Lawrence Livermore National Laboratory

Lawrence Livermore National Laboratory


Todd Gamblin


Email: gamblin2@llnl.gov
Phone: 925-422-9319

Mailing address:
Todd Gamblin
Lawrence Livermore National Laboratory
Box 808, L-557
Livermore, CA 94551-0808

Todd is a computer scientist in the Center for Applied Scientific Computing at Lawrence Livermore National Laboratory. His research focuses mainly on scalable algorithms for measuring, analyzing, and visualizing performance data from massively parallel applications. He is also interested in fault tolerance, resilience, MPI, and parallel programming models. Todd has been at LLNL since 2008.

Todd works closely with researchers in CASC and with staff in the Development Environment Group in Livermore Computing. He is the team leader for the Performance Analysis and Visualization at Exascale (PAVE) project, and he also works on the Exascale Computing Technologies LDRD project, the SciDAC Sustained Performance, Energy, and Resilience (SUPER) project, and many other ASC projects at LLNL.

Todd received the Ph.D. and M.S. degrees in Computer Science from the University of North Carolina at Chapel Hill in 2009 and 2005. He received his B.A. in Computer Science and Japanese from Williams College in 2002. He has also worked as a software developer in Tokyo and held graduate research internships at the University of Tokyo and IBM Research.

Public Software Projects

  • Muster: Massively Scalable Clustering Library
  • Libra: Scalable Parallel Load Balance Measurement
  • Nami: Scalable Parallel Wavelet Compression
  • Wrap: Versatile PMPI Wrapper Generator Library.

Professional Activities

  • Conferences: CCGrid’13, SC’12 Posters, CLUSTER’12, ICPP’12, ICS’11 (Program Committee); PACT’09 (Organizing); ACM SRC 2012, ISPASS’10, ICA3PP’10, IPDPS’09, ICS’09, PACT’09 (Reviewing)
  • Journals: IEEE TPDS, Parallel Computing, IJHPCA, The Computer Journal (Reviewing)
  • Grant Reviewing: DOE Small Business Innovation Research (SBIR) (R)
  • Workshops: WHIST’11,’12 (Co-Chair), PMBS’10,’11,’12 (Program, Steering Committees)
  • Memberships: IEEE, ACM.

Personal Web Site

Todd also maintains a personal website with his full CV. This site is not sanctioned or supported by DOE, UC, LLNL, or any other organization.

Publications

Conference & Journal Papers

  1. Abhinav Bhatele, Todd Gamblin, Katherine E. Isaacs, Brian T. N. Gunney, Martin Schulz, Peer-Timo Bremer, and Bernd Hamann. Novel views of performance data to analyze large-scale adaptive applications. In Supercomputing 2012 (SC'12), Salt Lake City, UT, November 10-16 2012. LLNL-CONF-554552.
  2. Abhinav Bhatele, Todd Gamblin, Steven H. Langer, Peer-Timo Bremer, Erik W. Draeger, Bernd Hamann, Katherine E. Isaacs, Aaditya G. Landge, Joshua A. Levine, Valerio Pascucci, Martin Schulz, and Charles H. Still. Mapping applications with collectives over sub-communicators on torus networks. In Supercomputing 2012 (SC'12), Salt Lake City, UT, November 10-16 2012. LLNL-CONF-556491.
  3. Kento Sato, Adam Moody, Kathryn Mohror, Todd Gamblin, Bronis R. de Supinski, Naoya Maruyama, and Satoshi Matsuoka. Design and modeling of a non-blocking checkpointing system. In Supercomputing 2012 (SC'12), Salt Lake City, UT, November 10-16 2012. LLNL-CONF-554431.
  4. Aaditya G. Landge, Joshua A. Levine, Katherine E. Isaacs, Abhinav Bhatele, Todd Gamblin, Martin Schulz, Steve H. Langer, Peer-Timo Bremer, and Valerio Pascucci. Visualizing network traffic to understand the performance of massively parallel simulations. In IEEE Symposium on Information Visualization (INFOVIS'12), Seattle, WA, October 14-19 2012. LLNL-CONF-543359.
  5. Ignacio Laguna, Dong H. Anh, Bronis R. de Supinski, Saurabh Bagchi, and Todd Gamblin. Probabilistic diagnosis of performance faults in large scale parallel applications. In International Conference on Parallel Architectures and Compilation Techniques (PACT'12), Minneapolis, MN, September 19-23 2012. LLNL-PROC-548642.
  6. Olga Pearce, Todd Gamblin, Bronis R. de Supinski, Martin Schulz, and Nancy M. Amato. Quantifying the Effectiveness of Load Balance Algorithms. In International Conference on Supercomputing (ICS'12), Venice, Italy, June 25-29 2012. LLNL-CONF- 523343.
  7. Sandeep Budanur, Frank Mueller, and Todd Gamblin. Memory Trace Compression and Replay for SPMD Systems using Extended PRSDs. Computer Journal, 55(2):206–217, February 2012. LLNL-CONF-460598.
  8. Allison H. Baker, Robert D. Falgout, Todd Gamblin, Tzanio V. Kolev, Martin Schulz, and Ulrike Meier Yang. Scaling Algebraic Multigrid Solvers: On the Road to Exascale. Competence in High Performance Computing (CiHPC), Dec 2011. LLNL-PROC-463941.
  9. Ignacio Laguna, Todd Gamblin, Bronis R. de Supinski, Saurabh Bagchi, Greg Bronevetsky, Dong H. Anh, Martin Schulz, and Barry Rountree. Large scale debugging of parallel tasks with AutomaDeD. In Supercomputing 2011 (SC'11), Seattle, WA, November 12-18 2011. LLNL-CONF-486911.
  10. Martin Schulz, Joshua A. Levine, Peer-Timo Bremer, Todd Gamblin, and Valerio Pascucci. Interpreting performance data across intuitive domains. In International Conference on Parallel Processing (ICPP'11), Taipei, Taiwan, September 13-16 2011. LLNL-CONF-476091.
  11. Allison H. Baker, Todd Gamblin, Martin Schulz, and Ulrike Meier Yang. Challenges of Scaling Algebraic Multigrid across Modern Multicore Architectures. In Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS'11), Anchorage, Alaska, May 16-20 2011. LLNL-CONF- 458074.
  12. Zoltan Szebenyi, Todd Gamblin, Martin Schulz, Bronis R. de Supinski, Felix Wolf, and Brian J. N. Wylie. Reconciling sampling and direct instrumentation for unintrusive call-path profiling of MPI programs. In Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS'11), Anchorage, Alaska, May 16-20 2011. LLNL-CONF-468224.
  13. Todd Gamblin, Bronis R. de Supinski, Martin Schulz, Robert J. Fowler, and Daniel A. Reed. Clustering performance data efficiently at massive scales. In International Conference on Supercomputing (ICS'10), Tsukuba, Japan, June 1-4 2010. LLNL-CONF-422684.
  14. Bronis R. de Supinski, Sadaf Alam, David H. Bailey, Laura Carrington, Chris Daley, Anshu Dubey, Todd Gamblin, Dan Gunter, Paul D. Hovland, Heike Jagode, Karen Karavanic, Gabriel Marin, John Mellor-Crummey, Shirley Moore, Boyana Norris, Leonid Oliker, Catherine Olschanowsky, Philip C. Roth, Martin Schulz, Sameer Shende, Allan Snavely, Wyatt Spear, Mustafa Tikir, Jeff Vetter, Pat Worley, and Nicholas Wright. Modeling the office of science ten year facilities plan: The PERI architecture tiger team. Journal of Physics: Conference Series, SciDAC 2009, 2009. LLNL-CONF-413427.
  15. Robert J. Fowler, Laksono Adhianto, Bronis R. de Supinski, Mike Fagan, Todd Gamblin, Mark Krentel, John Mellor-Crummey, Martin Schulz, and Nathan Tallent. Frontiers of performance analysis on leadership class systems. Journal of Physics: Conference Series, SciDAC 2009, 2009. LLNL-CONF-413969.
  16. Todd Gamblin, Bronis R. de Supinski, Martin Schulz, Robert J. Fowler, and Daniel A. Reed. Scalable load-balance measurement for SPMD codes. In Supercomputing 2008 (SC'08), Austin, Texas, November 15-21 2008. LLNL-CONF-406045.
  17. Robert J. Fowler, Todd Gamblin, Allan K. Porterfield, Patrick Dreher, Song Huang, and Balint Joo. Performance engineering challenges: The view from RENCI. Journal of Physics: Conference Series, SciDAC 2008, 125:5, August 2008.
  18. Todd Gamblin, Robert J. Fowler, and Daniel A. Reed. Scalable methods for monitoring and detecting behavioral classes in scientific codes. In Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS'08), Miami, FL, April 14-18 2008.

Workshop Papers & Technical Reports

  1. Kento Sato, Adam Moody, Kathryn Mohror, Todd Gamblin, Bronis R. de Supinski, Naoya Maruyama, and Satoshi Matsuoka. Towards a light-weight non-blocking checkpointing system. In HPC in Asia Workshop 2012, Hamburg, Germany, June 17 2012.
  2. Spyros Lyberis, Polyvios Pratikakis, Dimitrios Nikolopoulos, Martin Schulz, Todd Gamblin, and Bronis de Supinski. The myrmics memory allocator: Hierarchical, message-passing allocation for global address spaces. In International Symposium on Memory Management (ISMM'12), Beijing, China, June 15-16 2012. LLNL-CONF-545875.
  3. Kento Sato, Adam Moody, Kathryn Mohror, Todd Gamblin, Bronis R. de Supinski, Naoya Maruyama, and Satoshi Matsuoka. Design and modeling of a non-blocking checkpoint system. In ATIP - A*CRC Workshop on Accelerator Technologies in High Performance Computing, May 7-10 2012.
  4. Steven Langer, Abhinav Bhatele, Todd Gamblin, Bert Still, Denise Hinkel, Mike Kumbera, Bruce Langdon, and Ed Williams. Simulating Laser-Plasma Interaction in Experiments at the National Ignition Facility on a Cray XE6. In Cray Users Group (CUG 2012), Stuttgart, Germany, April 29-May 3 2012. LLNL-PROC-547711.
  5. Kento Sato, Adam Moody, Kathryn Mohror, Todd Gamblin, Bronis R. de Supinski, Naoya Maruyama, and Satoshi Matsuoka. Towards an asynchronous checkpointing system. In IPSJ SIG Technical Reports 2011-ARC-197 2011-HPC-132 (HOKKE-19), November 2011. LLNL-CONF-509152.
  6. Martin Schulz, Abhinav Bhatele, Peer-Timo Bremer, Todd Gamblin, Katherine Isaacs, Joshua Levine, and Valerio Pascucci. Creating a Tool Set for Optimizing Topology-aware Node Mappings. In 5th ZIH Parallel Tools Workshop, Dresden, Germany, September 26-27 2011. LLNL-CONF-402937.
  7. Todd Gamblin, Martin Schulz, Peer-Timo Bremer, Joshua A. Levine, and Valerio Pascucci. Intuitive performance visualization techniques for topological analysis on capability machines. In Kagoshima Summer United Workshops on Parallel, Distributed, and Cooperative Processing, Kagoshima, Japan, July 26-29 2011. LLNL-CONF- 490044.
  8. Barry Rountree, Guy Cobb, Todd Gamblin, Martin Schulz, Bronis R. de Supinski, and Henry Tufo. Parallelizing heavyweight debugging tools with MPIecho. In Workshop on High-performance Infrastructure for Scalable Tools (WHIST'11), Tucson, Arizona, June 4 2011. LLNL-CONF-481092.
  9. Lukasz G. Szafaryn, Todd Gamblin, Bronis R. de Supinski, and Kevin Skadron. Experiences with achieving portability across heterogeneous architectures. In Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing (WOLFHPC'11), Tucson, Arizona, May 31 2011. LLNL-CONF-486291.
  10. Sandeep Budanur, Frank Mueller, and Todd Gamblin. Memory Trace Compression and Replay for SPMD Systems using Extended PRSDs. In First International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computing Systems (PMBS'10), New Orleans, LA, November 15 2010. LLNL-CONF-460598.
  11. Frank Mueller, Xing Wu, Martin Schulz, Todd Gamblin, and Bronis R. de Supinski. ScalaTrace: Tracing, analysis and modeling of HPC codes at scale. In Para 2010, Reykjavik, Iceland, June 6-9 2010. LLNL-CONF-427005.
  12. Bronis R. de Supinski, Robert J. Fowler, Todd Gamblin, Frank Mueller, Martin Schulz, and Prasun Ratn. An open framework for scalable, reconfigurable analysis. In International Workshop on Scalable Tools for High-End Computing (STHEC), Kos, Greece, June 7-12 2008. LLNL-CONF-403954.
  13. Francisco Chinchilla, Todd Gamblin, Morten Sommervoll, and Jan F. Prins. Parallel N-body simulation using GPUs. Technical Report TR04-032, University of North Carolina at Chapel Hill, December 2004.

Book Chapters & Articles

  1. Todd Gamblin. Collaboration Leads to Advances in Power Grid Modeling. In 2010 Computation Annual Report, page 32. Lawrence Livermore National Laboratory, 2010. LLNL-TR-470873.
  2. Robert J. Fowler, Todd Gamblin, Gopi Kandaswamy, Anirban Mandal, Allan K. Porterfield, Lavanya Ramakrishnan, and Daniel A. Reed. Challenges of scale: When all computing becomes grid computing. In Lucio Grandinetti, editor, High Performance Computing and Grids in Action, volume 16 of Advances in Parallel Computing, pages 186–206. IOS Press, Amsterdam, 2007.

Ph.D. Dissertation

  1. Todd Gamblin. Scalable Performance Measurement and Analysis. PhD thesis, University of North Carolina at Chapel Hill, Chapel Hill, NC, August 2009. LLNL-TH-419482.

Posters & Presentations

  1. Brian T. N. Gunney, Abhinav Bhatele, and Todd Gamblin. Tree-based load balancer in the SAMRAI framework. In SIAM Annual Meeting, Minneapolis, MN, July 9-14 2012. LLNL-PRES-562671.
  2. Aaditya Landge, Joshua A. Levine, Peer-Timo Bremer, Martin Schulz, Todd Gamblin, Abhinav Bhatele, Katherine Isaacs, and Valerio Pascucci. Interactive Visualizations for Performance Analysis of Heterogeneous Computing Clusters. In GPU Technology Confernence (GTC'12), San Jose, CA, May 14-17 2012.
  3. Abhinav Bhatele, Todd Gamblin, Brian T. N. Gunney, Martin Schulz, Peer-Timo Bremer, and Katherine Isaacs. Revealing Performance Artifacts in Parallel Codes Through Multi-Domain Visualizations. In SIAM Conference on Parallel Processing for Scientific Computing (PP12), Savannah, Georgia, USA, February 15-17 2012. LLNL-ABS-518731.
  4. Olga Pearce, Todd Gamblin, Martin Schulz, Bronis R. de Supinski, and Nancy M. Amato. Load Balance: Correlating Application-Independent Measurements with Application-Semantic Computational Models. In Supercomputing 2010 (SC'10), New Orleans, LA, November 13-19 2010. LLNL-POST-442731.
  5. Allison H. Baker, Todd Gamblin, Martin Schulz, and Ulrike Yang. Algebraic multigrid for multicore architectures. In SIAM Annual Meeting, Pittsburgh, PA, July 12-16 2010. LLNL-PRES-435936.
  6. Todd Gamblin, Bronis R. de Supinski, Martin Schulz, Robert J. Fowler, and Daniel A. Reed. Clustering performance data efficiently at massive scales. In LLNL Computation Postdoctoral Poster Session, Livermore, CA, June 29 2010. LLNL-POST-433541.
  7. Todd Gamblin. Preparing for Exascale: System Software and Tools Research at LLNL. In Global Scientific Information and Computing Seminar, Tokyo Institute of Technology, Tokyo, Japan, June 11 2010. LLNL-PRES-434295.
  8. Todd Gamblin. Load Balance Analysis with Libra. In Proceedings of the Dagstuhl Seminar on Program Development for Extreme-Scale Computing, Dagstuhl, Germany, May 3-7 2010. LLNL-PRES-431860.
  9. Todd Gamblin. Scalable In-situ Analysis Techniques. In Proceedings of the Dagstuhl Seminar on Program Development for Extreme-Scale Computing, Dagstuhl, Germany, May 3-7 2010. LLNL-POST-433541.
  10. Todd Gamblin. Infrastructure challenges for scalable data analysis algorithms. In ParaDyn/Condor Week 2010, Madison, WI, April 12-16 2010. University of Wisconsin. LLNL-PRES-408863.
  11. Todd Gamblin, Bronis R. de Supinski, and Martin Schulz. Performance modeling and analysis at LLNL. In Proceedings of Joint Operations Weapons Operations Group 34 (JOWOG34), Sandia National Laboratories, Albuquerque, NM, July 20-24 2009. LLNL-PRES-463247.
  12. Todd Gamblin, Bronis R. de Supinski, Martin Schulz, Robert J. Fowler, and Daniel A. Reed. System-wide performance equivalence class detection using clustering. In Supercomputing 2008 (SC'08), Austin, TX, November 15-21 2008. LLNL-POST-408815.
  13. Todd Gamblin, Bronis R. de Supinski, Martin Schulz, Robert J. Fowler, and Daniel A. Reed. Scalable Load Balance Measurement Using Wavelets. In The Salishan Conference on High-Speed Computing, Gleneden Beach, OR, April 21-24 2008. LLNL-POST-463395.
  14. Todd Gamblin. Scalable load-balance measurement and analysis. In SIAM Conference on Parallel Processing for Scientific Computing (PP08), Atlanta, GA, March 12-14 2008.
  15. Todd Gamblin, Prasun Ratn, Bronis R. de Supinski, Martin Schulz, Frank Mueller, Robert J. Fowler, and Daniel A. Reed. An open framework for scalable, reconfigurable performance analysis. In Supercomputing 2007 (SC'07), Reno, NV, November 10-16 2007. UCRL-POST-236200.
  16. Todd Gamblin, Robert J. Fowler, and Daniel A. Reed. Methods for automatic behavioral stratification in scientific codes. In Proceedings of the 7th LACSI Symposium, Santa Fe, NM, October 17-19 2006.
  17. Todd Gamblin and Daniel A. Reed. Adaptive performance monitoring and profiling in large-scale systems. In Proceedings of the 6th LACSI Symposium, Santa Fe, NM, October 11-13 2005.


Updated: 2014-03-11 19:07:09