I am an Assistant Professor of Department of Computer Science and Engineering at University of California Santa Cruz. Prior to that, I obtained my Ph.D. degree from the Department of Computer Science, North Carolina State University (NCSU), advised by Dr. Xipeng Shen and Dr. Yan Solihin. I have been working as a research intern at SystemResearch@Google since 2021, where I am advised by Dr. David E. Culler.
My research interests are in computer architecture, security, and ML systems and architecture.
I am always looking for self-motivated Ph.D. students interested in these areas. Feel free to contact me at yxu314@ucsc.edu if you are interested in working with me!
News
- Three papers are accepted by MICRO 2026. Congratulations to Yuxin and Gangqi, and thanks to all collaborators!
- Decoupled-DSM: multi-host CXL memory security.
- HYDRA: CXL tiered-memory caching.
- ShareMMU: secure address translation for SoCs.
- Three papers are accepted by ISCA 2026. Congratulations to Xiangyue, and thanks to all collaborators!
- CDFD: NVLink-based multi-GPU memory management.
- LIBRA: multi-GPU page prefetching.
- FEnc2: efficient private inference.
- Honored to receive the prestigious NSF CAREER Award! Grateful to the NSF for their support!
- Two papers are accepted by ASPLOS 2026. Congratulations to Gangqi, and thanks to all collaborators!
- PIPM: page migration for multi-host CXL memory.
- Fanmem: failure-atomic transactions for CXL memory.
- Two papers are accepted by MICRO 2025. Congratulations to Chuanhan, Qizhong, Xiangyue, and thanks to all collaborators!
- AIORE: efficient security support for CXL memory.
- GPU Cache Eviction Hints: security and performance implications.
- Our research about ML inference on serverless computing is accepted by HPDC 2025.
- Our research about ML inference on serverless computing is accepted by SIGMETRICS 2025.
- Our research about disaggregated-memory key-value stores is accepted by VLDB 2025.
- Our research about system-on-chip security is accepted by DATE 2025.
- Serving as the program committee for ISCA 2025.
- Our research about ML inference on serverless computing is accepted by HPDC 2024.
- Our research about system-on-chip security has been awarded by NSF. Thank you for your support, NSF!
- Serving as the program committee for MICRO 2024.
- Received the 2024 Outstanding Dissertation Award from NCSU for my Ph.D. thesis on “Data-Centric Architecture Support for Security”.
- Serving as the program committee for ASPLOS 2025.
- Our research about trusted execution environments is accepted by HPCA 2024.
- Serving as the Registration Chair for ISCA 2023. Please consider attending!
Recent Selected Publications (full list)
The names of the students in my lab are underlined.
[MICRO 2026] Decoupled-DSM: A Scalable Secure Trusted Execution Environment for Multi-Host CXL Disaggregated Shared Memory
Yuxin Yang, Yuanchao Xu
The 59th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2026.
to appear[MICRO 2026] HYDRA: Hybrid DRAM Caching for Dynamic Complementary Multi-to-One Page Mapping in CXL Tiered Memory
Gangqi Huang, Heiner Litz, Yuanchao Xu
The 59th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2026.
to appear[MICRO 2026] ShareMMU: Supporting Secure Address Translation Sharing among Untrusted Accelerators
Faiz Alam, Mohamed Tarek Ibn Ziad, Yuanchao Xu, Abdulrahman Mahmoud, Aamer Jaleel, Greg Byrd
The 59th IEEE/ACM International Symposium on Microarchitecture (MICRO), 2026.
to appear[ISCA 2026] Coarse-Grained Duplication First, Fine-Grained Deduplication Later: Duplication-Centric Multi-GPU Memory Management
Xiangyue Huang, Yanan Guo, Yuanchao Xu
The 53rd International Symposium on Computer Architecture (ISCA), 2026.
to appear[ISCA 2026] LIBRA: A High-Accuracy, Cost-Aware, and Coordinated Multi-GPU Page Prefetcher
Xiangyue Huang, Yanan Guo, Yuanchao Xu
The 53rd International Symposium on Computer Architecture (ISCA), 2026.
to appear[ISCA 2026] FEnc2: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding
Ran Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu, Fan Yao, Wujie Wen
The 53rd International Symposium on Computer Architecture (ISCA), 2026.
to appear[ASPLOS 2026] CPU-Oblivious Offloading of Failure-Atomic Transactions for Disaggregated Memory
Cheng Chen, Chencheng Ye, Yuanchao Xu, Xipeng Shen, Xiaofei Liao, Hai Jin, Wenbin Jiang, Yan Solihin
The 31st ACM International Conference on Architecture Support for Programming Languages and Operating Systems (ASPLOS), 2026.
[Paper][ASPLOS 2026] PIPM: Partial and Incremental Page Migration for Multi-host CXL Disaggregated Shared Memory
Gangqi Huang, Heiner Litz, Yuanchao Xu
The 31st ACM International Conference on Architecture Support for Programming Languages and Operating Systems (ASPLOS), 2026. Acceptance rate: 89/840=10.60%
[Paper][MICRO 2025] Efficient Security Support for CXL Memory through Adaptive Incremental Offloaded (Re-)Encryption
Chuanhan Li, Jishen Zhao, Yuanchao Xu
The 58th International Symposium on Microarchitecture (MICRO), 2025. Acceptance rate: 124/597=20.77%
[Paper][MICRO 2025] Security and Performance Implications of GPU Cache Eviction Priority Hints
Qizhong Wang, Xiangyue Huang, Yanan Guo, Yuanchao Xu
The 58th International Symposium on Microarchitecture (MICRO), 2025. Acceptance rate: 124/597=20.77%
[Paper][HPDC 2025] FluidFaaS: A Dynamic Pipelined Solution for Serverless Computing with Strong Isolation-based GPU Sharing
Xinning Hui, Yuanchao Xu, and Xipeng Shen
The 34th International Symposium on High-Performance Parallel and Distributed Computing (HPDC), 2025.
[Paper][SIGMETRICS 2025] Exploring Function Granularity for Serverless Machine Learning Application with GPU Sharing
Xinning Hui, Yuanchao Xu, and Xipeng Shen
The 2025 ACM on Measurement and Analysis of Computing Systems (SIGMETRICS), 2025. Acceptance rate: 18.18%
[Paper]