Shengzhong Feng
Ph.D., Principal Investigator,Professor, Director of the National Open Innovation Platform for Artificial Intelligence Power, National Council Government Special Allowance Expert, Hundred-Talent of Chinese Academy of Sciences
Email: fengshengzhong@@gdiist.cn
Personal Profile
Prof. Shengzhong Feng, a Researcher and Doctoral Supervisor, is the leader of the High-Performance Intelligent Computing Research Group. He holds a Bachelor of Science from the University of Science and Technology of China and a Doctor of Engineering from Beijing Institute of Technology. Prof. Feng is a recipient of the Chinese Academy of Sciences Hundred-Talent Program. His previous roles include Associate Researcher at the Institute of Computing Technology, Chinese Academy of Sciences, Visiting Professor at the University of Toronto, Researcher at the Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, and Researcher at the National Supercomputing Center in Shenzhen.
His main research interests include high-performance computing, big data technologies, artificial intelligence, and bioinformatics. He has been a key member of teams that won the Chinese Academy of Sciences Award for Outstanding Contributions, the Second National Prize for Progress in Science and Technology, the First Prize in the Overseas Students Innovation and Entrepreneurship Competition, the First Prize in the Microsoft HPC Challenge, and the National Advanced Individual in Science and Technology against COVID-19. As the technical lead, he participated in the construction of the first and second phases of the major scientific infrastructure project, the Shenzhen Supercomputing Center. He has presided over or participated in dozens of major national, provincial, and municipal key scientific projects and has been involved in drafting national, provincial, and municipal science and technology plans. He has published over a hundred papers and has supervised dozens of master’s and doctoral students and postdoctoral researchers.
Laboratory of High-Performance Intelligent Computing
High-performance computing is a focal point of international scientific competition and plays a critical role in national scientific innovation, social development, and industrial upgrading. Challenges in high-performance computing include memory wall issues, reliability and availability, scalable parallel algorithm design and parallel programming, and low-power computing. Brain-inspired computing, a highly interdisciplinary field combining brain science, information technology, and mathematics, is a promising new direction to address issues of power consumption, memory access, reliability, and scalability, drawing significant attention from the academic and industrial communities. The group focuses on the research of brain-inspired computing application ecosystem technologies, targeting international frontiers and national strategic needs. Research directions include hardware-algorithm co-design for brain-inspired computing, brain-inspired computing models and programming models, foundational operator libraries for brain-inspired chips, integration of numerical and intelligent computing methods, mixed-precision computing techniques, low-power computing, and application demonstrations.
Representative publications
1. Jintao Meng, Chen Zhuang, Peng Chen, Mohamed Wahib, Bertil Schmidt, Xiao Wang, Haidong Lan, Dou Wu, Minwen Deng, Yanjie Wei, Shengzhong Feng: Automatic Generation of High-Performance Convolution Kernels on ARM CPUs for Deep Learning. IEEE Trans. Parallel Distributed Syst. 33(11): 2885-2899 (2022)
2. Jinzhi Lin, Shengzhong Feng, Yun Zhang, Zhile Yang, Yong Zhang: A novel deep neural network based approach for sparse code multiple access. Neurocomputing 382: 52-63 (2020)
3. Shengzhong Feng, Li Genguo, Li Xuelei, Qi Fumin, Huang Dian, Wan Yi, Wu Jincheng. Emerging high-performance computing industry applications and development strategies. Journal of the Chinese Academy of Sciences, 2019, 34(6): 640-647.
4. Zhendong Bei, Zhibin Yu, Huiling Zhang, Wen Xiong, Cheng-Zhong Xu, Lieven Eeckhout, Shengzhong Feng: RFHOC: A Random-Forest Approach to Auto-Tuning Hadoop's Configuration. IEEE Trans. Parallel Distributed Syst. 27(5): 1470-1483 (2016)
5. Jintao Meng, Sangmin Seo, Pavan Balaji, Yanjie Wei, Bingqiang Wang, Shengzhong Feng: SWAP-Assembler 2: Optimization of De Novo Genome Assembler at Extreme Scale. ICPP 2016: 195-204
6. Jintao Meng, Bingqiang Wang, Yanjie Wei, Shengzhong Feng, Pavan Balaji: SWAP-Assembler: scalable and efficient genome assembly towards thousands of cores. BMC Bioinform. 15(S-9): S2 (2014)
7. Yaobin He, Haoyu Tan, Wuman Luo, Shengzhong Feng, Jianping Fan: MR-DBSCAN: a scalable MapReduce-based DBSCAN algorithm for heavily skewed data. Frontiers Comput. Sci. 8(1): 83-99 (2014)
8. Shengzhong Feng, Elisabeth R. M. Tillier: A fast and flexible approach to oligonucleotide probe design for genomes and gene families. Bioinform. 23(10): 1195-1202 (2007)
9. Guangming Tan, Lin Xu, Zhenghua Dai, Shengzhong Feng, Ninghui Sun: Regular Paper: A Study of Architectural Optimization Methods in Bioinformatics Applications. Int. J. High Perform. Comput. Appl. 21(3): 371-384 (2007)
10. Guangming Tan, Shengzhong Feng, Ninghui Sun: Cache oblivious algorithms for nonserial polyadic programming. J. Supercomput. 39(2): 227-249 (2007)
11. Guangming Tan, Shengzhong Feng, Ninghui Sun: Biology - Locality and parallelism optimization for dynamic programming algorithm in bioinformatics. SC 2006: 78
12. Shengzhong Feng, Guangming Tan, Lin Xu, Ninghui Sun, Zhiwei Xu. High-performance algorithm research for the Dawning 4000H bioinformatics processing machine. Journal of Computer Research and Development, 2005, 46（2）：1053-1058.
