Wenlai Zhao

Wenlai.jpg


Contact

Mail: zhaowenlai@mail.tsinghua.edu.cn

Office: Room S814, Meng Minwei Science Building, Tsinghua University, Beijing, 100084

Current State

Postdoctoral Research Fellow, Department of Computer Science and Technology, Tsinghua University

Director of AI Division, National Supercomputing Center in Wuxi, Jiangsu Province

Experience

  • 2018 - present, Postdoc Research Fellow, Department of Computer Science & Technology, Tsinghua University
  • 2016 - present, Director of AI Division, National Supercomputing Center in Wuxi, Jiangsu Province
  • 2011 - 2018, Ph.D. Candidate, Department of Computer Science & Technology, Tsinghua University
  • 2015 - 2016, Visiting Student, Department of Computing, Imperial College London
  • 2007 - 2011, Bachelor Degree, Department of Computer Science & Technology, Tsinghua University

Research

  • Research Interests:

1) High performance computing based on heterogeneous and reconfigurable platform

2) Machine Learning and Deep Learning

  • Research Experience:

1) Optimization of HEVC decoder on ARM-based devices

2) FPGA-based Markov Random Field (MRF) inference algorithm

3) Convolutional Neural Network (CNN) training framework based on CPU/FPGA hybrid platform

4) High-performance deep learning library based on SW26010 many-core processor (swDNN)

5) Distributed deep learning framework on Sunway TaihuLight Supercomputer (swCaffe)

Publications

1) Wenlai Zhao, Haohuan Fu and Guangwen Yang, ”A Fully-Pipelined FPGA Design for Tree- reweighted Message Passing Algorithm”, Field-Programmable Custom Computing Machines (FCCM) 2014

2) Wenlai Zhao, Haohuan Fu, Wayne Luk, and Guangwen Yang, ”Patra: Parallel Tree-reweighted Message Passing Architecture”, Field Programmable Logic and Applications (FPL) 2014

3) Zihong Lv, Haohuan Fu, Wenlai Zhao, Guangwen Yang, ”Optimizing Complex Stencils in Elastic Wave Simulation Methods on GPUs”, HPC China 2014

4) Bangtian Liu, Haohuan Fu, Lin Gan, Wenlai Zhao and Guangwen Yang, ”Optimizing Residue Number Reverse Converters through Bitwise Arithmetics on FPGAs”, Field-Programmable Custom Computing Machines (FCCM) 2015

5) Wenlai Zhao, Haohuan Fu, Wayne Luk, Teng Yu, Shaojun Wang, Bo Feng, Yuchun Ma and Guangwen Yang, "F-CNN: An FPGA-based Framework for Training Convolutional Neural Networks", The 27th Annual IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) 2016

6) Haohuan Fu, Jingheng Xu, Lin Gan, Chao Yang, Wei Xue, Wenlai Zhao, Xinliang Wang and Guangwen Yang, "Unleashing the Performance Potential of CPU-GPU Platforms for the 3D Atmospheric Euler Solver", The 27th Annual IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) 2016

7) Teng Yu, Bo Feng, Mark Stillwell, Jose G F Coutinho, Wenlai Zhao, Shuang Liang, Wayne Luk, Alexander Wolf, and Yuchun Ma, "Relation-Oriented Resource Allocation for Multi-Accelerator Systems", The 27th Annual IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP) 2016

8) Jiarui Fang, Haohuan Fu, Wenlai Zhao, Bingwei Chen, Weijie Zheng, Guangwen Yang, "swDNN: A Library for Accelerating Deep Learning Applications on Sunway TaihuLight Supercomputer", 31st IEEE International Parallel & Distributed Processing Symposium (IPDPS) 2017

9)Wenlai Zhao, Haohuan Fu, Jiarui Fang, Weijie Zheng, Lin Gan and Guangwen Yang, "Optimizing Convolutional Neural Networks on Sunway TaihuLight Supercomputer", ACM Transactions on Architecture and Code Optimization (TACO) 15 (1), 13, 2018

10) Liandeng Li, Jiarui Fang, Haohuan Fu, Jinlei Jiang, Wenlai Zhao, Conghui He, Xin You, Guangwen Yang, "swCaffe: A Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight", IEEE International Conference on Cluster Computing (CLUSTER) 2018

11) Liandeng Li, Teng Yu, Wenlai Zhao, Haohuan Fu􏰀, Chenyu Wang, Li Tan, Guangwen Yang, John Thomson, "Large-Scale Hierarchical k-means for Heterogeneous Many-Core Supercomputers", Supercomputing (SC) 2018