Haohuan Fu

From geohpgc
Revision as of 02:55, 12 April 2023 by Lcw (talk | contribs) (→‎Research Highlights)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Haohuan:

Haohuan Fu|付昊桓

付昊桓.jpg


Professor, Department of Earth System Science, Tsinghua University
Deputy Director, National Supercomputing Center in Wuxi
Email: haohuan AT tsinghua.edu.cn
Address: Room S817, Mengminwei Building, Tsinghua University, Beijing, China

Research Interests

  • Extreme-Scale Computing on Heterogeneous Supercomputers: one of my research interest is to explore the numerical methods, parallelization schemes, performance tuning techniques, as well as redesigning strategies for mapping some of the most challenging scientific applications, such as atmospheric modeling, and earthquake simulation, onto emerging many-core, and reconfigurable architectures, and to enable depiction of extreme-scale scientific scenarios on leadership peta to exa-scale supercomputers.
  • Data Mining Methods for Analyzing Scientific Data Sets: facing a fast growth in the volume of data from both observations and simulations, we explore parallel data mining methods, enabled by the emerging heterogeneous architectures, to acclerate the process of making new discoveries.
  • Fusion of the above two.
  • Application-specific hardware customization.

Research Highlights

  • Real-Time Simulation of a Random Quantum Circuit Using a New Sunway Supercomputer: A performance of 1.2 Eflops (single-preicision), or 4.4 Eflops (mixed-precision) for simulating a 10x10x(1+40+1) circuit (a new milestone for classical simulation of RQC), using about 42 million Sunway cores. The time to sample Goolge Sycamore in a simulation way is reduced from years to 304 seconds (2021 ACM Gordon Bell Prize)[1].
  • Climate Modeling on Sunway TaihuLight: (1) The work started with refactoring[2] and redesign[3] of the entire Community Atmospheric Model (over half million lines of code) for Sunway TaihuLight, achieving 3.4 SYPD for 25km global atmospheric simulation and close-to-observation simulation of hurricane Katrina lifecycle; a sustainable double-precision performance of over 3.3 PFlops (750-m resolution) of the dynamical-core using 10,075,000 cores (2017 ACM Gordon Bell Prize finalist). (2) The work was then extended to a coupled climate model, CESM 1.3 (with a full coupling of atmosphere, ocean, land and sea-ice models), and achieved a first high resolution coupled climate model for heterogeneous supercomputers, CESM-HR_sw1.0 (https://github.com/ihesp/CESM_SW) (2020)[4]. (3) The model generates an unprecedented 600-year high-resolution climate modeling result data set[5].
  • Non-linear earthquake simulation: (1) We adopted comprehensive memory-related optimizations to resolve TaihuLight's bandwidth constraints, and proposed on-the-fly compression, which doubles the maximum problem size and further improves the performance by 24%; the resulting design achieved 15% of the peak, using 160,000 MPI processes, 10,400,000 cores, and enabled simulation for 18-Hz and 8-meter scenarios (2017 ACM Gordon Bell Prize), one of the Top 10 Research Achievements of Tsinghua University in 2017)[6]. (2) The work was later extended to support the description of complex topography, with case studies on simulating the Wenchuan earthquake that scales to 10 million cores on Sunway TaihuLight (2018)[7]. (3) The potential of using customized hardware architectures and mixed-precision numerical schemes is also studied on FPGA devices, with one FPGA chip to provide equivalent performance to over 200 Intel X86 cores or over 500 Sunway cores (2022)[8].
  • AI-enabled Remote Sensing Image Fusing and Analysis for Global Change Studies: (1) We improve the land cover classification accuracy by integrating free and public high-resolution Google Earth images (HR-GEI) with Landsat Operational Land Imager (OLI) and Enhanced Thematic Mapper Plus (ETM+) imagery, combining both texture and spectral features to achieve a better land cover map[9]. (2) We improve national and global scale land cover mapping from 10m to 3m resolution, by jointly optimizing the network parameters and correcting the noisy labels with a novel online noise correction approach[10]. (3) We propose a novel domain adaptive tree detection method, i.e., a Multi-level Attention Domain Adaptation Network (MADAN)[11], to support cross-regional oil palm tree counting, detection, and growing status monitoring[12].

Related Papers

  1. Yong Liu, Xin Liu, Fang Li, Haohuan Fu, Yuling Yang, Jiawei Song, Pengpeng Zhao, Zhen Wang, Dajia Peng, Huarong Chen, Chu Guo, Heliang Huang, Wenzhao Wu, Dexun Chen, “Closing the “quantum supremacy” gap: achieving real-time simulation of a random quantum circuit using a new Sunway supercomputer”, Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp, 1-12, 2021 (2021 ACM Gordon Bell Prize).
  2. Haohuan Fu, Junfeng Liao, Wei Xue, Lanning Wang, et al., "Refactoring and Optimizing the Community Atmosphere Model (CAM) on the Sunway TaihuLight Supercomputer", in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC16), pp. 969-980, Salt Lake City, Utah, US, 2016.
  3. Haohuan Fu, Junfeng Liao, Nan Ding, et al., "Redesigning CAM-SE for Peta-Scale Climate Modeling Performance and Ultra-High Resolution on Sunway TaihuLight", in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC17), 12 pages, 2017 (ACM Gordon Bell finalist, one out of the three in the world).
  4. Shaoqing Zhang, Haohuan Fu*, Lixin Wu*, et al., "Optimizing high-resolution Community Earth System Model on a heterogeneous many-core supercomputing platform", Geoscientific Model Development, Vol. 13, no. 10, pp. 4809-4829, 2020.
  5. Ping Chang, Shaoqing Zhang, Gokhan Danabasoglu, Stephen G Yeager, Haohuan Fu, et al., "An unprecedented set of high-resolution earth system simulations for understanding multiscale interactions in climate variability and change", Journal of Advances in Modeling Earth Systems, Vol. 12, no. 12, pp. e2020MS002298, 2020.
  6. Haohuan Fu, Conghui He, Bingwei Chen, Zekun Yin, et al., "18.9-Pflops Nonlinear Earthquake Simulation on Sunway TaihuLight: Enabling Depiction of 18-Hz and 8-Meter Scenarios", in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC17), 12 pages, 2017 (2017 ACM Gordon Bell Prize).
  7. Bingwei Chen, Haohuan Fu, Yanwen Wei, Conghui He, Wenqiang Zhang, Yuxuan Li, Wubin Wan, Wei Zhang, Lin Gan, Zhenguo Zhang, Guangwen Yang, Xiaofei Chen, "Simulating the Wenchuan earthquake with accurate surface topography on Sunway TaihuLight", SC18: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 517-528, 2018.
  8. Bingwei Chen, Haohuan Fu*, Wayne Luk, Guangwen Yang, “A fully-customized dataflow engine for 3D earth- quake simulation with a complex topography”, Science China: Information Sciences, Vol. 65, no. 152103, pp. 1-152103, 2022.
  9. Weijia Li, Runmin Dong, Haohuan Fu*, Jie Wang, Le Yu, and Peng Gong, "Integrating Google Earth imagery with Landsat data to improve 30-m resolution land cover mapping", Remote Sensing of Environment, Vol. 237, pp. 111563, 2020.
  10. Runmin Dong, Cong Li, Haohuan Fu*, Jie Wang, Weijia Li, Yi Yao, Lin Gan, Le Yu, Peng Gong*. "Improving 3-m resolution land cover mapping through efficient learning from an imperfect 10-m resolution map", Remote Sensing, Vol. 12, no. 9, pp. 1418, 2020.
  11. Juepeng Zheng, Haohuan Fu, Weijia Li*, Wenzhao Wu, Yi Zhao, Runmin Dong, Le Yu, "Cross-regional oil palm tree counting and detection via a multi-level attention domain adaptation network", ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 167, pp. 154-177, 2020.
  12. Juepeng Zheng, Haohuan Fu, Weijia Li, Wenzhao Wu, Le Yu, Shuai Yuan, Wai Yuk William Tao, Tan Kian Pang, and Kasturi Devi Kanniah, "Growing status observation for oil palm trees using Unmanned Aerial Vehicle (UAV) images", ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 173, pp. 95-121, 2021.

Education

2005 – 2009: PhD, Department of Computing, Imperial College, UK

2003 – 2005: MPhil, Department of CS, City University of Hong Kong

1993 – 2003: B.E., DCST, Tsinghua University

Honors & Awards

  • 2021 ACM Gordon Bell Prize (random quantum circuit simulation, forth author and co-corresponding author)
  • 2021 NSFC Distinguished Young Scientist Fund (Division of Multi-Disciplinary Research)
  • 2020 May 4th Youth Medal of China
  • 2018 May 4th Youth Medal of Jiangsu Province
  • 2017 Top 10 Research Achievements of Tsinghua University
  • 2017 ACM Gordon Bell Prize (non-linear earthquake simulation, lead author)
  • 2016 ACM Gordon Bell Prize (atmospheric dynamic solver, third author and co-corresponding author)
  • 2015 Tsinghua-Inspur Computational Earth Science Young Researcher Award
  • 2015 Best Paper Award (3 out of 278 submissions), IEEE International Conference on Tools with Artificial Intelligence (ICTAI)
  • 2015 Significant Paper in 25 Years, one of the 27 papers selected from the 1,765 publications in the first 25 years of the International Conference on Field Programmable Logic and Application (FPL)
  • 2008 Best Paper Award, International Conference on Field Programmable Technology (FPT)
  • 2007 Best Poster Award, Computer System Research Day, Imperial College London

Publications

For a full publication list, please refer to my Google scholar page.