Ruofan Wu 乌若凡

1st year PhD @ Umich

I am a first year Ph.D. student at University of Michigan, advised by Prof. Mosharaf Chowdhury. I received my Bachelor’s and Master’s degree in computer science at Renmin University of China (RUC) under the supervision of Prof. Feng Zhang. My current research interests lie in scalable machine learning systems and compilers.

Email: ruofanw@umich.edu

Education

2024 - Present: University of Michigan (Umich), Ph.D. student in Computer Science & Engineering, Advisor: Prof. Mosharaf Chowdhury
2021 - 2024: Renmin University of China (RUC), M.E. in Computer Application Technology, Advisor: Prof. Feng Zhang
2017 - 2021: Renmin University of China (RUC), B.E. in Data Science and Big Data Technology

Experience

2023 - 2024: Microsoft, ~~DeepSpeed~~ Bing, Research Intern, Mentor: Dr. Zhen Zheng
2022 - 2023: Alibaba Cloud, Platform of Artificial Intelligence (PAI), Research Intern, Mentor: Dr. Zhen Zheng
2021: Microsoft Research Asia (MSRA), Systems Research Group, Research Intern, Mentor: Dr. Fan Yang, Dr. Jilong Xue
2019 - 2020: North Carolina State University (NCSU), PICTure Research Group, Remote Intern, Advisor: Prof. Xipeng Shen
2019: DELL EMC China Technology R&D Center, Intern

Selected Publications

RECom: A Compiler Approach to Accelerating Recommendation Model Inference with Massive Embedding Columns paper illustration

Zaifeng Pan, Zhen Zheng, Feng Zhang, Ruofan Wu, Hao Liang, Dalin Wang, Xiafei Qiu, Junjie Bai, Wei Lin, Xiaoyong Du
RECom: A Compiler Approach to Accelerating Recommendation Model Inference with Massive Embedding Columns

In ASPLOS, 2024.

Main URL

ROLLER: Fast and Efficient Tensor Compilation for Deep Learning paper illustration

Hongyu Zhu, Ruofan Wu, Yijia Diao, Shanbin Ke, Haoyu Li, Chen Zhang, Jilong Xue, Lingxiao Ma, Yuqing Xia, Wei Cui, Fan Yang, Mao Yang, Lidong Zhou, Asaf Cidon, Gennady Pekhimenko
ROLLER: Fast and Efficient Tensor Compilation for Deep Learning

In OSDI, 2022.

Main URL

TREC: Transient Redundancy Elimination-based Convolution paper illustration

Jiawei Guan, Feng Zhang, Jiesong Liu, Hsin-Hsuan Sung, Ruofan Wu, Xiaoyong Du, Xipeng Shen
TREC: Transient Redundancy Elimination-based Convolution

In NeurIPS, 2022.

Main URL

DREW: Efficient Winograd CNN Inference with Deep Reuse paper illustration

Ruofan Wu, Feng Zhang, Jiawei Guan, Zhen Zheng, Xiaoyong Du, Xipeng Shen
DREW: Efficient Winograd CNN Inference with Deep Reuse

In WWW/TheWebConf, 2022.

Main URL

Cite RECom: A Compiler Approach to Accelerating Recommendation Model Inference with Massive Embedding Columns

@inproceedings{10.1145/3623278.3624761, author = {Pan, Zaifeng and Zheng, Zhen and Zhang, Feng and Wu, Ruofan and Liang, Hao and Wang, Dalin and Qiu, Xiafei and Bai, Junjie and Lin, Wei and Du, Xiaoyong}, title = {RECom: A Compiler Approach to Accelerating Recommendation Model Inference with Massive Embedding Columns}, year = {2024}, isbn = {9798400703942}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3623278.3624761}, doi = {10.1145/3623278.3624761}, booktitle = {Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4}, pages = {268–286}, numpages = {19}, location = {<conf-loc>, <city>Vancouver</city>, <state>BC</state>, <country>Canada</country>, </conf-loc>}, series = {ASPLOS '23} }

Cite ROLLER: Fast and Efficient Tensor Compilation for Deep Learning

@inproceedings {280896, author = {Hongyu Zhu and Ruofan Wu and Yijia Diao and Shanbin Ke and Haoyu Li and Chen Zhang and Jilong Xue and Lingxiao Ma and Yuqing Xia and Wei Cui and Fan Yang and Mao Yang and Lidong Zhou and Asaf Cidon and Gennady Pekhimenko}, title = {{ROLLER}: Fast and Efficient Tensor Compilation for Deep Learning}, booktitle = {16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)}, year = {2022}, isbn = {978-1-939133-28-1}, address = {Carlsbad, CA}, pages = {233--248}, url = {https://www.usenix.org/conference/osdi22/presentation/zhu}, publisher = {USENIX Association}, month = jul }

Cite TREC: Transient Redundancy Elimination-based Convolution

@inproceedings{NEURIPS2022_a995960d, author = {Guan, Jiawei and Zhang, Feng and Liu, Jiesong and Sung, Hsin-Hsuan and Wu, Ruofan and Du, Xiaoyong and Shen, Xipeng}, booktitle = {Advances in Neural Information Processing Systems}, editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh}, pages = {26578--26589}, publisher = {Curran Associates, Inc.}, title = {TREC: Transient Redundancy Elimination-based Convolution}, url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/a995960dd0193654d6b18eca4ac5b936-Paper-Conference.pdf}, volume = {35}, year = {2022} }

Cite DREW: Efficient Winograd CNN Inference with Deep Reuse

@inproceedings{10.1145/3485447.3511985, author = {Wu, Ruofan and Zhang, Feng and Guan, Jiawei and Zheng, Zhen and Du, Xiaoyong and Shen, Xipeng}, title = {DREW: Efficient Winograd CNN Inference with Deep Reuse}, year = {2022}, isbn = {9781450390965}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3485447.3511985}, doi = {10.1145/3485447.3511985}, booktitle = {Proceedings of the ACM Web Conference 2022}, pages = {1807–1816}, numpages = {10}, keywords = {Web systems, Winograd, data reuse, deep reuse}, location = {<conf-loc>, <city>Virtual Event, Lyon</city>, <country>France</country>, </conf-loc>}, series = {WWW '22} }