Page 59 - 2017 Brochure
P. 59
研究員
王建民 Chien-Min Wang
Associate Research Fellow
Ph.D., Electrical Engineering, National Taiwan University
Tel: +886-2-2788-3799 ext. 1703 Fax: +886-2-2782-4814
Email: cmwang@iis.sinica.edu.tw
http://www.iis.sinica.edu.tw/pages/cmwang
• Associate Research Fellow, Institute of Information Science, Academia Sinica (1996-present)
• Assistant Research Fellow, Institute of Information Science, Academia Sinica (1991-1995)
• Ph.D., Electrical Engineering, National Taiwan University (1991)
• B.S., Electrical Engineering, National Taiwan University (1987)
• Best paper award at the 2006 International Conference on Grid and Pervasive Computing.
Research Description computing resources.
My research interest is in the area of parallel and distributed As an increasing number of streaming data applications are moved
computing with an emphasis on software supports and optimization to Clouds, efficient parallel frameworks and distributed file systems
techniques for data-intensive applications. To this end, we have are key to meeting scalability and performance requirements. We
addressed replica and server placement problems in various aim to enhance the provision of QoS in distributed file systems by
distributed environments to improve reliability and performance of developing solutions to meet the bandwidth/latency requirements
the systems. By resolving replication transition problems, replica of each access and improve the overall utilization of storage
placement can adapt to user preferences and system configuration. resources. Concurrently, we aim to extend the general applicability
We have proposed efficient algorithms to improve the aggregate of MapReduce and develop methodology and software tools
bandwidth and reliability of data transfers with multiple servers in that are able to efficiently process streaming data. Virtualization
the systems. We have also investigated resource management is a critical technology for multi-cores and Clouds that allows
problems and proposed bidding-based mechanisms for resource applications running on such systems to be agnostic about the
selection in distributed systems. underlying platforms. Therefore, our research focuses on core
technologies, such as dynamic compilation techniques for binary
Recently, our focus has been on storage and processing of translation, binary optimization targeting multi-core systems, and
streaming data in Clouds and virtualization for multi-cores. efficient runtime support for system-mode virtualization.
Cloud computing is a new and promising paradigm that enables
ubiquitous, convenient, on-demand network access that can be
rapidly provisioned and released to a shared pool of configurable
Publications 6. Jan-Jan Wu, Shu-Fan Shih, Hsiangkai Wang, Pangfeng Liu, and Chien-
Min Wang, “QoS-aware Replica Placement for Grid Computing,”
1. Chien-Min Wang, Chun-Chen Hsu, Pangfeng Liu, Hsi-Min Chen, Concurrency and Computation: Practice and Experience, pp. 193-
and Jan-Jan Wu, “Optimizing Server Placement in Hierarchical Grid 213, Vol. 24, No. 3, March 2012.
Environments,” The Journal of Supercomputing, pp. 267-282, Vo. 42,
No. 3, December 2007. 7. Chien-Min Wang, Tse-Chen Yeh, and Guo-Fu Tseng, “Provision of
Storage QoS in Distributed File Systems for Clouds,” Proceedings of
2. Chun-Chen Hsu, Chien-Min Wang, and Pangfeng Liu, “Optimal the 41th International Conference on Parallel Processing, pp. 189-
Replication Transition Strategy in Distributed Hierarchical Systems,” 198, Pittsburgh, USA, Sep. 2012.
Proceedings of the 22nd IEEE International Parallel and Distributed
Processing Symposium, Miami, Florida, USA, April 2008. 8. Ding-Yong Hong, Jan-Jan Wu, Pen-Chung Yew, Wei-Chung Hsu,
Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang, and Yeh-Ching
3. Chien-Min Wang, Hsi-Min Chen, Chun-Chen Hsu, and Jonathan Lee, Chung, “Efficient and Retargetable Dynamic Binary Translation on
“Dynamic Resource Selection Heuristics for a Non-reserved Bidding- Multicores,” 3IE, pEpE. 6T2r2a-n6s3a2c,tiFoenbsrounaryPa2r0a1l4le.l and Distributed Systems,
b26as,eNdoG. 2ri,dpEp.n1v8ir3o-n1m97e,n2t,0”1F0u. ture Generation Computer Systems, Vol. Vol. 25, No.
4. Chien-Ming Wang, Chi-Chang Huang, and Huan-Ming Liang, “ASDF: 9. Hsiang-Huang Wu, Tse-Chen Yeh, and Chien-Min Wang, “Multiple
An Autonomous and Scalable Distributed File System,” Proceedings Two-Phase Data Processing with MapReduce,” Proceedings of the
of the 11th IEEE/ACM International Symposium on Cluster, Cloud 2014 IEEE International Conference on Cloud Computing, pp. 352-
and Grid Computing, pp. 485-493, Los Angeles, USA, May 2011. 359, Alaska, USA, June 2014.
5. Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang, Jan-Jan Wu, 10. Hsiang-Huang Wu and Chien-Min Wang, “Generalization of
Ding-Yong Hong, Pen-Chung Yew, and Wei-Chung Hsu, “LnQ: Large-Scale Data Processing in one MapReduce job for Coarse-
Building High Performance Dynamic Binary Translators with Grained Parallelism,” to appear in International Journal of Parallel
Existing Compiler Backends,” Proceedings of the 40th International Programming, 2016.
Conference on Parallel Processing, pp. 226-234, Taipei, Taiwan, Sep.
2011.
57
王建民 Chien-Min Wang
Associate Research Fellow
Ph.D., Electrical Engineering, National Taiwan University
Tel: +886-2-2788-3799 ext. 1703 Fax: +886-2-2782-4814
Email: cmwang@iis.sinica.edu.tw
http://www.iis.sinica.edu.tw/pages/cmwang
• Associate Research Fellow, Institute of Information Science, Academia Sinica (1996-present)
• Assistant Research Fellow, Institute of Information Science, Academia Sinica (1991-1995)
• Ph.D., Electrical Engineering, National Taiwan University (1991)
• B.S., Electrical Engineering, National Taiwan University (1987)
• Best paper award at the 2006 International Conference on Grid and Pervasive Computing.
Research Description computing resources.
My research interest is in the area of parallel and distributed As an increasing number of streaming data applications are moved
computing with an emphasis on software supports and optimization to Clouds, efficient parallel frameworks and distributed file systems
techniques for data-intensive applications. To this end, we have are key to meeting scalability and performance requirements. We
addressed replica and server placement problems in various aim to enhance the provision of QoS in distributed file systems by
distributed environments to improve reliability and performance of developing solutions to meet the bandwidth/latency requirements
the systems. By resolving replication transition problems, replica of each access and improve the overall utilization of storage
placement can adapt to user preferences and system configuration. resources. Concurrently, we aim to extend the general applicability
We have proposed efficient algorithms to improve the aggregate of MapReduce and develop methodology and software tools
bandwidth and reliability of data transfers with multiple servers in that are able to efficiently process streaming data. Virtualization
the systems. We have also investigated resource management is a critical technology for multi-cores and Clouds that allows
problems and proposed bidding-based mechanisms for resource applications running on such systems to be agnostic about the
selection in distributed systems. underlying platforms. Therefore, our research focuses on core
technologies, such as dynamic compilation techniques for binary
Recently, our focus has been on storage and processing of translation, binary optimization targeting multi-core systems, and
streaming data in Clouds and virtualization for multi-cores. efficient runtime support for system-mode virtualization.
Cloud computing is a new and promising paradigm that enables
ubiquitous, convenient, on-demand network access that can be
rapidly provisioned and released to a shared pool of configurable
Publications 6. Jan-Jan Wu, Shu-Fan Shih, Hsiangkai Wang, Pangfeng Liu, and Chien-
Min Wang, “QoS-aware Replica Placement for Grid Computing,”
1. Chien-Min Wang, Chun-Chen Hsu, Pangfeng Liu, Hsi-Min Chen, Concurrency and Computation: Practice and Experience, pp. 193-
and Jan-Jan Wu, “Optimizing Server Placement in Hierarchical Grid 213, Vol. 24, No. 3, March 2012.
Environments,” The Journal of Supercomputing, pp. 267-282, Vo. 42,
No. 3, December 2007. 7. Chien-Min Wang, Tse-Chen Yeh, and Guo-Fu Tseng, “Provision of
Storage QoS in Distributed File Systems for Clouds,” Proceedings of
2. Chun-Chen Hsu, Chien-Min Wang, and Pangfeng Liu, “Optimal the 41th International Conference on Parallel Processing, pp. 189-
Replication Transition Strategy in Distributed Hierarchical Systems,” 198, Pittsburgh, USA, Sep. 2012.
Proceedings of the 22nd IEEE International Parallel and Distributed
Processing Symposium, Miami, Florida, USA, April 2008. 8. Ding-Yong Hong, Jan-Jan Wu, Pen-Chung Yew, Wei-Chung Hsu,
Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang, and Yeh-Ching
3. Chien-Min Wang, Hsi-Min Chen, Chun-Chen Hsu, and Jonathan Lee, Chung, “Efficient and Retargetable Dynamic Binary Translation on
“Dynamic Resource Selection Heuristics for a Non-reserved Bidding- Multicores,” 3IE, pEpE. 6T2r2a-n6s3a2c,tiFoenbsrounaryPa2r0a1l4le.l and Distributed Systems,
b26as,eNdoG. 2ri,dpEp.n1v8ir3o-n1m97e,n2t,0”1F0u. ture Generation Computer Systems, Vol. Vol. 25, No.
4. Chien-Ming Wang, Chi-Chang Huang, and Huan-Ming Liang, “ASDF: 9. Hsiang-Huang Wu, Tse-Chen Yeh, and Chien-Min Wang, “Multiple
An Autonomous and Scalable Distributed File System,” Proceedings Two-Phase Data Processing with MapReduce,” Proceedings of the
of the 11th IEEE/ACM International Symposium on Cluster, Cloud 2014 IEEE International Conference on Cloud Computing, pp. 352-
and Grid Computing, pp. 485-493, Los Angeles, USA, May 2011. 359, Alaska, USA, June 2014.
5. Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang, Jan-Jan Wu, 10. Hsiang-Huang Wu and Chien-Min Wang, “Generalization of
Ding-Yong Hong, Pen-Chung Yew, and Wei-Chung Hsu, “LnQ: Large-Scale Data Processing in one MapReduce job for Coarse-
Building High Performance Dynamic Binary Translators with Grained Parallelism,” to appear in International Journal of Parallel
Existing Compiler Backends,” Proceedings of the 40th International Programming, 2016.
Conference on Parallel Processing, pp. 226-234, Taipei, Taiwan, Sep.
2011.
57
