About Me
I am a Professor in the Computer Science Department of University of California, Los Angeles. My research broadly covers computer systems, spanning programming languages, compilers, runtime/operating systems, distributed systems, and computer architecture. My current focus includes two main areas: (1) building infrastructures for future cloud computing, particularly user-defined clouds, and (2) creating scalable and cost-effective infrastructures for AI applications.
I was among the first academic researchers to address the problem of software bloat, a field that eventually led to ONR's $200M TPCP program. We recently developed kvcached, a GPU memory sharing system that has been used by many large enterprises to support their production LLM serving workloads across more than 10K GPUs. In recognition of these contributions, I received the 2018 Dahl-Nygaard Junior Prize and am an ACM Distinguished Scientist.
Professional
Current Projects Some Recent Papers
- The Open Virtual GPU Project (Prism, OSDI 2026, Concerto, ICML 2026, kvcached, GVM)
- Systems that detect and mitigate silent data corruption from CPU/GPU errors (SOSP 2025)
- Systems for affordable, efficient, and scalable AI/ML (SIGCOMM 2020, OSDI 2021, NSDI 2023-b, NSDI 2023-c, NSDI 2024-b, MLSys 2024, Concerto, ICML 2026, Pythia)
- Systems for resource-disaggregated datacenters (OSDI 2020, PLDI 2022-a, OSDI 2022 Best Paper, NSDI 2023-a, NSDI 2023-d, NSDI 2024-a, OSDI 2024-a, OSDI 2024-b)
- System design for emerging datacenter hardware (PLDI 2019, PLDI 2020, ASPLOS 2021, PLDI 2021-a, ASPLOS 2022-a, ASPLOS 2022-b, PLDI 2022-b, OSDI 2022-b)
- IoT usability and security (SEC 2018, FSE 2020-a)
- Graph systems for static code analysis and other workloads (ASPLOS 2017-a, ASPLOS 2017-b, OSDI 2018, EuroSys 2019, PLDI 2021-b, TOCS 2021, EuroSys 2023)
- Big Data systems and their runtime support (SOSP 2015, ASPLOS 2015, OSDI 2016, ASPLOS 2018, SOSP 2019-a, SOSP 2019-b)
- Software bloat detection and optimization (ECOOP 2015, PLDI 2018, FSE 2020-b)
Research Group
- Junyi Shu, PostDoc Researcher starting 2025, Outstanding PhD Dissertation Award at PKU
- Shan Yu, Ph.D. student starting Fall 2022, Intel DRA Award, Cisco "You Amaze 2" Technical Excellence Award, AWS AI Fellowship
- Zhenting Zhu, Ph.D. student starting Fall 2023, Yao Award, Andrew Yao Class at Tsinghua, Gold Medalist IOI 2018
- Shu Anzai, Ph.D. student starting Fall 2023, Funai Overseas Scholarship, University of Tokyo
- Yicheng Liu, Ph.D. student starting Fall 2024, co-advised with Sam Kumar, Top Graduate of Shanghai Jiaotong University
- Yue Jin, Ph.D. student starting Fall 2025, Most Innovative Spirit Award from the Ant Group
Alumni
- Shi Liu, Ph.D. 2025, UCLA to Databricks
- Jiyuan Wang (LinkedIn), Ph.D. 2025, UCLA to AWS to Tulane University
- Haoran Ma, Ph.D. 2024, UCLA to ByteDance AI Infra
- Yifan Qiao (LinkedIn), Ph.D. 2024, UCLA to Postdoc Berkeley to Inferact
- Christian Navasca, Ph.D. 2023, UCLA to BreezeML
- Pengzhan Zhao, M.S. 2023, UCLA to BreezeML to AMD
- Chenxi Wang, PostDoc 2018-2022, UCLA to Associate Professor, Institute of Computing Technology, Chinese Academy of Sciences
- Jonathan Eyolfson, PostDoc 2018-2022, UCLA to Assistant Professor in teaching stream, University of Toronto
- John Thorpe, Ph.D. 2022, UCLA to BreezeML Inc.
- Arthi Padmanabhan (LinkedIn), Ph.D. 2022, UCLA to Assistant Professor, Harvey Mudd College
- Usama Hameed, M.S. 2022, UCLA to Apple
- Yuanqi Li, startup founder
- Khanh Nguyen, Ph.D. 2019, UCLA to Assistant Professor at Texas A&M University
- Kai Wang, Ph.D. 2019, UCLA to Facebook System & Infrastructure
- Zhiqiang Zuo, PostDoc 2015-2018, UCI to Assistant Professor at Nanjing University
- Lu Fang, Ph.D. 2017, UCI to Facebook AI, co-creator of PyTorch and ONNX
- Keval Vora, Ph.D. 2017, co-advised with Rajiv Gupta, UCR to Assistant Professor at Simon Fraser University
- Shen Teng, M.S. 2021, UCLA to AWS
- Gaohong Liu, M.S. 2021, UCLA to RED to ByteDance Seed
- Cheng Cai, M.S. 2020, UCLA to Facebook
- Bojun Wang, M.S. 2019, UCI to Arista Networks
- Guanzhou Hu, CSST 2019, UCLA to Ph.D. student at UWisc
- Tim Nguyen, B.S. 2017, UCI to Facebook
- Aftab Hussain, M.S. Fall 2017
- Matthew Hartz, B.S. 2015
- Jianfei Hu, M.S. 2015, UCI to Google to ClickHouse
- Michael Li, 2018 summer intern from Newport Senior High to University of Washington
- Chengxi Li, 2017 summer intern from Beckman High to Berkeley CS
- Emily Hu, 2016 summer intern from Northwood High to Berkeley CS to Capital One
- Lawrence Xu, 2016 summer intern from University High to Purdue CS
- Louis Zhang, 2014 summer intern from Troy High to Berkeley CS
- Ankur Gupta, 2014 summer intern from University High to Regent's Scholar at UCSD CS
- Wendy Wei, 2013 summer intern from University High to MIT CS
- Allen Min, 2012 summer intern from Whitney High to UCI CS
- Jonathon Tsai, 2012 summer intern from Whitney High to UCI CS
Teaching
- CS 239: Large-Scale Machine Learning Systems, Spring 2020, Spring 2025, Spring 2026
- CS 111: Operating Systems, Spring 2019, Winter 2020, Winter 2021, Winter 2022, Winter 2026
- CS 214: Big Data Systems, Fall 2018, Fall 2019, Fall 2020, Fall 2021, Winter 2025, Winter 2026
Recent Services
- ASPLOS 2026, PC Co-Chair
Released Software Systems Our GitHub Repos
- The Open GPU Sharing Project
- Atlas: A hybrid data plane for remote memory applications
- DRust: An ownership-based DSM system
- VQPy: An object-oriented approach to video analytics queries
- Midas: Soft Memory as an OS service
- Hermit: Remote memory swap via feedback-directed asynchrony
- Canvas: An isolated and adaptive swap system for remote memory
- MemLiner: A remote-memory-friendly runtime system
- Mako: A low-pause evacuating collector for memory-disaggregated datacenters
- Dorylus: Affordable and scalable GNN training
- JPortal: Java Virtual Machine support for Intel PT
- Chianina: Graph system for context- and flow-sensitive static analysis
- Semeru: A memory-disaggregated managed runtime
- Reducto: On-camera frame filtering for video analytics
- Grapple: Graph system for finite-state property checking
- RStream: A single-machine, disk-based graph mining system
- Graspan: Disk-based parallel graph system for dynamic transitive closure
Why I Believe
I am a Protestant Christian. I regularly attend and help with several campus fellowships at both UCLA and UC Irvine.
- How can one be a CS professor and a Christian? collected by George Varghese
Contact Information
harryxu at cs dot ucla dot edu
http://www.cs.ucla.edu/~harryxu
Office:
Engineering VI, Room 496A
Computer Science Department
BOX 951596, UCLA
Los Angeles, CA 90095-1596
Work: 310-794-7145
Last updated: May 4, 2026. Maintained by OpenAI Codex.