InTheLoop | 10.04.2010
October 4, 2010
Chorin and Sethian Awarded Prestigious ICIAM Math Prizes
Berkeley Lab’s Alexandre Chorin and James Sethian won prestigious prizes from the International Council for Industrial and Applied Mathematics (ICIAM) for groundbreaking work in applied math, with impacts ranging from fluid mechanics and aerodynamics to medical imaging and semiconductor manufacturing. Chorin won the 2011 Lagrange Prize and Sethian won the 2011 Pioneer Prize. Learn more.
James Demmel Receives 2010 Fernbach Award
James W. Demmel, a professor of mathematics and computer science at the University of California, Berkeley, and a member of CRD’s Future Technologies Group, has been named the recipient of the 2010 IEEE Computer Society Sidney Fernbach Award for his contributions to high-performance linear algebra software. He received the award “for computational science leadership in creating adaptive, innovative, high-performance linear algebra software.” Read more.
CS Researchers Receive $6.3 Million to Tackle Exascale Challenges
Over the last two years, the nation's leading computer scientists held numerous workshops to determine what system requirements will be necessary to advance scientific research in the next decade, and there is nearly universal agreement that supercomputing systems will need to reach exaflop performance, a thousand times faster than today’s petaflop systems, by 2018. Many scientists agree that building an efficient exascale system will require fundamental breakthroughs in hardware technology, programming models, algorithms and software—at both the system and application levels. Because of power constrains, scientists will also have to develop effective designs for data movement and storage.
To tackle these exascale roadblocks, eight research groups at Berkeley Lab will receive approximately $6.3 million in grants from the Department of Energy's (DOE's) Office of Advanced Scientific Computing Research (ASCR) to investigate critical technologies and architectures for exascale computing, extreme scale scientific data management and analysis, as well as X-Stack software. The X-Stack refers to the scientific software stack that supports extreme scale scientific computing, from operating systems to development environments. Read more.
ANAG Has Opening for Project Scientist
The Applied Numerical Algorithms Group (ANAG) in CRD is looking for an experienced candidate to join ANAG for two years as a Project Scientist to participate in collaborative scientific studies in microfluidics with the Center for Nanoscale Control of Geologic CO2. The successful candidate must be able to contribute to ongoing research projects in numerical methods and software for partial differential equations, specifically embedded boundary methods for representing complex geometries. See job details. The Lab’s Employee Referral Incentive Program (ERIP) awards $1,000 (net) to employees whose referral of an external candidate leads to a successful hire.
NASA Conference on Intelligent Data Understanding This Week
The NASA Conference on Intelligent Data Understanding (CIDU 2010) will bring together top researchers and practitioners in the field of data mining focusing on research and development activities in the Earth Sciences, Space Sciences, and Aerospace and Engineering Systems. It will be held tomorrow and Wednesday, October 5–6, at the Computer History Museum in Mountain View, CA. Registration is free; there will be a non-mandatory cost for food of about $100 for both days.
Mike Helm Speaking at Symposium on Authentication Technologies
Mike Helm of ESnet is giving a presentation on the Science Identity Federation at the Symposium on Authentication Technologies for Research and Education being held today through Thursday, October 4–7, at Texas Tech University in Lubbock, Texas. The Science Identity Federation will provide the basis for interoperable identity and identity-based services for DOE national laboratories and their collaborators: academia, other laboratories, and other organizations.
Tony Drummond Giving Invited Talks in Italy, France
Tony Drummond of CRD will give a talk on “Numerical Libraries” this Wednesday, October 6, at the European-US Summer School on HPC Challenges in Computational Sciences, organized by DEISA and TeraGrid, in Catania, Italy. On October 10-13, he will be attending a meeting on auto-tuning techniques and standards for numerical software at INRIA, the French national institute for research in computer science and control, in Saclay, France, where he will present a talk on “Addressing the Multi-Core Performance Challenge for High Performance Numerical Software Tools in the USA DOE ACTS.”
This Week’s Computing Sciences Seminars
Computationally Efficient Statistical Modeling for Spatial and Spatio-Temporal Data
Monday, October 4, 10:00–11:00 am, 50B-4205
Chris Paciorek, University of California, Berkeley
Spatial and spatio-temporal data are ubiquitous in environmental research, including climate science. In this talk, I will briefly describe how statisticians model such data. Then I will focus on the computational issues that arise in such modeling efforts. In particular, traditional spatial statistics models involve covariance matrices of size n by n, where n is the number of observations. Fitting such models involves solving a system of equations via the Cholesky decomposition, which is computationally burdensome. An alternative is to use a Markov random field to represent the spatial surface of interest. This involves specifying a sparse inverse covariance or precision matrix, with resulting computational efficiencies. I’ll present a case study that involves predicting particulate matter air pollution in space and time, using both ground observations and proxy information (remote sensing and atmospheric chemistry model output). In the case study, I highlight the importance of considering systematic discrepancy between the proxy and the true process of interest.
LAPACK Seminar: Recent Progress in Communication Avoiding Algorithms for Linear Algebra
Wednesday, October 6, 11:10 am–12:00 pm, 380 Soda Hall, UC Berkeley
Jim Demmel, UC Berkeley and LBNL/CRD
We discuss recent progress, and obstacles, in both communication lower bounds and upper bounds for various problems in numerical linear algebra.
Link of the Week: Collective Intelligence Boosts Group Performance
According to new study co-authored by researchers at the Massachusetts Institute of Technology, Carnegie Mellon University and Union College, group intelligence may not be quantified as the sum or average of the cognitive abilities of its members. By studying small teams of randomly assembled individuals, researchers discovered that groups featuring the right kind of internal dynamics perform well on a wide range of assignments, regardless of the sum or average individual cognitive abilities of the group’s members.
Further, a group’s intelligence, or its ability to complete a series of demanding multi-functional tasks, is positively linked to higher levels of “social sensitivity,” a more equal distribution of member participation levels, and to the number of women in a group. 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.