Dan Reed

Chancellor's Eminent Professor Director, Renaissance Computing Institute (RENCI) University of North Carolina, Chapel Hill VGrADS Activities: Co-PI, working on Execution System (Fault Tolerance) and LEAD Application Dan_Reed@unc.edu http://www.renci.org/about.php

Professional Preparation

• Ph.D., Computer Science, Purdue University, 1983
• M.S., Computer Science, Purdue University, 1980
• B.S., Computer Science, University of Missouri at Rolla , 1978

Appointments

• Chancellor's Eminent Professor, University of North Carolina at Chapel Hill (UNC), 2004-
• Vice Chancellor of Information Technology, University of North Carolina at Chapel Hill (UNC), 2004-
• Director, Renaissance Computing Institute (RENCI), 2004-
• Adjunct Professor of Computer Science, North Carolina State University (NCSU), 2004-
• Adjunct Professor of Computer Science, Duke University, 2004-
• Director, National Center for Supercomputing Applications (NCSA), 2001-2004
• Director, National Computational Science Alliance, 2001-2004
• Edward William and Jane Marr Gutgsell Professor, Department of Computer Science, University of Illinois at Urbana-Champaign, 2000-2004
• Head, Department of Computer Science, University of Illinois at Urbana-Champaign, 1997-2001
• Assistant, Associate, and Professor, Department of Computer Science, University of Illinois 1984-2004
• Senior Research Scientist, National Center for Supercomputing Applications, 1995-2000
• Visiting Scientist, IBM T. J. Watson Research Center, 1990
• Assistant Professor, Department of Computer Science, University of North Carolina, 1983-1984

Synergistic Activities

• Advisory Boards and Committees: President's Information Technology Advisory Committee (PITAC) (2003-), Board of Directors, Computing Research Association (1998-) and Chair (2005-), Argonne/University of Chicago Computation Institute External Advisory Council (2000-), Supercomputing XY Steering Committee (1999-2003), Los Alamos Computer Science Institute Steering Committee (1999-), AAAS Member at Large, Section on Information, Computing, and Communication (2001-), Chair, DOE NERSC Policy Board (2003-)

• Recent Program and Conference Chairs: Vice-chair, Software, IPDPS (2005), Vice-Chair, Petascale Computing, ICPP (2005), Chair, SC02 Technical Program (2002)
• Current Editorial Boards: Concurrency: Practice and Experience, Performance Evaluation and Modeling for Computer Systems, Parallel Computing (North American editor)

• Awards and Honors: NSF Presidential Young Investigator Award (1987), University Scholar, University of Illinois (1989), Edward William and Jane Marr Gutgsell Professor (2000-2004), Chancellor's Eminent Professor (2004-), Fellow, IEEE and ACM

Dr. Reed is the author of over one hundred research papers and monographs on algorithms, architectures, and performance evaluation techniques for high-performance computing and virtual environments.

He currently directs the Renaissance Computing Institute (RENCI), a venture supported by three universities -- the University of North Carolina at Chapel Hill, Duke University and North Carolina State University -- that is exploring the interactions of computing technology with the sciences, arts and humanities.

His Pablo project has developed portable performance data capture and presentation tools for scalable parallel systems, exploring the integration of high-level languages and data reduction techniques to relate dynamic performance data to application code. The Pablo toolkit has also been the basis for I/O characterization on HPC systems and was the springboard for creating the Virtue performance visualization system and the Autopilot Grid performance monitoring system. These tools are available at www.renci.org

As Director of NCSA and the Alliance, as well as Chief Architect for the NSF TeraGrid, he led a national team of computing and application researchers developing computational grids, scalable PC clusters, and distributed collaboration tools in support of 21st century computational science. Dr. Reed has also participated in two DOE ASCI/ASAP centers, the Illinois Center for Simulation of Advanced Rockets (CSAR), where he is a past member of the steering committee, and the Caltech Facility for Simulating the Dynamic Response of Materials.

He has been a principal in the multi-agency (NSF, DARPA, DOE, and NASA) national Scalable I/O Initiative (SIO) and a member of a collaborative, NSF-funded Grand Challenge group with Caltech to explore the input/output performance of scientific codes using the Pablo instrumentation software. This work led to the book Scalable Input/Output: Achieving System Balance (MIT Press), containing guidelines for I/O tuning.

With Los Alamos National Laboratory, he organized a series of workshops on performance analysis techniques for scalable parallel systems. The workshop goals have been to understand the technical, economic, and political issues that affect development and deployment of software tools on scalable parallel systems. The latest of these workshops led to the 1996 book Debugging and Performance Tuning for Parallel Computing Systems, which has catalyzed national discussion of HPCC software testing and evaluation, as well as the need for increased funding of research software infrastructure.

VGrADS and Other Significant Publications

• Berman, F, Casanova, H, Chien, A, Cooper, K, Dail, H, Dasgupta, A, Deng, W, Dongarra, J, Johnsson, L, Kennedy, K, Koelbel, C, Liu, B, Liu, X, Mandal, A, Marin, G, Mazina, M, Mellor-Crummey, J, Mendes, C, Olugbile, A, Patel, M, Reed, D, Shi, Z, Sievert, O, Xia, H, and YarKhan, A. “New Grid Scheduling and Rescheduling Methods in the GrADS Project,” International Journal of Parallel Programming (IJPP). (To appear 2005).
• Reed, DA, and Mendes, CL. “Intelligent Monitoring for Adaptation in Grid Applications,” Proceedings of the IEEE, Volume 93(2):426- 435. (2005).
• D. A. Reed, “Grids, the TeraGrid, and Beyond,” IEEE Computer, Volume 36, No. 1, pp. 62-68, January 2003.
• D. A. Reed and R. A. Aydt, “Performance Analysis and Measurement,” in High-Performance Computing, K. Kennedy (ed.), 2002.
• C-D. Lu and D. A. Reed, “Compact Application Signatures for Parallel and Distributed Scientific Codes,” SC02, November 2002.
• N. Tran and D. A. Reed, “ARIMA Time Series Modeling and Forecasting for Adaptive I/O Prefetching,” Proceedings of the 15th ACM International Conference on Supercomputing, June 2001, pp. 473-485.
• R. L. Ribler, H. Simitci, and D. A. Reed, “The Autopilot Performance-Directed Adaptive Control System,” Future Generation Computer Systems, special issue (Performance Data Mining), 18 (1) pp. 175-187, September 2001.
• F. Vraalsen, R. A. Aydt, C. L. Mendes, and D. A. Reed, “Performance Contracts: Prediction and Monitoring Grid Application Behavior,” Proceedings of the 2nd International Workshop on Grid Computing/LNCS (GRID 2001), Springer-Verlag Lecture Notes in Computer Science, November 2001.
• L. DeRose, M. Pantano, and D. A. Reed, “An Approach to Immersive Performance Visualization of Parallel and Wide-Area Distributed Applications”, Eighth IEEE Symposium on High-Performance Distributed Computing, August 1999.
• C. L. Mendes and D. A. Reed, “Integrated Compilation and Scalability Analysis for Parallel Systems,” Parallel Architectures and Compilation Techniques (PACT '98), October 1998.
• D. A. Reed, R. A. Aydt, L. DeRose, C. L. Mendes, R. L. Ribler, E. Shaffer, H. Simitci, J. Vetter, D. R. Wells, S. Whitmore, and Y. Zhang, “Performance Analysis of Parallel Systems: Approaches and Open Problems,” Japan JSPP, pp. 239--256, June 1998.
• D. A. Reed and R. L. Ribler, “Performance Analysis and Visualization,” in The Grid: Blueprint for a New Computing Infrastructure, Ian Foster and Carl Kesselman (eds), Morgan-Kaufmann, August 1998.