InTheLoop | 07.29.2013
Papers by ESnet, CRD Staff Nominated for Best Paper Awards at SC13 Conference
Two technical papers co-authored by Computing Sciences staff have been nominated for “Best Paper” awards at the SC13 conference to be held Nov. 17-22 in Denver. Of the 92 accepted papers, eight were nominated for Best Paper and eight for Best Student Paper.
Eli Dart, Lauren Rotman, Brian Tierney and Mary Hester of ESnet are co-authors of “The Science DMZ: A Network Design Pattern for Data-Intensive Science” along with Jason Zurawski, who worked at Internet2 when the paper was submitted but who has since joined ESnet. The paper, nominated for a Best Paper Award., describes how a network architecture called ScienceDMZ, developed by ESnet, helps researchers who would otherwise struggle with improperly built cyberinfrastructure that cripples their data transfer performance, despite external connections to high-bandwidth networks. Read a Q&A with Eli Dart about the Science DMZ.
As a Ph.D. student at Pennsylvania State University, Myoungsoo Jung spent two summers as a guest research scientist working with CRD’s Hasan Metin Aktulga and John Shalf to model and simulate diverse memory technologies on scientific applications for reducing power consumption in exascale computing systems. Jung is the lead author of “Exploring the Future of Out-Of-Core Computing with Compute-Local Non-Volatile Memory,” along with Shalf, Aktulga and Chao Yang of CRD; Ellis H. Wilson III, Wonil Choi and Mahmut Kandemir of Penn State; and Erik Saule and Umit V. Catalyurek of Ohio State University. The paper was nominated for both Best Student Paper and Best Paper awards.
CRD’s Sherry Li Is Invited Lecturer at Gene Golub SIAM Summer School
Xiaoye “Sherry” Li of the Scientific Computing Group in the Computational Research Division is one of five invited lecturers for the 2013 Gene Golub SIAM Summer School to be held Aug. 5-9 at Fudan University in Shanghai. The program is sponsored by the Society for Industrial and Applied Mathematics (SIAM) through an endowment from the estate of Gene Golub, a professor of computer science at Stanford University and one of the preeminent numerical analysts of his generation.
This year’s summer school, the fourth in the series, will introduce students to underlying theory, algorithms and applications of matrix functions and matrix equations, and relevant linear solvers and eigenvalue computations. Matrix functions and matrix equations are widely used in science, engineering and the social sciences, due to the succinct and insightful way they allow problems to be formulated and solutions to be expressed.
The participants are students, postdocs and junior researchers. Li will teach 10 hours of lectures on “Factorization based sparse solvers and preconditioners.” Li is well known for her working in developing sparse matrix solvers and SuperLU, the software library for solving sparse linear systems of equations she developed for her Ph.D., was downloaded more than 24,000 times in FY2012.
CS Summer Students to Present Lab Experiences at Aug. 1 Poster Session
Each year, as the culmination of the CS Summer Student Program, a poster session gives students the opportunity to prepare and present posters that summarize their experience at the lab and present results of their research here. For many students, this is their first opportunity to present their work via a poster presentation. This year’s session will be held from 2-5 p.m. Thursday, Aug. 1, in the Lab cafeteria and all employees are invited to attend.
The session, to be held in conjunction with the poster session for students participating in LBNL's Center for Science and Engineering Education program, also allows students to interact and share ideas with each other, while allowing mentors to review and learn from the poster presentations.
East Bay Consortium of Educational Institutions Visits Berkeley Lab
About 40 students from the East Bay Consortium of Educational Institutions visited Berkeley Lab on July 26 to learn about careers in science, technology, engineering and mathematics. Deb Agarwal,who heads CRD's Advanced Computing for Sciences Department, welcomed the group and gave a brief overview of Berkeley Lab. Then, Andy Nonaka(CRD) talked about his research is computational cosmology, Ben Bowen(Life Sciences Division) talked about mass spectroscopy and Susan Amrose (Environmental Energy Technology Division) talked about engineering projects to improve the quality of life in developing countries. The visit culminated with a tour of the Advanced Light Source led by Christine Beavers, Bruce Rude , Thomas Scarvieand Doug Taube . The visit was organized by CRD's Sarah Poon .
Green Flash Project Featured in UC Berkeley Science Review
Green Flash, an innovative architecture first proposed by CS researchers in 2008 as a way to improve global climate change predictions by using a supercomputer with low-power embedded microprocessors, has drawn the attention of Berkeley Science Review, a graduate student-run magazine that aims to highlight the groundbreaking research occurring at UC Berkeley in a wide variety of scientific disciplines, from biology to physics to computer science.
In an article published in the Spring 2013 issue, Anna Lieb writes “Like the planet they simulate, climate models themselves are changing. As our scientific computing technology improves, models are getting larger and more complicated in order to make better predictions. However, with greater predictive power comes greater demand for computational and electric power. In fact, scaling up the current generation of models to meet the need for reliable local-level predictions could require as much power as a city of 100,000 inhabitants.”
The article also led to a write-up in HPCwire.
This Week’s Computing Sciences Seminars
European Human Brain Project: Opportunities for new Developments in Computing
Monday, July 29, 10:30 a.m. – 12 p.m., Bldg. 50B, Room 4205
Prof. Dr. Thomas Schulthess, Director, Swiss National Supercomputing Center
Abstract: The goal of the EU Human Brain Project is to pull together all our existing knowledge about the human brain and to reconstruct the brain, piece by piece, in supercomputer-based models and simulations. The models offer the prospect of a new understanding of the human brain and its diseases and of completely new computing and robotic technologies. Central to the Human Brain Project is Information and Computing Technology (ICT). The project will develop ICT platforms for neuroinformatics, brain simulation and supercomputing that will make it possible to federate neuroscience data from all over the world, to integrate the data in unifying models and simulations of the brain, to check the models against data from biology and to make them available to the world scientific community. Exploiting the resulting knowledge on the architecture and circuitry of the brain will allow researchers to develop new computing systems. Starting in 2013, the European Commission will support this vision through the new FET Flagship Program. Federating more than 80 European and international research institutions, the Human Brain Project is planned to last ten years and estimated to cost an estimated EUR 1,190 million. This talk aims at presenting the challenge and the progress and to provide a platform for engaging the community of high performance computing and beyond.