Xi Xie

prof_pic.jpg

About Me

I am a Ph.D. student in the Department of Computer Science and Engineering at the University of Connecticut since Fall 2022, advised by Prof. Caiwen Ding. I obtained my M.S. degree in Geophysics from the Institute of Geophysics, China Earthquake Administration, advised by Prof. Zhongliang Wu.

My research interests include high-performance GPU algorithm design and secure and trustworthy AI/ML systems. I am skilled in C++/CUDA programming and CUDA algorithm design, and I enjoy challenging the performance of official libraries.

News

Aug 02, 2024 I received the Eversource Fellowship. Thanks Uconn Eversource Energy Center!
Jul 22, 2024 I gave a talk at the Artificial Intelligence Hardware (AIHW) Annual Review about my work on MaxK-GNN (ASPLOS 24).
Jun 25, 2024 Our paper AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing has been accepted by ICCAD 24.
Apr 15, 2024 I was invited to be a program committee member of the Great Lakes Symposium on VLSI 2024.
Nov 07, 2023 Our paper MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training has been accepted by ASPLOS 24.

Selected Publications

  1. Preprint
    topk_kernel_0913.png
    RTop-K: Ultra-Fast Row-Wise Top-K Algorithm and GPU Implementation for Neural Networks
    Xi Xie, Yuebo Luo, Hongwu Peng, and 1 more author
    arXiv preprint arXiv:2409.00822, 2024
    HTML PDF
  2. ASPLOS
    maxk_forward_kernel.png
    MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Training
    Xi Xie*, Hongwu Peng*, Kaustubh Shivdikar, and 6 more authors
    In Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2, La Jolla, CA, USA, 2024
    HTML PDF Code
  3. ICCAD
    block_level_partition0517_new.png
    Accel-GCN: High-Performance GPU Accelerator Design for Graph Convolution Networks
    Xi Xie, Hongwu Peng, Amit Hasan, and 7 more authors
    In 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD), 2023
    HTML PDF Code