Page 64 - 2017 Brochure
P. 64
究員
吳真貞 Jan-Jan Wu
Research Fellow
Ph.D., Computer Science, Yale University
Tel: +886-2-2788-3799 ext. 1610 Fax: +886-2-2782-4814
Email: wuj@iis.sinica.edu.tw
http://www.iis.sinica.edu.tw/pages/wuj
• Research Fellow, Institute of Information Science, Academia Sinica (2011-present)
• Associate Research Fellow, Institute of Information Science, Academia Sinica (2001-2011)
• Assistant Research Fellow, Institute of Information Science, Academia Sinica (1996-2001)
• Associate Software Engineer, Institute of Information Industry (1987-1989)
• Ph.D., Computer Science, Yale University (1995)
• M.S., Computer Science and Information Engineering, National Taiwan University (1987)
• B.S., Computer Science and Information Engineering, National Taiwan University (1985)
Research Description have adopted many distinct strategies for microprocessor design
to improve parallelism, including multi-cores, many-cores, GPGPU,
My research interests include resource management in parallel SIMD, and others. However, these parallel architectures have very
and cloud computing, parallel and distributed processing for big different parallel execution models and thus substantial problems
data, and dynamic binary translation for multicores/manycores. In are encountered when migrating applications from one architecture
resource management, we study dynamic provision, scheduling to another: (1) application developers have to re-write programs
and management of virtual machines, automatic scaling of system based on the target execution model, which increases the time
resources for application service requirements, and dynamic to market (2) legacy applications are poorly optimized due to
resource management for performance/energy tradeoff. In big data under-utilization of parallelism in the target hardware, and thus,
processing, we develop efficient data partitioning strategies for only a small fraction of the potential performance gain is realized.
NoSQL databases, data caching and replacement techniques for To overcome these problems, we developed an efficient and
in-memory cluster computing, and distributed algorithms for large- retargetable dynamic binary translator to transparently transform
scale graph computing. application binaries among different parallel execution models. In
our current work, the DBT dynamically transforms binaries of short-
In dynamic binary translation (DBT), we developed a system SIMD loops to equivalent long-SIMD loops, in order to exploit the
emulator, HQEMU, which supports efficient simulation of ARM wider SIMD lanes of the hosts.
binary execution on x86 architectures. We also extend our research
to address important DBT issues in architectures with SIMD (single
instruction, multiple data) extensions. Hardware manufacturers
Publications 6. Li-Yung Ho, Jan-Jan Wu, Pangfeng Liu, Chia-Chun Shih, Chi-Chang
Huang and Chao-Wen Huang, “Efficient Cache Update for In-Memory
1. Meng-Ju Hsieh, Li-Yung Ho, Jan-Jan Wu, Pangfeng Liu, “Data Cluster Computing with Spark,” 17th IEEE/ACM International
Partition Optimization for Column-Family NoSQL databases,” to Symposium on Cluster, Cloud and Grid Computing, May 2017.
appear in International Journal of Big Data Intelligence.
7. Ding-Yong Hong, Sheng-Yu Fu, Yu-Ping Liu, Jan-Jan Wu, and
2. Ding-Yong Hong, Chun-Chen Hsu, Cheng-Yi Chou, Wei-Chung Wei-Chung Hsu, “Exploiting Longer SIMD Lanes in Dynamic
Hsu, Pangfeng Liu, Jan-Jan Wu, “Optimizing Control Transfer and Binary Translation,” IEEE International Conference on Parallel and
Memory Virtualization in Full System Emulators,” ACM Transactions Distributed Systems (ICPADS), December 2016, Best Paper (out of
on Architecture and Code Optimization (TACO), volume 12, number 412 submissions)
47, pages 1-24, December 2015.
8. Sheng-Yu Fu, Ding-Yong Hong, Jan-Jan Wu, Liu Pangfeng and Wei-
3. Ching-Chi Lin, You-Cheng Syu, Chao-Jui Chang, Jan-Jan Wu, Chung Hsu, “SIMD Code Translation in an Enhanced HQEMU,”
Pangfeng Liu, Po-Wen Cheng, Wei-Te Hsu, “Energy-efficient Task IEEE International Conference on Parallel and Distributed Systems
Scheduling for Multi-core Platforms with per-core DVFS,” Journal (ICPADS)., December 2015.
of Parallel and Distributed Computing, volume 86, pages 71-81,
December 2015. 9. Li-Yung Ho, Fei Shao, Jan-Jan Wu, and Pangfeng Liu, “Efficient
Distributed Maximum Matching for Solving the Container Exchange
4. Chun-Chen Hsu, Ding-Yong Hong, Wei-Chung Hsu, Pangfeng Liu, Problem in the Maritime Industry,” IEEE International Conference on
Jan-Jan Wu, “A Dynamic Binary Translation System in a Client/ Big Data, October 2015.
Server Environment,” Journal of Systems Architecture, volume 61,
number 7, pages 307-319, August 2015. 10. Ting-Chou Lin, Ching-Chi Lin, Ting-Weii Chang, Pangfeng Liu, Jan-
Jan Wu, Chia-Chun Shih, Chao-Wen Huang, “Job Dispatching and
5. Ding-Yong Hong, Jan-Jan Wu, Pen-Chung Yew, Wei-Chung Hsu, Scheduling for Heterogeneous Clusters – a Case Study on the Billing
Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang and Yeh-Ching Subsystem of Chung-Hua Telecomunication,” the 39th IEEE Annual
Chung, “Efficient and Retargetable Dynamic Binary Translation on International Computers, Software and Applications Conference
Multicores,” IEEE Transactions on Parallel and Distributed Systems, (COMPSAC 2015), July 2015.
volume 25, number 3, pages 622 - 632, March 2014.
62 研究人員 Research Faculty
吳真貞 Jan-Jan Wu
Research Fellow
Ph.D., Computer Science, Yale University
Tel: +886-2-2788-3799 ext. 1610 Fax: +886-2-2782-4814
Email: wuj@iis.sinica.edu.tw
http://www.iis.sinica.edu.tw/pages/wuj
• Research Fellow, Institute of Information Science, Academia Sinica (2011-present)
• Associate Research Fellow, Institute of Information Science, Academia Sinica (2001-2011)
• Assistant Research Fellow, Institute of Information Science, Academia Sinica (1996-2001)
• Associate Software Engineer, Institute of Information Industry (1987-1989)
• Ph.D., Computer Science, Yale University (1995)
• M.S., Computer Science and Information Engineering, National Taiwan University (1987)
• B.S., Computer Science and Information Engineering, National Taiwan University (1985)
Research Description have adopted many distinct strategies for microprocessor design
to improve parallelism, including multi-cores, many-cores, GPGPU,
My research interests include resource management in parallel SIMD, and others. However, these parallel architectures have very
and cloud computing, parallel and distributed processing for big different parallel execution models and thus substantial problems
data, and dynamic binary translation for multicores/manycores. In are encountered when migrating applications from one architecture
resource management, we study dynamic provision, scheduling to another: (1) application developers have to re-write programs
and management of virtual machines, automatic scaling of system based on the target execution model, which increases the time
resources for application service requirements, and dynamic to market (2) legacy applications are poorly optimized due to
resource management for performance/energy tradeoff. In big data under-utilization of parallelism in the target hardware, and thus,
processing, we develop efficient data partitioning strategies for only a small fraction of the potential performance gain is realized.
NoSQL databases, data caching and replacement techniques for To overcome these problems, we developed an efficient and
in-memory cluster computing, and distributed algorithms for large- retargetable dynamic binary translator to transparently transform
scale graph computing. application binaries among different parallel execution models. In
our current work, the DBT dynamically transforms binaries of short-
In dynamic binary translation (DBT), we developed a system SIMD loops to equivalent long-SIMD loops, in order to exploit the
emulator, HQEMU, which supports efficient simulation of ARM wider SIMD lanes of the hosts.
binary execution on x86 architectures. We also extend our research
to address important DBT issues in architectures with SIMD (single
instruction, multiple data) extensions. Hardware manufacturers
Publications 6. Li-Yung Ho, Jan-Jan Wu, Pangfeng Liu, Chia-Chun Shih, Chi-Chang
Huang and Chao-Wen Huang, “Efficient Cache Update for In-Memory
1. Meng-Ju Hsieh, Li-Yung Ho, Jan-Jan Wu, Pangfeng Liu, “Data Cluster Computing with Spark,” 17th IEEE/ACM International
Partition Optimization for Column-Family NoSQL databases,” to Symposium on Cluster, Cloud and Grid Computing, May 2017.
appear in International Journal of Big Data Intelligence.
7. Ding-Yong Hong, Sheng-Yu Fu, Yu-Ping Liu, Jan-Jan Wu, and
2. Ding-Yong Hong, Chun-Chen Hsu, Cheng-Yi Chou, Wei-Chung Wei-Chung Hsu, “Exploiting Longer SIMD Lanes in Dynamic
Hsu, Pangfeng Liu, Jan-Jan Wu, “Optimizing Control Transfer and Binary Translation,” IEEE International Conference on Parallel and
Memory Virtualization in Full System Emulators,” ACM Transactions Distributed Systems (ICPADS), December 2016, Best Paper (out of
on Architecture and Code Optimization (TACO), volume 12, number 412 submissions)
47, pages 1-24, December 2015.
8. Sheng-Yu Fu, Ding-Yong Hong, Jan-Jan Wu, Liu Pangfeng and Wei-
3. Ching-Chi Lin, You-Cheng Syu, Chao-Jui Chang, Jan-Jan Wu, Chung Hsu, “SIMD Code Translation in an Enhanced HQEMU,”
Pangfeng Liu, Po-Wen Cheng, Wei-Te Hsu, “Energy-efficient Task IEEE International Conference on Parallel and Distributed Systems
Scheduling for Multi-core Platforms with per-core DVFS,” Journal (ICPADS)., December 2015.
of Parallel and Distributed Computing, volume 86, pages 71-81,
December 2015. 9. Li-Yung Ho, Fei Shao, Jan-Jan Wu, and Pangfeng Liu, “Efficient
Distributed Maximum Matching for Solving the Container Exchange
4. Chun-Chen Hsu, Ding-Yong Hong, Wei-Chung Hsu, Pangfeng Liu, Problem in the Maritime Industry,” IEEE International Conference on
Jan-Jan Wu, “A Dynamic Binary Translation System in a Client/ Big Data, October 2015.
Server Environment,” Journal of Systems Architecture, volume 61,
number 7, pages 307-319, August 2015. 10. Ting-Chou Lin, Ching-Chi Lin, Ting-Weii Chang, Pangfeng Liu, Jan-
Jan Wu, Chia-Chun Shih, Chao-Wen Huang, “Job Dispatching and
5. Ding-Yong Hong, Jan-Jan Wu, Pen-Chung Yew, Wei-Chung Hsu, Scheduling for Heterogeneous Clusters – a Case Study on the Billing
Chun-Chen Hsu, Pangfeng Liu, Chien-Min Wang and Yeh-Ching Subsystem of Chung-Hua Telecomunication,” the 39th IEEE Annual
Chung, “Efficient and Retargetable Dynamic Binary Translation on International Computers, Software and Applications Conference
Multicores,” IEEE Transactions on Parallel and Distributed Systems, (COMPSAC 2015), July 2015.
volume 25, number 3, pages 622 - 632, March 2014.
62 研究人員 Research Faculty
