I am a PhD student in ECE at the University of Illinois Urbana-Champaign, advised by Prof. Jian Huang in Illinois PlatformX. My research explores hardware/software co-design techniques for building efficient ecosystems for Neural Processing Units (NPUs), such as TPUs. Although the NPU hardware architecture provides massive computational power for machine learning (ML) workloads, their real-world performance and efficiency depend critically on the surrounding ecosystem. My work aims to define the hardware/software interfaces and abstractions that best balance complexity, expressiveness, performance, and efficiency by determining which optimizations belong in hardware, which belong in software, and which require coordinated support across both. I build the hardware mechanisms and software systems to make NPUs faster, more cost-effective, and more energy-efficient.
Beyond NPUs, I am also interested in other ML accelerators such as GPUs and inter-core connected AI chips (i.e., Graphcore IPUs, Tenstorrent). I am also exploring how to leverage AI/LLM agents to develop the NPU ecosystem.
Publications
- Hardware/Software Co-design for NPU Ecosystem
-
ReGate: Enabling Power Gating in Neural Processing UnitsYuqi Xue , Jian HuangMICRO 2025Best Artifact Award
-
Hardware-Assisted Virtualization of Neural Processing Units for Cloud PlatformsYuqi Xue , Yiqi Liu , Lifeng Nai , Jian HuangMICRO 2024Best Paper Runner-Up IEEE Micro Top Picks 2024
-
System Virtualization for Neural Processing UnitsYuqi Xue , Yiqi Liu , Jian HuangHotOS 2023
-
V10: Hardware-Assisted NPU Multi-tenancy for Improved Resource Utilization and FairnessYuqi Xue , Yiqi Liu , Lifeng Nai , Jian HuangISCA 2023
-
ReGate: Enabling Power Gating in Neural Processing Units
Show more publications Show fewer publications
- ML Compiler for Inter-core Connected AI Chips
-
Elk: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler TechniquesYiqi Liu , Yuqi Xue , Noelle Crawford , Jilong Xue , Jian HuangMICRO 2025
-
Scaling Deep Learning Computation over the Inter-Core Connected Intelligence ProcessorYiqi Liu , Yuqi Xue , Yu Cheng , Lingxiao Ma , Ziming Miao , Jilong Xue , Jian HuangSOSP 2024
-
Elk: Exploring the Efficiency of Inter-core Connected AI Chips with Deep Learning Compiler Techniques
- Memory and Storage for AI Accelerators
-
Managing Scalable Direct Storage Accesses for GPUs with GoFSShaobo Li* , Yirui Eric Zhou* , Yuqi Xue , Yuan Xu , Jian HuangSOSP 2025
-
G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor MigrationsHaoyang Zhang* , Yirui Eric Zhou* , Yuqi Xue , Yiqi Liu , Jian HuangMICRO 2023
-
Managing Scalable Direct Storage Accesses for GPUs with GoFS
- Other Publications
-
Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMsXingang Guo , Yaxin Li , Xiangyi Kong , Yilan Jiang , Xiayu Zhao , Zhihua Gong , Yufan Zhang , Daixuan Li , Tianle Sang , Beixiao Zhu , Gregory Jun , Yingbing Huang , Yiqi Liu , Yuqi Xue , et al.NeurIPS 2025
-
SkyByte: Architecting an Efficient Memory-Semantic CXL-based SSD with OS and Hardware Co-designHaoyang Zhang* , Yuqi Xue* , Yirui Eric Zhou , Shaobo Li , Jian HuangHPCA 2025
-
RackBlox: A Software-Defined Rack-Scale Storage System with Network-Storage Co-DesignBenjamin Reidys , Yuqi Xue , Yiqi Liu , Daixuan Li , Bharat Sukhwanim , Wen-mei Hwu , Deming Chen , Sameh Asaad , Jian HuangSOSP 2023
-
IceClave: A Trusted Execution Environment for In-Storage ComputingLuyi Kang* , Yuqi Xue* , Weiwei Jia* , Xiaohao Wang , Jongryool Kim , Changhwan Youn , Myeong Joon Kang , Hyung Jin Lim , Bruce Jacob , Jian HuangMICRO 2021
-
Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs
* Co-primary authors.
Service
Tutorial
- NexNPU: Building an Open-Source Ecosystem for Neural Processing Units (colocated with ISCA'26) 2026
Organizing Committee
Peer Review
- IEEE Computer Architecture Letters 2022, 2023, 2024
- ACM Transactions on Architecture and Code Optimization 2024, 2025
- Student Program Committee — IEEE/ACM International Symposium on Microarchitecture (MICRO) 2026
Artifact Evaluation Committee
- IEEE/ACM International Symposium on Microarchitecture (MICRO) 2022
- USENIX Symposium on Operating Systems Design and Implementation (OSDI) 2022, 2023
- USENIX Annual Technical Conference (ATC) 2022, 2023
- IEEE International Symposium on High-Performance Computer Architecture (HPCA) 2023
Awards
- Qualcomm Graduate Award Apr 2025
- IEEE Micro Top Picks from 2024 Computer Architecture Conferences Jan 2025
- Best Paper Runner-Up, MICRO 2024 Nov 2024
- Student Travel Grants (ISCA 2023, MICRO 2024) Oct 2024
- Dan Vivoli Endowed Fellowship Sep 2024
Education
- PhD in Electrical and Computer Engineering 2021 – PresentUniversity of Illinois Urbana-Champaign
- BS in Electrical and Computer Engineering, BS in Mathematics 2017 – 2021University of Illinois Urbana-Champaign
- High School 2014 – 2017Shenzhen Middle School
Work Experience
- Graduate Research Assistant August 2021 – PresentSystems Platform Research Group, UIUC
- Research Intern September 2023 – January 2024Google LLC (Remote)
- Research Intern June 2023 – August 2023Google LLC, Sunnyvale, CA
Teaching
- ECE 511 — Computer Architecture (Graduate TA) Spring 2023, Spring 2024List of Teachers Ranked as Excellent By Their Students
- ECE 411 — Computer Organization and Design (Graduate TA) Spring 2022, Fall 2023
- ECE 522 — Emerging Memory and Storage Systems (Graduate TA) Spring 2023
- ECE 310 — Digital Signal Processing (Undergraduate Grader) Jan – Jul 2020