Yitu Wang is a Ph.D. candidate in computer engineering in Duke ECE Department under the supervision of Prof. Yiran Chen. He received B.S.E. in Microelectronics from Fudan University in 2020. His research interests focus on computer architecture, including machine learning acceleration, near data processing for data-intensive applications such recommendation system, approximate nearest neighbor search and retrieval-augmented generation (RAG) for LLM, and algorithm-architecture co-design for deep learning system.

📖 Educations

• 2020.08 - Present, Ph.D. candidate in Computer Engineering at Duke University, Durham, NC, USA.
• 2016.09 - 2020.06, B.S.E in Microelectronics at Fudan University, Shanghai, China.

💻 Experiences

• 2024.06 - 2023.09, System Architect Intern in Samsung Memory Solution Lab, San Jose, California, USA.
• 2023.05 - 2023.08, Memory Research Intern in Samsung Memory Solution Lab, San Jose, California, USA.
• 2022.05 - 2022.08, Research Intern in Samsung Memory Solution Lab, San Jose, California, USA.

📝 Publications

Preprints

• [In Submission] Yitu Wang, Minxue Tang, Hanqiu Chen, Shiyu Li, Andrew Chang, Cong “Callie” Hao, Hai “Helen” Li, Yiran Chen, “FedRepre: End-to-End Acceleration of Federated Learning System with Client Representative”.

First-author papers

• [ISCA’24] Yitu Wang, Shiyu Li, Qilin Zheng, Linghao Song, Zongwang Li, Andrew Chang, Hai “Helen” Li, Yiran Chen, “NDSearch: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing”. 2024 ACM/IEEE 51st IEEE/ACM Annual International Symposium on Computer Architecture (ISCA).

• [DAC’24] Hanqiu Chen*, Yitu Wang*, Vitorio Cargnini, Reza Soltaniyeh, Dongyang Li, Gongjin Sun, Pradeep Subedi, Andrew Chang, Yiran Chen, Cong “Callie” Hao, “ICGMM: CXL-enabled Memory Expansion with Intelligent Caching Using Gaussian Mixture Model”. 61st IEEE/ACM Annual Design Automation Conference, 2024. (*equal contribution)

• [ESWEEK’23/TECS’23] Yitu Wang, Shiyu Li, Qilin Zheng, Andrew Chang, Hai “Helen” Li, Yiran Chen, “EMS-I: An Efficient Memory System Design with Specialized Caching Mechanism for Recommendation System”. ACM Transactions on Embedded Computing System, 2023.

• [ICCAD’21] Yitu Wang, Zhenhua Zhu, Fan Chen, Mingyuan Ma, Guohao Dai, Yu Wang, Hai “Helen” Li, and Yiran Chen, “ReRec: In-ReRAM Acceleration with Access-Aware Mapping for Personalized Recommendation”. 2021 IEEE/ACM International Conference on Computer Aided Design.

• [DATE’20] Yitu Wang, Fan Chen, Linghao Song, C.J. Richard Shi, Hai “Helen” Li, and Yiran Chen, “ReBoc: Accelerating Block-Circulant Neural Networks in ReRAM”. 2020 Design, Automation & Test in Europe Conference & Exhibition.

Co-author papers

• [DAC’24] Qilin Zheng, Ziru Li, Jonathan Ku, Yitu Wang, Brady Taylor, Yiran Chen, “Improving the Efficiency of In- Memory-Computing Macro with a Hybrid Analog-Digital Computing Mode For Lossless Neural Network Inference”. 61st IEEE/ACM Annual Design Automation Conference, 2024.

• [TC’24] Shiyu Li, Yitu Wang, Edward Hanson, Andrew Chang, Yang Seok Ki, Hai “Heleln” Li, Yiran Chen, “NDRec: Accelerating the Training of Recommendation Models through Near-Data Processing”, IEEE Transaction on Computers, 2024.

• [ISCAS’24] Qilin Zheng, Shiyu Li, Yitu Wang, Ziru Li, Hai “Helen” Li, Yiran Chen, “Hybrid Digital/Analog Memoristorbased Computing Architecture for Sparse Deep Learning Acceleration”. 2024 International Symposium on Circuits and Systems.

• [MICRO’23] Edward Hanson, Shiyu Li, Guanglei Zhou, Feng Cheng, Yitu Wang, Hai “Helen” Li, and Yiran Chen, “Si-kintusgi: Towards Recovering Golden-like Performance of Defective Many-core Spatial Architecture for AI”. Proceedings of the 56th Annual IEEE/ACM International Symposium on Microarchitecture, 2023.

• [DAC’23] Qilin Zheng, Shiyu Li, Yitu Wang, Ziru Li, Hai “Helen” Li, and Yiran Chen, “Accelerating Sparse Attention with Reconfigurable Non-Volatile Processing-in-Memory Architecture”. 60th IEEE/ACM Annual Design Automation Conference, 2023.

• [CVPR’22] Minxue Tang, Xuefei Ning, Yitu Wang, Yu Wang and Yiran Chen, “FedGP: Correlation-Based Active Client Selection for Heterogeneous Federated Learning”. Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pttern Recognition.

• [EMC2-NeurIPS’19] Jingyang Zhang, Huanrui Yang, Fan Chen, Yitu Wang, and Hai “Helen” Li, “Exploring Bit-Slice Sparsity in Deep Neural Networks for Efficient ReRAM-Based Deployment”. Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing NeurIPS Edition, 2019.

👨‍💼 Services

• Reviwer of CAL, CVPR, TC, TPDS, TCAD, TCAS-I, TVLSI, TODAES.