计算机科学与技术系

Department of Computer Science and Technology

 

Education background

Bachelor of Automatic Control, Tsinghua University, Beijing, China, 1970;

Master of Computer Science & Technology, Tsinghua University, Beijing, China, 1982.

Social service

China Computer Federation: Deputy Executive Chair (2004-);

Department of Computer Science and Technology, Tsinghua University: Director of High Performance Computing Institute (2000-2008);

Tsinghua University: Member of Academic Evaluation Committee (2002-2008);

China Education and Research Grid (ChinaGrid): Vice Chair (2002-);

China Natural Science Foundation Grid (NSFCGrid): Steering Committee Member (2006-);

ICPP 2011: Vice Chair of Program Committee (2011);

SOSP 2007: PC Member (2007).

Areas of Research Interests/ Research Projects

Parallel and Distributed Computing, Network Storage and Disaster Recovery

Compute Architecture, CPU design

Compiler Techniques

National Basic Research Program of China (The 973 Program): Structure-Independent Disaster Recovery Center: Theory and Implementation (2008-2012);

National Natural Science Foundation of China: Peer-to-peer computing and Wide-Area Virtual Platform (2005-2008);

National 863 High-Tech Program: High-End Fault-Tolerant Computer Assessment (2008-2010);

National Science and Technology Infrastructure Funding: Network Computing and Application System for Bioinformatics (2004-2008);

"211" Research Funding by China Ministry of Education: Supporting Platform for China Education and Research Grid (ChinaGrid) (2002-2008);

Intel Research Funding: Security of Cloud Storage (2009-2010);

EMC Research Funding: Campus Storage Cloud (2008-2010);

HP Labs Research Funding: Grid Monitoring (2006-2009).

Research Status

As the leading scientist and professor in computer architecture, I have been directing the research of our department in four areas, namely Computer Cluster, CPU Design, Grid and Cloud computing, and Network Storage and Disaster Recovery.

1. In computer cluster area, I led the development of Tsinghua Discovery Series Computer Clusters, which have been applied to many fields such as weather forecast and network information security. We have gained practical experience in cluster design and assessment. Specifically, we have designed a user-level file system to support consistent file states for checkpoint and restart. Its related paper was published in ACM ICS 2008. The OpenMP Compiler we developed and released has been adopted by HP and AMD as the compiler for their products, and by many foreign universities as the platform for their research. We have also developed a suite of cluster assessment techniques that cover the full system, and are able to identify various system faults caused by hardware, software installation, system configuration and driver mismatch.

2. In CPU design area, I led the development of THUMP107, an embedded CPU running at the highest frequency in China at that time. Based on this work, we have put forward a new Network on Chip (NoC) architecture in which NoC, instead of CPU, maintains the consistency of cache. With computing and communication separated, this architecture eases the design of multicore CPUs and enhances the scalability of CPU.

3. In grid and cloud computing area, we have proposed a method for deploying grid services dynamically and remotely without restarting the service container. This technology has been adopted by Globus Toolkits 4 (GT4), the most famous grid middleware around the world. I led the development of Network Computing and Application System for Bioinformatics, which has been put into operation with over 50,000 daily users. We have developed a community-based data sharing and storage technology, as well as methods of automatic on-demand software deployment and quick virtual cluster construction. Based on the above work, we developed Tsinghua Cloud, the first cloud computing platform in China with more than 15,000 registered users and 400 communities.

4. In network storage and disaster recovery area, we have put forward a flexible and scalable network storage architecture, and developed Tsinghua Mass Storage Network System (TH-MSNS), which has nearly 100 successful deployments in industries and areas of audit, public security, telecommunication, and education. We devised ways of scaling striped volumes of array and out-of-band storage, and published related papers in ACM Transactions on Storage and IEEE Transactions on Computers, respectively. We developed a new coding scheme, named GRID, which has features of high fault tolerance and high storage utilization, and is regarded as one of the most classic erasure codes by IEEE Fellow Darrell D.E. Long. We also developed structure-independent techniques for the fast disaster recovery of data centers, which greatly reduce the investment for disaster recovery, improving recovery speed at the same time.

Honors And Awards

National Award for Science and Technology Progress, First Class-Information Security Management System for Ministry of Information Industry (2002);

National Award for Science and Technology Progress, Second Class-High-Performance Cluster and Mass Storage System (2007);

National Award for Science and Technology Progress, Second Class-China Education and Research Grid (2008);

Best Academic Course Award by Ministry of Education-Computer Architecture (2008);

Science and Technology Progress Award by Ministry of Education, First Class-High-Performance Computer Assessment Techniques (2009).

Academic Achievement

[1] Weimin Zheng, Binxing Fang. Structure-independent disaster recovery: Concept, architecture and implementations. Science in China Series F: Information Sciences, vol. 52, no. 5, pp. 813-823, 2009

[2] Weimin Zheng. An Introduction to Tsinghua Cloud. Science in China Series F: Information Sciences, vol. 53, no.5, to appear, 2010

[3] Jidong Zhai, Wenguang Chen, Weimin Zheng. PHANTOM: predicting performance of parallel applications on large-scale parallel machines using a single node. Proc. 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPOPP 2010), Bangalore, India, 2010, pp. 305-314

[4] Guangyan Zhang, Jiwu Shu, Wei Xue, and Weimin Zheng. Design and Implementation of an Out-of-Band Virtualization System for Large SANs. IEEE Transactions on Computers, vol. 56, no. 12, pp. 1654-1665, 2007

[5] Xing Zhou, Wenguang Chen and Weimin Zheng. Cache Sharing Management for Performance Fairness in Chip Multiprocessors. Proc. 18th International Conference on Parallel Architectures and Compilation Techniques (PACT 2009), Raleigh, North Carolina, USA, 2009, pp. 384-393

[6] Yongwei Wu, Yulai Yuan, Guangwen Yang, Weimin Zheng. Load Prediction Using Hybrid Model for Computational Grid. Proc. 8th IEEE/ACM International Conference on Grid Computing (Grid 2007), Austin, Texas, USA, 2007, pp. 235-242

[7] Yongwei Wu, Kai Hwang, Yulai Yuan, Weimin Zheng. Adaptive Workload Prediction of Grid Performance in Confidence Windows. IEEE Transactions on Parallel and Distributed Systems, In Press, 2010

[8] Ruini Xue, Wenguang Chen, Weimin Zheng. CprFS: a user-level file system to support consistent file states for checkpoint and restart. Proc. 22nd ACM International Conference on Supercomputing (ICS 2008), Island of Kos, Aegean Sea, Greece, 2008, pp. 114-123

[9] Hongliang Yu, Dongdong Zheng, Ben Y. Zhao, Weimin Zheng. Understanding User Behavior in Large-scale Video Streaming Services. Proc. 1st Eurosys Conference (EuroSys 2006), Leuven, Belgium, 2006, pp. 333-344

[10] Weimin Zheng and Zhizhong Tang. Computer Architecture (2nd edition). Tsinghua University Press, Beijing, 1998 (in Chinese).