Associate Professor · School of Computer Science and Engineering · Sun Yat-sen University (SYSU)

[Official Homepage]  ·  [Google Scholar]

I am an Associate Professor at the School of Computer Science and Engineering, Sun Yat-sen University, and a member of the Interdisciplinary Research Center (xRC) led by Prof. Yutong Lu and Prof. Nong Xiao. My research focuses on scalable and efficient computing systems for AI and HPC, through innovations in hardware operator design, task scheduling, resource management, and algorithm–system codesign.

I currently serve as an Executive Member of the High Performance Computing Technical Committee and the Storage Technical Committee of the China Computer Federation (CCF). I have served on the program committees of HiPC, CCGrid, and HPC China, and as a reviewer for IEEE TC, IEEE TPDS, ACM TACO, IEEE IOTJ, Journal of Supercomputing, Journal of Systems Architecture, CCF THPC, SC, and ICML.

I am actively recruiting highly motivated Ph.D., Master’s, and undergraduate students. I maintain long-term research collaborations with Tencent and Alibaba Group on large language model and diffusion model systems, with research internship opportunities available. Please feel free to reach out via email with your CV.

News

• [2026-04] One paper (EcoServe) conditionally accepted at OSDI 2026 — congratulations to Hongbin Zhang, Taosheng Wei, and Zhenyi Zheng.
• [2025-08] Two papers (Ghidorah, AuLoRA) accepted at ICCD 2025 — congratulations to Jinhui Wei and Xiao Shi.
• [2025-07] Joined Sun Yat-sen University as an Associate Professor.
• [2025-07] One paper (TD-Pipe) accepted at ICPP 2025 — congratulations to Hongbin Zhang.
• [2025-07] One paper (coMtainer) accepted at SC 2025.
• [2025-01] One paper (ORFA) accepted at WWW 2025 — congratulations to Yuhao Gu.
• [2024-12] One paper accepted at TPDS.
• [2024-12] One paper (IncrCP) accepted at VLDB 2025 — congratulations to Qingyin Lin.
• [2024-10] One paper (Concerto) accepted at ASPLOS 2025 — congratulations to Shenggan Cheng.
• [2024-04] One paper (APTMoE) accepted at SC 2024 — congratulations to Yuanxin Wei.
• [2023-11] One paper accepted at PPoPP 2024.

Selected Publications

* denotes corresponding author. See full list on Google Scholar.

Conference Papers

• [VLDB 2025] [CCF-A] Qingyin Lin, Jiangsu Du*, Rui Li, Zhiguang Chen, Wenguang Chen, and Nong Xiao, “IncrCP: Decomposing and Orchestrating Incremental Checkpoints for Effective Recommendation Model Training.”
• [ICPP 2025] [CCF-B] Hongbin Zhang, Taosheng Wei, Zhenyi Zheng, Jiangsu Du*, Zhiguang Chen*, and Yutong Lu, “TD-Pipe: Temporally-Disaggregated Pipeline Parallelism Architecture for High-Throughput LLM Inference.”
• [ICCD 2025] [CCF-B] Jinhui Wei, Ye Huang, Yuhui Zhou, Jiazhi Jiang, Jiangsu Du*, Hongbin Zhang, Taosheng Wei, Zhenyi Zheng, Zhiguang Chen, and Yutong Lu, “Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism.”
• [ICCD 2025] [CCF-B] Xiao Shi, Jiangsu Du, Zhiguang Chen, and Yutong Lu, “AuLoRA: Fine-Grained Loading and Computation Orchestration for Efficient LoRA LLM Serving.”
• [ASPLOS 2025] [CCF-A] Shenggan Cheng, Shengjie Lin, Lansong Diao, Hao Wu, Siyu Wang, Chang Si, Ziming Liu, Xuanlei Zhao, Jiangsu Du, Wei Lin, and Yang You, “Concerto: Automatic Communication Optimization and Scheduling for Large-Scale Deep Learning.”
• [SC 2025] [CCF-A] Yuhao Gu, Haoquan Chen, Xianjie Chen, Jiangsu Du, Zhiguang Chen, Nong Xiao, Xianwei Zhang, and Yutong Lu, “coMtainer: Compilation-Assisted HPC Container Images with Enhanced Adaptability.”
• [WWW 2025] [CCF-A] Yuhao Gu, Junyu Chen, Jiangsu Du, Xiaoxi Zhang, and Xianwei Zhang, “ORFA: A WebAssembly-based Runtime to Optimize Remote Procedure Calls with Complete Expressiveness.”
• [PPoPP 2024] [CCF-A] Jiangsu Du, Jinhui Wei, Jiazhi Jiang, Shenggan Cheng, Dan Huang, Zhiguang Chen, and Yutong Lu, “Liger: Interleaving Intra- and Inter-Operator Parallelism for Distributed Large Model Inference.”
• [SC 2024] [CCF-A] Yuanxin Wei, Jiangsu Du*, Jiazhi Jiang, Xiao Shi, Xianwei Zhang, Dan Huang*, Nong Xiao, and Yutong Lu, “APTMoE: Affinity-Aware Pipeline Tuning for MoE Models on Bandwidth-Constrained GPU Nodes.”
• [INFOCOM 2024] [CCF-A] Shengyuan Ye, Jiangsu Du*, Liekang Zeng, Wenzhong Ou, Xiaowen Chu, Yutong Lu, and Xu Chen*, “Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference.”
• [DATE 2024] [CCF-B] Yuanxin Wei, Shengyuan Ye, Jiazhi Jiang, Xu Chen, Dan Huang*, Jiangsu Du*, and Yutong Lu, “Communication-Efficient Model Parallelism for Distributed In-situ Transformer Inference.”
• [ICS 2022] [CCF-B] Jiangsu Du, Jiazhi Jiang, Yang You, Dan Huang, and Yutong Lu, “Handling Heavy-tailed Input of Transformer Inference on GPUs.”
• [ICPP 2022] [CCF-B] Jiazhi Jiang, Jiangsu Du, Dan Huang, Dongsheng Li, Jiang Zheng, and Yutong Lu, “Characterizing and Optimizing Transformer Inference on ARM Many-Core Processor.”
• [ICCD 2023] [CCF-B] Jiazhi Jiang, Rui Tian, Jiangsu Du, Dan Huang, and Yutong Lu, “MixRec: Orchestrating Concurrent Recommendation Model Training on CPU-GPU Platform.”
• [ICCD 2020] [CCF-B] Jiangsu Du, Minghua Shen, and Yunfei Du, “A Distributed In-Situ CNN Inference System for IoT Applications.”

Journal Papers

• [TPDS] [CCF-A] Jiangsu Du, Xin Zhu, Minghua Shen, Yunfei Du, Yutong Lu, Nong Xiao, and Xiangke Liao, “Co-designing Transformer Architectures for Distributed Inference with Low Communication.”
• [TPDS] [CCF-A] Jiangsu Du, Yuanxin Wei, Shengyuan Ye, Jiazhi Jiang, Xu Chen, Dan Huang, and Yutong Lu, “Model Parallelism Optimization for Distributed Inference via Decoupled CNN Structure.”
• [TACO] [CCF-A] Jiangsu Du, Jiazhi Jiang, Jiang Zheng, Hongbin Zhang, Dan Huang, and Yutong Lu, “Improving Computation and Memory Efficiency for Real-world Transformer Inference on GPUs.”
• [JCST] [CCF-B] Jiangsu Du, Dongsheng Li, Yingpeng Wen, Jiazhi Jiang, Dan Huang, Xiangke Liao, and Yutong Lu, “SAIH: A Scalable Evaluation Methodology for Understanding AI Performance Trend on HPC Systems.”
• [IOTJ] [JCR Q1] Jiangsu Du, Yunfei Du, Dan Huang, Yutong Lu, and Xiangke Liao, “Enhancing Distributed In-Situ CNN Inference in the Internet of Things.”
• [TPDS] [CCF-A] Rui Tian, Jiazhi Jiang, Jiangsu Du, Dan Huang, and Yutong Lu, “Sophisticated Orchestrating Concurrent DLRM Training on CPU/GPU Platform.”
• [TPDS] [CCF-A] Jiazhi Jiang, Jiangsu Du, Dan Huang, Zhiguang Chen, Yutong Lu, and Xiangke Liao, “Full-Stack Optimizing Transformer Inference on ARM Many-Core CPU.”

Courses

Education