Developedanautomaticcalibrationalgorithmthatusesaregularvideocameratoalignahigh-resolutiond

Yuqun Chen

Department of Computer Science Office: (609) 258-6126 Princeton University Cell:(609) 558-8702

35 Olden Street Fax:(609) 258-1771 Princeton, NJ 08544yuqun@https://www.wendangku.net/doc/5014148787.html, Education

Ph.D. Computer Science, Princeton University Expected Sept. 2000

M.A. Computer Science, Princeton University May 1995

B.Sc. Computer Science, Highest Distinction, University of Maine May 1993

Research Interests

Scalable and distributed server systems, large-scale simulations, system-area and wide-area networking, smart matter, MEMS devices and applications, intuitive human-computer interactions, and parallel computation. Professional Experience

Princeton University, Department of Computer Science, Princeton, New Jersey

Ph.D. Candidate

Sept. 1994 – July 1995

Sept. 1997 – present

Played a lead role in the Scalable Display Wall Project that pioneered tiled, high-resolution displays built out of portable projectors, PC clusters, and commodity system-area networks[1].

Developed an automatic calibration algorithm that uses a regular video camera to align a high-resolution display with pixel-level accuracy [2].

Developed a novel technique to remove the communication bottleneck by running multiple program instances via system call synchronization[1].

Wrote or designed key Display Wall software and supervised four undergraduate projects.

Member of the SHRIMP project that investigated issues in building high-performance PC clusters and fast

networks[12].

Developed User-managed Translation Look-aside Buffer (UTLB), a novel mechanism for translating virtual

addresses into physical addresses on the network interface, with full protection and without OS modification [6];

later incorporated into an industrial standard for cluster communication, the Virtual Interface (VI).

Co-developed the spin-block technique to reduce idle CPU cycles for a multi-programming system employing

user-level communication [9].

Collaborated with colleagues on defining VMMC-II, an improved virtual-memory-mapped communication

paradigm for Myrinet system-area network [8].

Wrote operating system software for the SHRIMP-II multi-computer and developed a Windows NT port of Virtual Memory Mapped Communication [4].

Made key contributions to the MIMDRAID Project that studied system approaches to reduce disk read latencies [3].

Developed a software-only technique to track disk heads with 99.5% accuracy.

Statistical modeling of several disk array configurations.

Princeton University, Department of Computer Science, Princeton, New Jersey

Engineer

Oct. 1995 – Aug. 1997

Responsible for the Scalable I/O Initiative (SIO), a nation-wide collaborative effort, jointly funded by DARPA and NSF, to tackle the “big I/O problem” for large-scale computation.

Developed a checkpointing and restart tool [5,7], which takes a consistent snapshot of any running parallel

program and correctly restarts the program after a system crash *.

Co-authored SIO Low-level API (LLAPI), a system-level parallel I/O standard that provides an efficient

programming interface to access tera-byte data spanning hundreds of disks [10].

Contributed to the design of the LLAPI reference implementation [11]*.

*Both software packages achieved excellent performance on a 512-CPU Intel Paragon super-computer for a scientific program and a military battle simulation that were in real use.

Advanced Systems Concepts, Inc., Hoboken, New Jersey

System Engineer

Aug. 1995 – Oct. 1996

Developed the Linux prototype of a remote tape backup system based on the company’s VMS product.

Silicon Graphics, Inc., Digital Sight & Sound Division, Mountain View, California

Summer Intern

June 1994 – Aug. 1994

Developed a fast memory copy technique using R4600 cache-line operations. Improved the speed of kernel buffer copy – a bottleneck in the file system – by as much as 43%.

Laboratory For Surface Science and Technology, University of Maine, Orono, Maine

Programmer

June 1992 – Aug. 1992

Created new scan modes on the Atomic Force Microscope to help physicists study surface properties of polymers. Released Software

NT VMMC-II: A high-speed cluster communication software package, including the base-line communication system, the user library, and the cluster management software. The entire package has been downloaded and used by several research institutions and companies such as Intel Corporation.

CLIP: A tool to checkpoint and restore parallel applications running on Intel Paragon supercomputers. It has since been released by Caltech to the public under the Scalable I/O Initiative.

U.S. Patent (Pending)

K. Li, Y. Chen, and T. Housel. “Optical Blending For Multi-Projector Display Wall Systems.”

Achievements and Awards

Top 5% (top 100) in the Putnam North America Collegiate Mathematics Competition, 1994.

2nd team place in the ACM Northeast Regional Programming Contest, 12th team place in the International ACM Programming Contest Final, 1993.

Full Tuition Scholarship, University of Maine, 1990 – 1993.

1st Class Merit Scholarship, (given to students in top 1 percentile), Fudan University, 1988 – 1990.

T.D. Lee Physics Scholarship, (Dr. Lee is a Nobel Laureate in Physics), Shanghai, 1988 – 1990.

1st place in Shanghai, National silver medal, Physics Competition, China, 1988.

Winner of 1st Regional Student Mathematics Papers Competition, Shanghai, 1988.

Publications

1. Building A Scalable High-Resolution Display System.

Yuqun Chen. Ph.D. Thesis, Princeton University, August, 2000.

2. Automatic Alignment of High-Resolution Multi-Projector Displays Using An Un-Calibrated Camera.

Yuqun Chen, Douglas W. Clark, Adam Finkelstein, Timothy C. Housel, and Kai Li.

IEEE Visualization 2000, Salt Lake City, Utah, October 8-13, 2000.

3. Trading Capacity For Performance In A Disk Array.

X. Yu, B. Gum, Y. Chen, R. Y. Wang, K. Li, A. Krishnamurthy, and T. Anderson.

The 4th USENIX Symposium On Operating Systems Design And Implementation (OSDI 2000), San Diego,

California, October 23-25, 2000.

4. Porting a User-level Communication Architecture to NT: Experience and Performance.

Yuqun Chen, Stefanos N. Damianakis, Sanjeev Kumar, Xiang Yu, and Kai Li.

The 3rd USENIX Windows NT Symposium, Seattle, Washington, July, 1999.

5. Memory Exclusion: Optimizing the Performance of Checkpointing Systems.

James S. Plank, Yuqun Chen, Kai Li, Micah Beck and Gerry Kingsley.

Software -- Practice and Experience, Jon Wiley & Sons, vol. 29, no. 2, pp. 125-142, 1999.

6. UTLB: A Mechanism for Address Translations on Network Interfaces.

Yuqun Chen, Angelos Bilas, Cezary Dubnicki, Stefanos N. Damianakis, and Kai Li.

The Eighth Architectural Support for Programming Languages and Operating Systems (ASPLOS-VIII), San

Jose, California, October, 1998.

7. CLIP: A Checkpointing Tool for Message-Passing Parallel Programs.

Yuqun Chen, James S. Plank, and Kai Li.

SuperComputing'97, San Jose, California, November, 1997.

8. VMMC-II: Efficient Support For Reliable, Connection-Oriented Communication.

Cezary Dubnicki, Angelos Bilas, Yuqun Chen, Stefanos N. Damianakis, and Kai Li.

IEEE Hot Interconnects Symposium V, Stanford, California, August, 1997.

IEEE MICRO, Jan/Feb, 1998.

9. Reducing Waiting Costs in User-Level Communication.

Stefanos N. Damianakis, Yuqun Chen, and Edward W. Felten.

International Parallel Processing Symposium, Geneva, Switzerland, 1997.

10. Proposal For A Common Parallel File System Programming Interface.

P. F. Corbett, J. Prost, C. Demetriou, G. Gibson, E. Riedel, J. Zelenka, Y. Chen, E. W. Felten, K. Li, J. Hartman, L. Peterson, B. Bershad, A. Wolman, and R. Aydt.

Supercomputing’96, Pittsburgh, Pennsylvania, 1996.

11. Reference Implementation of Scalable I/O Low-level API on Intel Paragon Multicomputer.

Ninghui Sun, Yuqun Chen, and Kai Li.

Scalable I/O Initiative, upcoming, MIT Press.

12. Design Choices in the SHRIMP System: An Empirical Study.

M. A. Blumrich, R. D. Alpert, Y. Chen, D. W. Clark, S. N. Damianakis, C. Dubnicki, E. W. Felten, L. Iftode, K.

Li, M. Martonosi, and R. A. Shillner.

The 25th Annual International Symposium On Computer Architecture (ISCA), May, 1998.

References

Kai Li, Professor, Princeton University,609-258-4637,li@https://www.wendangku.net/doc/5014148787.html,

Douglas W. Clark, Professor, Princeton University,609-258-6314,doug@https://www.wendangku.net/doc/5014148787.html,

Adam Finkelstein, Asst. Professor, Princeton University, 609-258-5756,af@https://www.wendangku.net/doc/5014148787.html,

Edward W. Felten, Assoc. Professor, Princeton University,609-258-5906,felten@https://www.wendangku.net/doc/5014148787.html,

James S. Plank, Assoc. Professor, University of Tennessee, 615-974-4397,plank@https://www.wendangku.net/doc/5014148787.html,