InTheLoop | 02.22.2010
February 22, 2010
CRD Gets $3.5 Million for Cyber-Security Related Research
As the nation and the world become increasingly dependent on complex networks ranging from the Internet to electrical grid and centralized computing systems, determining the best way to protect these resources is of paramount importance. To address this issue, U.S. Department of Energy solicited proposals for research addressing the mathematical challenges involved in improving our understanding of complex, interconnected systems such as computer networks.
Of the seven projects receiving funding in this area, researchers in Lawrence Berkeley National Laboratory's Computational Research Division (CRD) were named to lead two projects funded at more than $1.16 million per year for three years. The DOE program, called Mathematics for Complex, Interconnected Distributed Systems, was established to “support basic research in mathematical models, methods and tools for the modeling, simulation and analysis of complex, distributed, interconnected systems.” Read more.
A Computational Science Approach for Analyzing Culture
Just as photography revolutionized the study of art by allowing millions of people all over the world to scrutinize sculptures and paintings outside of museums, researchers from the Software Studies Initiative at the University of California at San Diego (UCSD) believe that a new paradigm called cultural analytics will drastically change the study of culture by allowing people to quantify evolving trends across time and countries.
Inspired by scientists who have long used computers to transform simulations and experimental data into multi-dimensional models that can then be dissected and analyzed, cultural analytics applies similar techniques to cultural data. With an allocation on NERSC supercomputers and help from the facility’s analytics team, UCSD researchers recently illustrated changing trends in media and design across the 20th and 21st centuries via Time magazine covers and Google logos. Read more.
Chatterjee Named Director of SC Communications and Public Affairs
Last week the DOE Office of Science (SC) named Dr. Lali Chatterjee as the Director of the Office of SC Communications and Public Affairs. Chatterjee will move from the Office of Advanced Scientific Computing Research (ASCR), where she was the Program Manager for SciDAC.
As Director of SC Communications, Chatterjee oversees a broad range of public affairs responsibilities, including coordination with the national laboratories, the DOE Office of Public Affairs, and internal and external SC outreach. She reports to Dr. Walter Warnick, Director of the Office of Scientific and Technical Information.
Chatterjee has a PhD in high energy (muon) physics. She has written numerous research papers as well as two books about physics for nonspecialists, has lectured at leading universities and laboratories around the world, and was the first editor-in-chief of SciDAC Review magazine.
Peter Nugent to Lead NERSC Analytics Team
On February 17, NERSC Director Kathy Yelick made this announcement:
In an effort to better meet the challenges and opportunities for NERSC posed by data intensive science, and continue to grow and strengthen LBNL’s research program in scientific visualization, I am pleased to announce that Peter Nugent will be assuming the lead for the NERSC Analytics Team while Wes Bethel will continue to lead CRD Visualization Group. As one of DOE’s leading researchers in scientific visualization, Wes is the Coordinating PI for the SciDAC Visualization and Analytics Center for Enabling Technologies, DOE’s largest-ever open science visualization effort, and he will continue to be involved with the NERSC Analytics Team in an advisory capacity.
NERSC is currently involved in long-term planning that has as one of its centerpieces this data intensive science, a field that includes advanced algorithms, data management tools, and storage and communication systems, along with visualization. A good example of the types of potential success is the Deep Sky project, architected and led by Peter Nugent, over the past two years. DeepSky is one of the largest repositories of astronomical imaging data (over 80 TB) and is the backbone of the Palomar Transient Factory, currently the largest source for the discovery of new astrophysical transients in the world.
The existing staff from the Visualization Group who have made the NERSC Analytics program what it is will continue on with Peter as the new team lead, and they’ll continue to be matrixed from the CRD Visualization Group. Please join me in welcoming Wes and Peter to their new and ongoing roles.
CRD, NERSC Staff Active at SIAM Conference on Parallel Processing
More than two dozen CRD and NERSC staff will be contributing to the SIAM Conference on Parallel Processing for Scientific Computing (PP10) this Wednesday through Friday, February 24–26, in Seattle:
- Ann Almgren will present a paper co-authored with John Bell, Mike Lijewski, Andy Nonaka (all from CRD) and Mike Zingale of Stony Brook University on “Parallel Adaptive Simulation of Low Mach Number Flows.”
- Hank Childs of CRD/NERSC will lead a mini-symposium on “The Challenges Ahead for Visualizing and Analyzing Massive Data Sets.”
- Phillip Colella will present a paper co-authored with Brian Van Straalen (both from CRD) on “High-Performance Adaptive Methods for Elliptic PDE.”
- Jim Demmel of UC Berkeley and CRD will lead a mini-symposium on “Communication-Avoiding Linear Algebra.” He will present a paper co-authored with Mark Hoemmen of UCB and Marghoob Mohiyuddin of UCB and CRD on “Communication-Avoiding Iterative Methods.” In the “Graduate Education for the Parallel Revolution” session, Demmel will present “Big Events at UC Berkeley: The Multicore Revolution, Cloud Computing, and a Graduate Program in Computational Science and Engineering.” He also co-authored papers on “Lower Bounds on Communication” and “Communication Bounds for Sequential and Parallel Eigenvalue Problems.”
- Tony Drummond of CRD will lead a mini-symposium on “Coupling and Regridding Tools for Supporting Parallel Multi-physics Modeling.” He will present a paper, co-authored with Dany DeCechis of San Diego State University, on “Parallel Regridding Schemes in the Distributed Coupling Toolkit.” In another session, Drummond will present “Software Sustainability in the DOE ACTS Collection.”
- Paul Hargrove of CRD will present “A Brief Introduction to BLCR (Berkeley Lab Checkpoint/Restart).”
- Alice Koniges of NERSC will present “Many Core Architectural Challenges for Parallel Computing of Fluids.” She is also co-author of two papers, “Modeling of ICF Experiments using a New Multi-physics Code, ALE-AMR” and “Multimaterial Remapping in ALE-AMR.” Koniges and John Shalf of NERSC are co-organizers, along with Gabriele Jost of the University of Texas at Austin, of “Exploring Languages for Expressing Medium to Massive On-Chip Parallelism.” Shalf and Koniges co-authored “The Architectural Requirements driving Language Evolution.”
- Kamesh Madduri of CRD will receive the SIAM SIAG/SC Junior Scientist Prize in Supercomputing and will present “High Performance Computing for Massive Graph Analysis.”
- Osni Marques of CRD is on the Organizing Committee for the conference.
- Leonid Oliker of CRD is principal organizer of “Emerging Programming Paradigms for Large-Scale Scientific Computing.” He will present “Hierarchical Auto-Tuning of a Hybrid Lattice Boltzmann Computation,” co-authored by Samuel Williams of CRD and John Shalf and Jonathan Carter of NERSC. With researchers from Georgia Institute of Technology, Williams and Oliker co-authored “Optimizing and Tuning the Fast Multipole Method for Multicore and Accelerator Systems.”
- John Shalf of NERSC, in addition to contributions mentioned above, is co-organizer of the Joint JSIAM-SIAM Minisymposium on Automatically Tuned Scientific Libraries and Applications.
- Associate Lab Director Horst Simon will give a plenary talk on “Energy Efficient Computing: From Bits to Buildings.”
- Eric Strohmaier will present “Parallel Motifs as Paradigms for Comparing Language Performance.”
- Samuel Williams of CRD, in addition to contributions mentioned above, will present “Memory-Efficient Optimization of Gyrokinetic Particle-to-Grid Interpolation for Multicore Processors,” co-authored by Kamesh Madduri, Leonid Oliker, and Eric Strohmaier of CRD; Stephane Ethier of Princeton Plasma Physics Laboratory; and John Shalf and Katherine Yelick of NERSC.
- Yili Zheng of CRD will lead a session on “System Software, Environments, and Tools” and will present a paper, co-authored by Costin Iancu, Paul Hargrove, and Seung-Jai Min of CRD and NERSC Director Kathy Yelick, on “Extending Unified Parallel C for GPU Computing.” Zheng will also present “Getting Multicore Performance with UPC,” co-authored by Filip Blagojevic, Paul Hargrove, Steven Hofmeyr, Costin Iancu, and Seung-Jai Min of CRD; Dan Bonachea and Rajesh Nishtala of UC Berkeley; and NERSC Director Katherine Yelick. With Rajesh Nishtala of UC Berkeley, Zheng co-authored “UPC at Scale.”
CS Diversity Working Group Can Fund Six Summer Students
The Computing Sciences Diversity Working Group can fund four college students and two high school students for the 2010 Summer Student Program. Details for the college students program can be found here. Potential summer students from under-represented populations may be eligible for the funding.
High school students can participate in summer research and training opportunities through the Berkeley Lab Internships for Precollegiate Scholars (BLIPS) (formerly HSSRPP) program. This program is an important contributor to community outreach and workforce diversity efforts and is a seven-week summer appointment. You may also use your own project funding for the program if interested. (The cost per student is still to be determined for 2010; in 2009 it was $2,000 per student.) Projects should be appropriate for high school students, and mentors must be willing to invest the time.
Please contact Michael Helm (email@example.com) if you are interested in mentoring one of these students. (For best results, use a subject of “Diversity Summer Student.”) Funding is available on first-come, first-served basis.
Computing Sciences Mentoring Program Is Starting New Round
The next round of the Mentoring Program will be starting in April 2010. If you are interested in being a mentor in the next round of the program, please complete a sign-up sheet, available here, by Monday, March 1.
About Computing Sciences at Berkeley Lab
The Lawrence Berkeley National Laboratory (Berkeley Lab) Computing Sciences organization provides the computing and networking resources and expertise critical to advancing the Department of Energy's research missions: developing new energy sources, improving energy efficiency, developing new materials and increasing our understanding of ourselves, our world and our universe.
ESnet, the Energy Sciences Network, provides the high-bandwidth, reliable connections that link scientists at 40 DOE research sites to each other and to experimental facilities and supercomputing centers around the country. The National Energy Research Scientific Computing Center (NERSC) powers the discoveries of 7,000-plus scientists at national laboratories and universities, including those at Berkeley Lab's Computational Research Division (CRD). CRD conducts research and development in mathematical modeling and simulation, algorithm design, data storage, management and analysis, computer system architecture and high-performance software implementation. NERSC and ESnet are Department of Energy Office of Science User Facilities.
Lawrence Berkeley National Laboratory addresses the world's most urgent scientific challenges by advancing sustainable energy, protecting human health, creating new materials, and revealing the origin and fate of the universe. Founded in 1931, Berkeley Lab's scientific expertise has been recognized with 13 Nobel prizes. The University of California manages Berkeley Lab for the DOE’s Office of Science.
DOE’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States, and is working to address some of the most pressing challenges of our time. For more information, please visit science.energy.gov.