Cunyang Wei

Department of Computer Science

University of Maryland

College Park, MD, US

cunyang [at] umd.edu

I am a Ph.D. student at the University of Maryland, College Park, advised by Prof. Abhinav Bhatele in the Parallel Software and Systems Group (PSSG). My current research focuses on parallel optimization for large-scale GNNs, performance variability, and collective communication.

Prior to joining UMD, I completed my Master’s degree at the Institute of Computing Technology (ICT), University of Chinese Academy of Sciences, Beijing, China, in 2023, where I was advised by Prof. Haipeng Jia. During my time at ICT, I focused on irregular matrix multiplication, resulting in first-author publications in TPDS, ICPP, and HPCC.

My research interests include high-performance computing, parallel algorithms, and optimizing AI workloads for modern hardware. I have been honored with awards such as the National Scholarship of China and Outstanding Graduate of Beijing.

For additional details, please refer to my full CV.

selected publications

ICS

Skew-aware Adaptive All-to-allv Algorithms for Dynamic Deep Learning Workloads

Cunyang Wei and Abhinav Bhatele

In ACM International Conference on Supercomputing (ICS), 2026

Bib PDF Website

@inproceedings{wei2026alltoallv,
  title = {Skew-aware Adaptive All-to-allv Algorithms for Dynamic Deep Learning Workloads},
  author = {Wei, Cunyang and Bhatele, Abhinav},
  booktitle = {ACM International Conference on Supercomputing (ICS)},
  year = {2026},
}

IPDPS

The Case of the Elusive Application Performance on Production GPU Supercomputers

Cunyang Wei, Keshav Pradeep, and Abhinav Bhatele

In Proceedings of the IEEE International Parallel & Distributed Processing Symposium (IPDPS), 2026

Bib PDF Website

@inproceedings{wei2026variability,
  title = {The Case of the Elusive Application Performance on Production GPU Supercomputers},
  author = {Wei, Cunyang and Pradeep, Keshav and Bhatele, Abhinav},
  booktitle = {Proceedings of the IEEE International Parallel \& Distributed Processing Symposium (IPDPS)},
  year = {2026},
}

Plexus: Taming Billion-edge Graphs with 3D Parallel GNN Training

Aditya K. Ranjan, Siddharth Singh, Cunyang Wei, and 1 more author

In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC), 2025

Bib PDF Website

@inproceedings{ranjan2025plexus,
  title = {Plexus: Taming Billion-edge Graphs with 3D Parallel GNN Training},
  author = {Ranjan, Aditya K. and Singh, Siddharth and Wei, Cunyang and Bhatele, Abhinav},
  booktitle = {Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (SC)},
  year = {2025},
}

TPDS

IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs

Cunyang Wei, Haipeng Jia, Yunquan Zhang, and 3 more authors

IEEE Transactions on Parallel and Distributed Systems (TPDS), 2024

Bib PDF Website

@article{wei2024irgemm,
  title = {IrGEMM: An Input-Aware Tuning Framework for Irregular GEMM on ARM and X86 CPUs},
  author = {Wei, Cunyang and Jia, Haipeng and Zhang, Yunquan and Yao, Jianyu and Li, Chendi and Cao, Wenxuan},
  journal = {IEEE Transactions on Parallel and Distributed Systems (TPDS)},
  year = {2024},
  publisher = {IEEE},
}

ICPP

IATF: An Input-Aware Tuning Framework for Compact BLAS Based on ARMv8 CPUs

Cunyang Wei, Haipeng Jia, Yunquan Zhang, and 2 more authors

In International Conference on Parallel Processing (ICPP), 2022

Bib PDF Website

@inproceedings{wei2022iatf,
  title = {IATF: An Input-Aware Tuning Framework for Compact BLAS Based on ARMv8 CPUs},
  author = {Wei, Cunyang and Jia, Haipeng and Zhang, Yunquan and Xu, Liusha and Qi, Ji},
  booktitle = {International Conference on Parallel Processing (ICPP)},
  year = {2022},
}