InTheLoop | 06.14.2010
June 14, 2010
Why the U.S. Must Lead in Supercomputing
“China officially claimed the world’s second-fastest computer earlier this month. China was in fifth place just six months ago — and is expected to have the world’s fastest machine by year end. While its systems currently rely on U.S. components, China is already constructing comparable machines using its domestic technology. These challenges to U.S. leadership in supercomputing and chip design threaten our country’s economic future.”
So begins an opinion piece by DOE Undersecretary for Science Steven E. Koonin in this morning’s San Francisco Chronicle. Read more.
Berkeley Lab Team Receives NASA Public Service Group Achievement Award
Julian Borrill, Christopher Cantalupo, and Theodore Kisner of Berkeley Lab’s Computational Cosmology Center (C3) are being honored with a NASA Public Service Group Achievement Award for developing the supercomputing infrastructure for the U.S. Planck Team’s data and analysis operations at NERSC. C3 is a joint center of Berkeley Lab’s Computational Research and Physics Divisions. Read more.
“Magellan at NERSC” and 2008–09 NERSC Annual Report Now on the Web
The “Magellan at NERSC” web site is now live at http://magellan.nersc.gov. The mini-site features information and news about the portion of this scientific cloud computing testbed which is located at Berkeley Lab. (The other half of the system is operated by the Argonne Leadership Computing Facility). Margie Wylie of the CS Communications Team is the site coordinator.
A PDF file of the 2008–09 NERSC Annual Report has been posted here. The print and HTML versions will be available in a few weeks.
CS Announces New Safety Competition
Berkeley Lab Computing Sciences staff are encouraged to send near-miss safety hazards and safety suggestions to Safety Coordinator Betsy MacGowan. Horst Simon, Betsy MacGowan, and the CS Safety Committee will select the “CS Safety Top 10” suggestions that provide the greatest improvement to Lab safety. Employees who submit the winning entries will be recognized with a Spot Award, which includes a cash prize.
This safety competition is being launched as part of Berkeley Lab’s initiative to transform the safety culture at the Lab. The competition is open to CS staff, guests and matrixed employees, and is intended to increase awareness of safety issues within CS, CRD, and NERSC. The “CS Safety Top 10” winners will be featured on the Computing Sciences website. All safety submissions for the first cycle are due on August 31, and the winners will be announced in September. Deadlines, winners, and the Top 10 list will be announced periodically in InTheLoop.
Top 10 Things to Know about the Google Calendar Transition
The Lab will be migrating from Oracle Calendar to Google Calendar during the weekend of July 31. Interested calendar users and Google Guides are invited to attend a one hour seminar from 1:30 to 2:30 pm Wednesday, June 16, in the Bldg. 50 Auditorium to hear about the calendar transition, including observations concerning the success of trial data migrations from Oracle to Google.
Summer Student Program Kicks Off with Lunch and Presentation This Thursday
All Computing Sciences summer students are invited to a kick-off event from 11:30 am to 1:00 pm in the 50B-4205 conference room. Associate Lab Director Horst Simon will give a presentation on Computing Sciences, and pizza and refreshments will be available.
CS Staff Contribute to Algorithms for Massive Data Sets Workshop
Several CRD and NERSC staff are contributing to the Workshop on Algorithms for Modern Massive Data Sets (MMDS 2010) being held June 15–18 at Stanford University. Jim Demmel of UC Berkeley and CRD will give a talk on “Minimizing Communication in Linear Algebra.” Daniela Ushizima, Andrew Uselton, and Katie Antypas of NERSC, with Jefferey Sukharev of UC Davis, are presenting a poster on “Minimizing I/O contention at NERSC using data analysis.”
Ng and Li Are Invited Speakers at CERFACS Sparse Days Meeting
Esmond Ng and Sherry Li of CRD are invited speakers for the Sparse Days Meeting being held June 15–17 at CERFACS (the European Centre for Research and Advanced Training in Scientific Computation) in Toulouse, France. Ng will talk about “Sparse Matrix Computation in Large-Scale Scientific Applications.” Li will discuss “A Supernodal Approach to Incomplete LU Factorization with Partial Pivoting.”
Funding Available to Attend Grace Hopper Conference
The Grace Hopper Celebration of Women in Computing conference will be held in Atlanta, Georgia from September 28 to October 2, 2010.
This conference is designed to bring the research and career interests of women in computing to the forefront. Presenters are leaders in their respective fields, representing industrial, academic, and government communities. Leading researchers present their current work, while special sessions focus on the role of women in today’s technology fields, including computer science, information technology, research, and engineering.
The Berkeley Lab Computing Sciences Diversity Working Group is able to pay the travel and registration of a few Lab staff to attend. If you would like to attend the Grace Hopper Conference and would like to have your travel costs sponsored by the Diversity Working Group, please contact Deb Agarwal. Send the following information:
- Paragraph giving the reason you would like to attend Grace Hopper:
The deadline for submitting applications is June 23, 2010.
This Week’s Computing Sciences Seminars
A Forward Looking Evolutionary View of Computing for a Large Physics Experiment (STAR)
Monday, June 14, 9:30–10:30 am, 50F-1647
Jerome Lauret, Brookhaven National Laboratory, Leader, STAR Software and Computing Project
As Moore’s Law has driven exponential growth in compute and storage, it has also driven growth in the capabilities and data generation of experimental physics. Three orders of magnitude increase in storage and compute resource needs for the STAR experiment since its inception (the 10th year of data taking is just completed) are driving a transition from localizing resources in a dedicated facility to utilizing shared, opportunistic and even commercial cloud resources. STAR has been a participant in the development of grid computing in the Particle Physics Data Grid and Open Science Grid and is currently active in the utilization of cloud resources accessed through grid infrastructure. The Cloud paradigm is an important and necessary evolution of a distributed computing model beyond the foundation technologies provided by grid services. The driving forces in the computational aspects of experimental physics will continue to demand evolution of the software and computing capabilities of STAR. We are currently on the threshold of the transition from serial computing (embarrassingly parallel) to efficient use of multi-core processors. With these and other trends, the next 5+ years promises to be dynamic, challenging and exciting for STAR and experimental physics in general.
High Performance Flow Simulations on Graphics Processing Units
Thursday, June 17, 12:00–1:00 pm, 90-3122
Wangda Zuo, LBNL Energy and Environmental Technologies Division
Building design and operation often requires real-time or faster-than-real-time simulations for detailed information on air distributions. However, none of the current flow simulation techniques can satisfy this requirement. To solve this problem, a Fast Fluid Dynamics (FFD) model has been developed. The FFD can solve Navier-Stokes equations at a speed of 50 times faster than Computational Fluid Dynamics (CFD). In addition, the computing speed of the FFD program has been further enhanced up to 30 times by executing in parallel on a Graphics Processing Unit (GPU) instead of a Central Processing Unit (CPU). As a whole, the FFD on a GPU can be 1500 times faster than the CFD on a CPU.
Consortium for Electric Reliability Technology Solutions Organization and Research Overview
Thursday, June 17, 2:00–3:30 pm, 50B-4205
Joseph Eto, LBNL Energy and Environmental Technologies Division
The U.S. electric power system is in the midst of a fundamental transition from a centrally planned and utility-controlled structure to one that will depend on competitive market forces for investment, operations, and reliability management. Electricity system operators are being challenged to maintain the reliability of the grid and support economic transfers of power as the industry’s structure changes and market rules evolve. Meanwhile, the U.S. economy depends more than ever on reliable and high-quality electricity supplies. New technologies are needed to prevent major outages such as those experienced on August 14, 2003, which cost an estimated $4–10 billion and affected tens of millions of customers.
The Consortium for Electric Reliability Technology Solutions (CERTS) was formed in 1999 to research, develop, and disseminate new methods, tools, and technologies to protect and enhance the reliability of the U.S. electric power system and efficiency of competitive electricity market. CERTS’ vision is to:
- Transform the electricity grid into an intelligent network that can sense and respond automatically to changing flows of power and emerging problems;
- Enhance reliability management through market mechanisms, including transparency of real-time information on the status of the grid;
- Empower customers to manage their energy use and reliability needs in response to real-time market price signals; and
- Seamlessly integrate distributed technologies—including those for generation, storage, controls, and communications—to support the reliability needs of both the grid and individual customers.
The founding members of CERTS are LBNL, ORNL, PNNL, SNL, NSF’s Power System Engineering Research Center, and the Electric Power Group. LBNL serves as the program office for CERTS (http://certs.lbl.gov/).
Link of the Week: Ranking and Mapping Scientific Knowledge
Science is a massively parallel human endeavor to explain and predict the nature of the physical world. In science, knowledge is acquired cumulatively and collaboratively—and the principal mode for sharing this knowledge is the institution of scholarly publishing. In science, ideas are built upon ideas, models upon models, verifications upon prior verifications. This cumulative process of construction leaves behind it a latticework of citations, from which we can reconstruct the geography of scientific thought and retrace the paths along which intellectual activity has proceeded.
The Eigenfactor Project is a non-commercial academic research project sponsored by the Bergstrom lab in the Department of Biology at the University of Washington. They aim to use recent advances in network analysis and information theory to develop novel methods for evaluating the influence of scholarly periodicals and for mapping the structure of academic research. Results include maps of how different fields of science influence each other, and samples of four different ways of visualizing information flow in science. You can check out the rankings of individual journals from their home page.
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 6,000 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 DOE 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.