InTheLoop | 05.31.2011
May 31, 2011
Petaflops Power to NERSC!
NERSC has accepted its first petaflops supercomputer—a 153,216-core Cray XE6. The new flagship system is called “Hopper” in honor of American computer scientist Grace Hopper, who was a pioneer in the field of software development and programming languages. The system is currently the fifth most powerful supercomputer in the world and the second most powerful in the United States, according to the latest edition of the TOP500 list. Read more or view a slide show of the Hopper installation.
FastBit Featured in DOE SC Stories of Discovery & Innovation
FastBit, the Berkeley Lab-developed software that quickly finds information in massive databases, is the subject of a feature story, “Superfast Search Engine Speeds Past the Competition,” in the Stories of Discovery & Innovation section of the DOE Office of Science website. Although the software was developed for analyzing physics data, the article points out that it has also found powerful commercial applications.
“Getting Started at NERSC” Training on June 7
NERSC will present a two-hour “Getting Started at NERSC” training event aimed at new users on Tuesday, June 7, from 10:00 am to 12:00 pm. This event will be broadcast over the web and presented in person at NERSC’s Oakland Scientific Facility. For more information and to register, go here. There is no registration fee, but registering helps with planning.
David Culler Appointed Faculty Director of i4Energy Center
David E. Culler, Professor and Chair of Computer Science at UC Berkeley, Associate Chair of the Department of Electrical Engineering and Computer Science, and Associate CIO of the College of Engineering has been appointed Faculty Director of the i4Energy Center. Culler is also a faculty researcher in the Berkeley Lab Computational Research Division’s Future Technologies Group.
The i4Energy Center is a collaboration among the Center for Information Technology Research in the Interest of Society (CITRIS: UC Berkeley, Davis, Merced, and Santa Cruz), the California Institute for Energy and Environment (CIEE), and the Environmental Energy Technologies Division at Lawrence Berkeley National Laboratory (LBNL). The mission of the Center is to facilitate and promote research on system-integrated enabling technologies that will achieve better energy efficiency, improved demand/response, and dramatic improvements in energy distribution. Read more.
Al Early: 22 Years of Making All the Right Connections
Al Early clearly remembers his first impression of the Lab. Encouraged by a colleague to apply for a computer support job, Early arrived one afternoon to find a staff barbecue in full swing and with many people wearing shorts or other casual attire.
“I thought right then and there that this was the kind of place where I wanted to work,” said Early, who will retire in June after 22 years at Berkeley Lab, most of it spent in what is now the IT Division. For most of his career here, Early worked as a member of the LBLnet team, installing, managing and supporting the extensive networking linking Lab researchers and connecting them to the outside world via ESnet. Read more.
ICiS 2011 Announces Summer Workshops in Park City, Utah
This year the DOE-supported Institute for Computing in Science (ICiS) is hosting eight week-long workshops starting July 16 through August 6 in Park City, Utah. The ICiS institute aims to build ties between the computer science, mathematics, and computational science communities through an annual series of intensive workshops aimed at examining deep questions that lie at the intersection of computation and science. Go here for this summer’s lineup.
The workshops are aimed at forging deep connections between researchers in a setting that promotes interaction, thoughtful discussion, and plenty of time for reflection. Each session is approximately 30 people. All participants are expected to attend for the duration of the meeting and actively participate in the discussions, talks, and brainstorming sessions. Some will be asked to give talks that will frame issues and possible approaches to the problems.
Three sessions still have some room available:
- “MyAnton” will look at the prospects and challenges of affordable custom or semi-custom hardware to support specific scientific applications.
- “Verification, Validation and Uncertainty Quantification Across Disciplines” aims to bring together practitioners from across the natural and social sciences, from data rich to data poor environments, together with computer scientists and applied mathematicians involved in developing V&V and UQ methodologies.
- “Future of the Field” will look at challenges in billion-way concurrency, the possibility of probability computing, and new ideas targeting 2025 and beyond.
Other sessions are close to capacity, though there is some flexibility to add additional space based on demand. ICiS can provide a limited number of stipends to cover most of the expenses of attending. All of the sessions are being held at the Canyons Conference Center in Park City. Bringing your family is encouraged, and there are many activities for a range of age groups. For more information, contact firstname.lastname@example.org.
This Week’s Computing Sciences Seminars
Static Analysis of Multi-Staged Programs
Tuesday, May 31, 4:00–5:00 pm, 310 Soda Hall, UC Berkeley
Kwangkeun Yi, Seoul National University
I will present a general static analysis framework of multi-staged programs. Multi-staged programming have program text as first-class values (e.g. in runtime program generation in web/mobile apps, partial evaluation, and macro systems). Statically analyzing the semantics of multi-staged programs is challenging because the program text itself is no longer a fixed static entity, but rather a dynamically constructed value. Our proposed static analysis framework consists of three steps: we first apply a semantics-preserving unstaging translation, then we apply conventional static analysis to the unstaged version, and finally we cast the analysis results back in terms of the original staged program. Our translation handles staging constructs that have been evolved to be useful in practice: open code as values, unrestricted operations on references and intentional variable-capturing substitutions. We showed the correctness of the unstaging translation and a correctness condition of the three-step detouring of multi-staged static analysis.
This work was presented at POPL 2011 and is a co-work with Wontae Choi, Baris Aktemur, and Makoto Tatsuda.
Link of the Week: Mind over Milkshakes
After eating food marketed as “low-fat” or “guilt-free,” do you still feel hungry? If so, don’t blame the food. Blame the label.
A key hormone associated with the feeling of satiety responds far more dramatically when people think they are consuming an indulgent treat. That’s the conclusion of newly published research from Yale University, which finds that what we tell ourselves about the food we eat affects the point at which we start feeling full.
The study, tastily titled “Mind Over Milkshakes,” has weighty implications for the campaign against obesity. Its findings suggest labeling foods as healthy may be counterproductive, since doing so apparently produces an unwanted and unhelpful physical response. Think of it as the evil twin of the placebo effect. 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.