Publications

Huawei Zhang, Chunwei Xia, Zheng Wang (2026). KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference. In ACM MobiSys ‘26.

Shuoming Zhang, Jiacheng Zhao, Qiuchu Yu, Chunwei Xia, Zheng Wang, Xiaobing Feng, Huimin Cui (2026). The new compiler stack: a survey on the synergy of LLMs and compilers. In CCF THPC.

Shuaijiang Li, Jiacheng Zhao, Ying Liu, Shuoming Zhang, Lei Chen, Yijin Li, Yangyu Zhang, Zhicheng Li, Runyu Zhou, Xiyu Shi, Chunwei Xia, Yuan Wen, Xiaobing Feng, Huimin Cui (2026). From Threads to Tiles: T2T, a Compiler for CUDA-to-NPU Translation via 2D Vectorization. In CGO 2026.

Jiayu Zhao, Chunwei Xia, Zheng Wang (2025). Leveraging Compilation Statistics for Compiler Phase Ordering. IPDPS'25.

Shenghao Qiu, Chunwei Xia, Zheng Wang (2025). Accelerating Tensor-train Decomposition on Graph Neural Networks. IPDPS'25.

Shuoming Zhang, Jiacheng Zhao, Chunwei Xia, Zheng Wang, Yunji Chen, Huimin Cui (2024). Introducing Compiler Semantics into Large Language Models as Programming Language Translators: A Case Study of C to x86 Assembly. In EMNLP ‘24.

Chunwei Xia, Jiacheng Zhao, Qianqi Chen, Zheng Wang, Xiaobing Feng, Huimin Cui (2024). Optimizing Deep Learning Inference via Global Analysis and Tensor Expression. In ASPLOS ‘24.

Huanting-Wang, Zhanyong-Tang, Shin Hwei Tan, Chunwei Xia, Zheng Wang (2024). Combining Structured Static Code Information and Dynamic Symbolic Traces for Software Vulnerability Prediction. ICSE'24.

Chunwei Xia, Jiacheng Zhao, Huimin Cui, Xiaobing Feng (2022). HOPE: a heterogeneity-oriented parallel execution engine for inference on mobiles. In HTL ‘22.

Ning Lin, Xiaoming Chen, Chunwei Xia, Jing Ye, Xiaowei Li (2021). Optimizing Deep Learning Inference via Global Analysis and Tensor Expression. In ATS ‘21.