Xiaoyu Hao (郝晓宇)

Email: haoxiaoyu@mail.ustc.edu.cn

Hi! I am Xiaoyu Hao, a final-year Ph.D. student in Computer Science and Technology at the University of Science and Technology of China (USTC), advised by Prof. Hong An. I received my Bachelor’s degree in Software Engineering from University of Electronic Science and Technology of China (UESTC) in 2018. My research interests include Computer Architecture, Processor (CPU/NPU) Performance Modeling, and High-Performance Computing.

💡 Job Seeking:
I am actively seeking job opportunities in the industry. If my research and experience align with your team, please contact me. Thank you!

我正在寻找业界的工作，如果您对我的研究方向感兴趣请联系我，谢谢!

You can find my Chinese CV here: Xiaoyu Hao’s CV

中文简历: Xiaoyu Hao’s CV

Selected Publications

  1. (Preprint) Xiaoyu Hao, Sen Zhang, Junshi Chen, and Hong An. MILES: Instruction-Level Simulation of Dense and Sparse Matrix Engines in CPUs with A Unified Performance Model. pdf

  2. (DATE’26) Xiaoyu Hao, Sen Zhang, Liang Qiao, Jun Shi, Junshi Chen, and Hong An. 2026. CISim: ISA-Agnostic Custom Instruction Simulation for General-Purpose Processor. In Design, Automation and Test in Europe Conference (DATE). pdf

  3. (ICS’25) Xiaoyu Hao, Sen Zhang, Liang Qiao, Qingcai Jiang, Jun Shi, Junshi Chen, Hong An, Xulong Tang, Hao Shu, and Honghui Yuan. 2025. CIExplorer: Microarchitecture-aware exploration for tightly integrated custom instruction. In Proceedings of the 39th ACM International Conference on Supercomputing (ICS). pdf

  4. (TPDS’22) Xiaoyu Hao, Tao Fang, Junshi Chen, Jun Gu, Jiawang Feng, Hong An, and Chun Zhao. swMPAS-A: Scaling mpas-a to 39 million heterogeneous cores on the new generation sunway supercomputer. 2022. IEEE Transactions on Parallel and Distributed Systems (TPDS). pdf

  5. (Science Bulletin’22) Jun Gu*, Jiawang Feng*, Xiaoyu Hao*, Tao Fang*, Chun Zhao, Hong An, Junshi Chen, Mingyue Xu, Jian Li, Wenting Han, et al. 2022. Establishing a non-hydrostatic global atmospheric modeling system at 3-km horizontal resolution with aerosol feedbacks on the sunway supercomputer of china. Science Bulletin.

  6. (JIG’20) Xiaoyu Hao, Junfeng Xiong, Xudong Xue, Jun Shi, Ke Wen, Wenting Han, et al. 2020. 3D U-Net with Dual Attention Mechanism for Lung Tumor Segmentation. 2020. Journal of Image and Graphic (JIG).

Competitions and Awards

  1. 2015 UESTC National Scholarship (电子科技大学国家奖学金).

  2. Third prize in both 2018 and 2021 Parallel Application Challenge.

  3. 2023 ACM Gordon Bell Prize for Climate Modelling Finalist.

  4. Outstanding Meteorological Science and Technology Progress in Anhui Province (安徽省优秀气象科技进展).

Research Projects

  1. Domain Specific Archtecture Design and Performance Modeling. The research focuses on: (1) automated custom instruction exploration; (2) performance modeling for irregular custom instructions; and (3) performance modeling for CPU matrix extensions.

  2. Porting and Optimization of an Ultra High Resolution Atmospheric Model (MPAS-A) on the New Generation Sunway Supercomputer. The project includes: (1) addressing severe I/O bottlenecks of MPAS-A on the supercomputer and (2) optimization of computational hotspots for the heterogeneous many-core processors.

  3. Workload Characterization and Performance Analysis for Kunpeng 920 CPU. This research investigates the mapping between PMU events and instruction sequences for the Kunpeng 920 CPU.

  4. Deep Learning for Medical Image Segmentation and Detection.

Last Modified: 2026.06.29