofei Liao, Hai Jin
    DAC2026
  5. [DAC'26]Dypamear: Efficient and Scalable Dynamic Graph Pattern Mining on Practical Processing-in-Memory Architecture
    Yi Zhang, Yu Huang, Deting Chen, Chaoqiang Liu, Haifeng Liu, Xueqi Li, Xiaofei Liao, Hai Jin
    DAC2026
  6. [ISCAS'26] HOPESim: a Lightweight and Modern C++ Based Accelerator Simulation Approach
    Xueqi Li*, Ruihao Gao, Xiaoyu Zhang, Xiaoming Chen, Shunchen Shi, Fan Yang, Ninghui Sun.
    2026 IEEE International Symposium on Circuits and Systems (ISCAS)
  7. [ISCAS'26] GPA: A General-Purpose In-Memory Computing Accelerator
    Xiaoyu Zhang, Zerun Li, Libo Shen, Boyu Long, Xueqi Li, Yinhe Han, Xiaoming Chen.
    2026 IEEE International Symposium on Circuits and Systems (ISCAS)
  8. [HPCA'26] CoCoTree: A Computation-Capable Architecture for Collective Communication in Scalable PIM
    Shunchen Shi#, Qijia Yang#, Fan Yang, Youwei Zhuo, Zhichun Li, Ninghui Sun, Xueqi Li*.
    2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)
  9. [HPCA'26] TurboFuzz: FPGA Accelerated Hardware Fuzzing for Processor Agile Verification
    Yang Zhong#, Haoran Wu#, Xueqi Li, Sa Wang, David Boland, Yungang Bao, Kan Shi.
    2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)
  10. [TCAD] DuoPIM: RRAM-DRAM Hybrid PIM Acceleration for Flexible-Batch LLM Decoding
    Xiaotian Sun, Xinyu Wang, Wanqian Li, Xueqi Li, Chunmeng Dou, Yinhe Han, Xiaoming Chen.
    The 21st Annual IFIP International Conference on Network and Parallel Computing
  11. [NPC'25] upTSA: A DIMM-Based Near Data Processing Accelerator for Time Series Analysis
    Shunchen Shi, Fan Yang, Qijia Yang, Xiaohui Peng, Xueqi Li, Ninghui Sun.Xueqi Li*, Ninghui Sun.
    The 21st Annual IFIP International Conference on Network and Parallel Computing
  12. [ISLPED'25] upGEMV: A Bandwidth-Efficient and Scalable GEMV Accelerator for PIM Systems
    Fan Yang, Shunchen Shi, Peiheng Zhang, Xueqi Li*.
    2025 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)
  13. [CAL'25] Exploring the DIMM PIM Architecture for Accelerating Time Series Analysis
    Shunchen Shi, Fan Yang, Zhichun Li, Xueqi Li (correspondence), Ninghui Sun.
    IEEE Computer Architecture Letter
  14. [DAC'25] BlockPIM: Optimizing Memory Management for PIM-enabled Long-Context LLM Inference
    Zhichun Li, Jun Zhou, Xueqi Li (correspondence), Ninghui Sun.
    The 62nd Design Automation Conference (DAC-62)
  15. [JCST'25] FuHsi: Shifting Base-calling Closer to Sequencer via In-Cache Acceleration
    Yewen Li, Guangming Tan (correspondence), Xueqi Li (correspondence).
    Journal of Computer Science and Technology (JCST)
  16. [BIBM'24] ProXplore: A GPU-Enhanced Protein Discovery Engine
    Zewen Sun, Peiheng Zhang, Xingzhuo Fu, and Xueqi Li (correspondence).
    International Conference on Bioinformatics and Biomedicine (BIBM24)
  17. [HPCC'24] LazyCAT: Efficient Fine-Grained Cache Partitioning with Two Boundaries
    Chuanqi Zhang, Xueqi Li, Ninghui Sun, Yungang Bao, Sa Wang
    2024 IEEE International Conference on High Performance Computing and Communications (HPCC)
  18. [ICCD'24] CoPIM: A Collaborative Scheduling Framework for Commodity Processing-in-memory Systems
    Shunchen Shi, Xueqi Li (correspondence), Zhaowu Pan, Peiheng Zhang, Ninghui Sun.
    The 42nd IEEE International Conference on Computer Design (ICCD24)
  19. [ASPLOS'24] BeeZip: Towards An Organized and Scalable Architecture for Data Compression
    Ruihao Gao, Zhichun Li, Guangming Tan, Xueqi Li (correspondence).
    Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS24)
  20. [BIBM'23] TransCaller: An End-to-end Accelerated Transformer-based Nanopore Basecaller on GPUs
    Di Xu, Peiheng Zhang, Yang Zhang, Shunchen Shi, Xueqi Li (correspondence).
    IEEE International Conference on Bioinformatics & Biomedicine (BIBM23)
    Towards AI4S, this is our first job!
  21. [TPDS'23] Accelerating k-Shape Time Series Clustering Algorithm Using GPU
    Xun Wang, Ruibao Song, Junmin Xiao, Tong Li Xueqi Li (correspondence).
    Transactions on Parallel and Distributed Systems
  22. [HPCA'23] NvWa: Enhancing Sequence Alignment Accelerator Throughput via Hardware Scheduling
    Yewen Li, Xueqi Li (correspondence), Ruihao Gao, Wanqi Liu, Guangming Tan
    The 29th IEEE International Symposium on High-Performance Computer Architecture (HPCA-29)
  23. [SC'22] AlphaSparse: Generating High Performance SpMV Codes Directly from Sparse Matrices
    Zhen Du, Jiajia Li, Yinshan Wang, Xueqi Li, Guangming Tan, Ninghui Sun
    The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC22)
  24. [BIBM'22] Crescent: A GPU-based Targeted Nanopore Sequence Selector
    Tong Li, Xueqi Li (correspondence), Yewen Li, Ruibao Song, Xun Wang (correspondence)
    IEEE International Conference on Bioinformatics & Biomedicine (BIBM22)
  25. [DAC'22] MetaZip: A High-throughput and Efficient Accelerator for DEFLATE
    Ruihao Gao, Xueqi Li (correspondence), Yewen Li, Xun Wang, Guangming Tan
    The 59th Design Automation Conference (DAC-59)
  26. [JCST'21] PIM-Align: A Processing-in-Memory Architecture for FM-index Search Algorithm
    Xueqi Li, Guangming Tan, Ninghui Sun
    Journal of Computer Science and Technology (JCST) (IF: 1.506)
  27. [MICRO'19] MEDAL: Scalable DIMM based Near Data Processing Accelerator for DNA Seeding Algorithm
    Wenqin Huangfu, Xueqi Li, Shuangchen Li, Xing Hu, Peng Gu, Yuan Xie
    The 52nd IEEE/ACM International Symposium on Microarchitecture (MICRO-52)
  28. [DAC'19] Efficient System Architecture in the Era of Monolithic 3D: Dynamic Inter-tier Interconnect and Processing-in-Memory
    Dylan Stow, Itir Akgun, Wenqin Huangfu, Yuan Xie, Xueqi Li, Gabriel H. Loh
    The 56th Design Automation Conference (DAC-56)
  29. [AACBB'19] Scalable In-Memory System for Genomic Analysis (publised work)
    Xueqi Li
    HPCA 2019 Workshop on Accelerator Architecture In Computational Biology and Bioinformatics
  30. [ICPP'18] Accelerating FM-index Search for Genomic Data Processing
    Yuanrong Wang, Xueqi Li, Dawei Zang, Guangming Tan, Ninghui Sun
    The 47th International Conference on Parallel Processing
  31. [AACBB'18] The Genomic Benchmark Suite: Characterization and Architecture Implications
    Xueqi Li, Guangming Tan, Yuanrong Wang, Ninghui Sun
    HPCA 2018 Workshop on Accelerator Architecture In Computational Biology and Bioinformatics
  32. [PPoPP'18] High-performance genomic analysis framework with in-memory computing
    Xueqi Li, Guangming Tan, Bingchen Wang, Ninghui Sun
    The 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
  33. [BIBM'16] Accelerating Large-Scale Genomic Analysis with Spark
    Xueqi Li, Guangming Tan, Chunming Zhang, Xu Li, Zhonghai Zhang, Ninghui Sun
    The IEEE International Conference on Bioinformatics and Biomedicine

Funding and Awards

  • 存储与计算融合基础科学中心 - (NSFC，架构与系统课题执行负责人，2025.01-2030.12)
  • RISC-V相关项目 - (2024.01-2030.12)
  • 混合精度高能效存算一体芯片架构及关键技术 - (NSFC，基金重大子课题负责人，2025.01-2029.12)
  • NSFC Youth Program - (国家自然科学基金青年基金项目, F204, 2023.01-2025.12)
  • National Key R&D Program of China (国家重点研发计划，总体组成员，子课题负责人, 2022.10-2025.10)
  • National Postdoctoral Program for Innovative Talents (14 in Computer Science, 400 in China, 博新计划, 2021.07-2023.07)
  • ········································································
  • Before graduation
  • ········································································
  • National Scholarship (Ph.D.) - 2019
  • Ray Wu Prize (13 Winners in China or Singapore) - 2018
  • Travel Grants for HPCA - 2019
  • TANG Lixin Award, University of Chinese Academy of Sciences (60/~45479 students) - 2018
  • Travel Grants for SIGPLAN PAC/PPoPP 18 - 2018
  • Director Special Award (XIA Peisu Award) - 2017
  • National Scholarship - 2013 & 2012

Professional Activities

  • PC Member: BIBM.
  • Reviewer: TPDS, TC, TVLSI, TCAD.
  • Artifact Evaluation Committee, PPoPP, 2021, 2022
  • Session Chair, NPC, 2020
  • Data Space Summit and Computility Infrastructure Seminar, 2023