InTheLoop | 02.21.2012
February 21, 2012
NERSC Initiative for Scientific Exploration (NISE) 2012 Allocations Announced
Twenty-two research projects have received allocations of computer time ranging from 500,000 to 15 million hours in the 2012 NERSC Initiative for Scientific Exploration (NISE) program. NISE is a competitive process administered by NERSC staff and management for allocating the NERSC reserve (10 percent of the center’s total allocation).
This year, reviewers were particularly interested in large-scale or data-intensive proposals. Most of the 2012 NISE projects have applications in energy technologies or climate science. Go here for a complete list and short descriptions of the winning projects.
CRD Mathematicians Sethian and Saye Win Cozzarelli Prize
James Sethian and Robert Saye, mathematicians who both hold joint appointments with Berkeley Lab and UC Berkeley, have won the 2011 Cozzarelli Prize for the best scientific paper in the category of Engineering and Applied Sciences. Their winning paper, “The Voronoi Implicit Interface Method for Computing Multiphase Physics,” introduces a robust, accurate, and efficient numerical method for tracking large numbers of interacting and evolving regions (phases) whose motions are determined by complex interactions of geometry, physics, constraints, and internal boundary conditions.
“This class of numerical methods presents a mathematically unified approach to complex interconnected moving interfaces, and opens the door to computing a host of challenging problems,” says Sethian, who heads the Mathematics Group of Berkeley Lab’s Computational Research Division. Read more.
Kathy Yelick Speaks at NITRD’s 20th Anniversary Symposium
Kathy Yelick, Berkeley Lab’s Associate Laboratory Director for Computing Sciences, was one of 16 speakers who shared their expertise at a symposium last Thursday, Feb. 16, marking the 20th anniversary of the Federal Networking and Information Technology Research and Development (NITRD) Program. Yelick gave a presentation on “More and Moore: Growing Computing Performance for Scientific Discovery.”
While the federal investment in Networking and Information Technology (NIT) Research and Development (R&D) dates from the birth of the field more than 60 years ago, the High-Performance Computing Act of 1991, recognizing the unique importance NIT R&D to the nation, provided for multi-agency coordination of this investment. The invitation-only symposium in Washington, DC, explored the accomplishments and prospects of this coordinated effort, which involves 15 federal agencies as full partners.
Other speakers on the program included former Vice President Al Gore, who spearheaded the High-Performance Computing Act of 1991; David Keyes of Columbia University and the King Abdullah University of Science and Technology; and Vinton Cerf, one of the “fathers of the Internet” and a member of the ESnet Policy Board. For more information, visit the symposium website.
Workshop on Manycore, Accelerator-Based Scientific Computing Calls for Talks, Posters
The International Center for Computational Sciences (ICCS) in Berkeley and the National Astronomical Observatory/Chinese Academy of Sciences have issued a call for research posters and contributed talks to be presented at the Third International Manycore and Accelerator-Based High-Performance Scientific Computing Workshop, to be held March 26–30 in Beijing. Abstracts for posters and contributed talks must be submitted by this Saturday, February 25. Submissions should be made using the workshop registration site.
The workshop is a joint venture between ICCS/Lawrence Berkeley National Laboratory, the Chinese Academy of Sciences, and the University of Heidelberg, Germany. The National Astronomical Observatories of Chinese Academy of Sciences (NAOC) is a member of a special network operating GPU-accelerated supercomputers for basic and applied sciences in China. For more information, visit the ICCS workshop web site.
Lowell High School Robotics Club Needs Mentor
San Francisco’s Lowell High School Robotics Club needs a mentor with an engineering and programming background to drop in after school or on Saturdays to provide advice and encouragement. Club members are building a robot from scratch and are entering a competition which involves the robot rolling around, pushing a basketball, and throwing the ball into a hoop. Any amount of time the mentor is willing to spend will be appreciated—right now the club has no one. Contact Gaymond.Yee@uc-ciee.org if you are interested.
This Week’s Computing Sciences Seminars
Mathematica 8 Comprehensive Overview
Tuesday, February 21, 9:30–11:30 am, Bldg. 66 auditorium
Repeat: 12:00–1:00 pm, 2-400F
Megan Dino, Wolfram Research
Megan Dino of Wolfram Research will be onsite to demonstrate Mathematica 8, the latest release of the technical, all-in-one integrated software. This seminar will showcase capabilities in modeling, statistics, control systems, graphics and visualization, image processing, computation, Wolfram|Alpha, import/export, database connectivity, data mining/analysis, finance, wavelets, C code generation, and more.
Two Case Studies of Parallel Visualization: Surface Rendering and Particle Advection
Tuesday, February 21, 2:00–3:00 pm, 50F-1647
Boonthanome Nouanesengsy, The Ohio State University
With the advent of significant gains in computational power within the past decade, scientific simulations can now be performed at unprecedented spatial and temporal resolutions. The sheer amount of data generated from these simulations poses a steep challenge when attempting to perform interactive and effective visualization on them. In this talk, I will cover two techniques designed to improve the visualization process for large datasets. The first technique involves testing a large shared-memory machine for parallel rendering. We adapt three parallel rendering techniques originally designed for distributed memory architectures, and test their effectiveness on a modern shared-memory machine. The second method aims to improve the performance of parallel streamline generation. A workload-aware partitioning algorithm is employed to decompose a steady state vector field into partitions with near equal workloads. Compared to a standard round-robin partitioning, our workload-aware partitioning algorithm offers better overall run times and scalability.
Link of the Week: Europe Aims to Become World Leader in Supercomputing
In what is increasingly seen as a global competition for supercomputing capability, the European Commission (EC) last week put forth a plan to double its investment in high performance computing and deploy exascale machines before the end of the decade. HPCwire reports that the plan would increase Europe’s public HPC spend from €630 million to €1.2 billion and pump a greater share of the money into development, training, and creating “new centres of excellence.”
According to an IDC study, even though European GDP is roughly equal to that of the United States, the European Union (EU) only spends about half as much on big iron. As in the US and elsewhere, HPC is seen as a strategic technology to help solve societal issues like climate change and health care and advancing basic science in areas like particle physics and genomics. It is also seen as a means to spur businesses come up with new products and services, as well as increase productivity. As was noted by the EC report that describes its new HPC investment strategy: “At a macroeconomic level, it has been shown that returns on investment in HPC are extremely high and that the companies and countries that invest the most in HPC lead in science and economic success.” Read more.
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.