A-Z Index | Phone Book | Careers

InTheLoop | 04.18.2011

April 18, 2011

“Drag and Drop Archiving” Earns Innovation Award for NERSC

At GlobusWORLD 2011, held April 11–13 at Argonne National Laboratory, NERSC was awarded “Most Innovative Use of Globus Online” for using it to archive data onto HPSS. In a session on “Globus Community Updates and User Experiences,” Shreyas Cholia presented this use case in his talk “Globus Online @ NERSC.”

Archiving data has traditionally involved running command-line tools, but several NERSC users have requested a graphical user interface (GUI) to move data between HPSS and compute systems. A GUI makes it easier to back up or restore relevant data. Using Globus Online, NERSC implemented a “Drag and Drop Archiving” capability which is currently being tested and will be available to the NERSC user community shortly. Contributing to the implementation and testing are Shreyas Cholia, Nick Balthaser, and Matt Andrews of NERSC, and Michael Link and Karl Pickett of Argonne National Lab.


Using perfSONAR to Find Network Anomalies

ESnet and Berkeley Lab Computing Sciences recently sponsored a talk on network anomaly detection by Prasad Calyam, Ph.D., from the Ohio Supercomputer Center/OARnet, and The Ohio State University. For the last year and a half, Calyam has worked on a DOE funded perfSONAR-related project. He emphasized that accurate measurement is necessary to be able to troubleshoot in multiple domains and layers. Calyam’s group is developing metrics and adaptive performance sampling techniques to analyze network performance across multiple layers for better network status awareness, performance, and to determine optimal paths for large data sets. Read more.


Lab Reps Climb the Hill to Brief Congress/Staffers

On Thursday, April 7, while Congress was deliberating budget cuts, five Berkeley Lab national user facilities administrators (including David Skinner of NERSC) and their outside user representatives (those who have benefited from access to a facility) made a strong and timely showing on Capitol Hill. Led by Berkeley Lab head of federal government relations Don Medley, the team spent the first part of the day briefing staffers from Senators Feinstein and Boxer’s offices, and had a short conversation with staff from the office of Representative Barbara Lee, before joining an even larger contingent from some 40 other user facilities from around the country.

They convened in the foyer of the Rayburn House Office Building at the official invitation of several members of Congress to hold an exhibition to educate members and staff about the research being conducted at national user facilities, as well as the ultimate benefit of this research to the United States, under the auspices of the National User Facility Organization (NUFO). Several National Laboratory Directors participated, including Berkeley Lab’s Paul Alivisatos and Oak Ridge’s Thom Mason, who addressed the gathering. Director of the DOE Office of Science William Brinkman and Pat Dehmer, Deputy Director for Science Programs, DOE Office of Science, were also in attendance. See photo.


Safety Culture Survey Results Are Now Available

Safety was named as one of Lab Director Paul Alivisatos’s strategic goals in his January 2010 State of the Lab address. A DuPont Safety Culture Survey was sent to the Lab community in November 2010. Results indicate there are several areas for improvement, both at the institutional level and at the divisional level.

EHS staff presented a summary of the CS, CRD, NERSC, and OSF safety culture survey results to the CS Safety Committee on April 1, 2011. A copy of this presentation, along with detailed results for each group, are posted here for review by staff.

While there are some differences between the divisions, the results show several opportunities for improvement:

  • Belief that injuries can be prevented
  • Involvement in safety
  • Recognition of safety achievements by the organization
  • Off-the-job safety

Areas where Computing Sciences could consider making changes were “supervisor and manager accountability for safety” (specifically in CS) and “frequency of safety meetings.” CS management and the CS Safety Committee will review these issues and formulate responses to improve our safety culture.


“Navigating NERSC File Systems” Training on April 26

A NERSC training event, “Navigating NERSC File Systems,” will be presented Tuesday, April 26, 2011, from 10:00 to 11:00 am PDT. The event will be presented simultaneously at the NERSC Oakland Scientific Facility and as a webcast.

NERSC hosts a number of file storage systems, each with its unique characteristics. In this tutorial we will describe best uses for each file system, their data retention policies, how to move data among them, and how to share data with colleagues.

Please go here for free registration. Registered users will have priority access to the webcast.


NERSC Staff Address Lustre User Group Conference

Two NERSC staff members addressed the annual Lustre User Group conference (LUG 2011), which was held April 12–14 in Orlando, FL. Lustre is the open-source parallel file system used on NERSC’s Cray XT systems. Andrew Uselton presented “The Statistical Properties of Lustre Server-Side I/O,” and Nick Cardo discussed “Detecting Hidden File System Problems.”


i4Science Lecture Series Sponsors Eight Talks on May 3, 5 at CITRIS

The Berkeley Computational Science and Engineering program, developed jointly by Berkeley Lab Computing Sciences, UC Berkeley, and the University’s Center for Information Technology Research in the Interest of Society (CITRIS), is sponsoring a series of presentations on Tuesday, May 3, and Thursday, May 5. The talks are open to the public and will be held in the Banatao Auditorium in Sutardja Dai Hall on the Cal campus.

CSE is a rapidly growing multidisciplinary field that encompasses real-world complex applications (scientific, engineering, social, economic, policy), computational mathematics, and computer science and engineering. High performance computing, large-scale simulations and scientific applications all play a central role in CSE. i4Science will focus mainly on a smaller subset of CSE applications that within three to five years would be scalable from thousands to millions of processors and from tera- to exascale computing using emerging computing technologies.

Here is the i4Science lecture schedule:

Tuesday, May 3
Noon–1 pm: Eng Lim Goh, senior vice president and chief technology officer at SGI, will discuss “Computer Modeling of Natural and Synthetic Systems.”

Thursday, May 5
Noon–1:15 pm: New Engineering Trends and Data Challenges

  • 12:15–12:45 pm: Prof. Jose Carmena, co-director of the Center for Neural Engineering and Prostheses at UC Berkeley and UCSF and professor in the Brain-Machine Interface Systems Laboratory at UCB, will discuss “New Trends in Neural Engineering and Prostheses.”
  • 12:45–1:15 pm: Juan Meza, Acting Director of LBNL’s Computational Research Division (CRD), will discuss “Data Challenges in Energy and Environmental Applications.”

1:15–2:00 pm: Jim Spohrer, director of IBM University Programs Worldwide, will discuss “The Future of ICT to Build a Smarter Planet.”

2:00–3:00 pm: Computation and Data-Driven Modeling

  • 2:00–2:30 pm: Bahram Parvin, a scientist in LBNL’s Life Sciences Division, will discuss “Computational Histopathology for the Cancer Genome Atlas.”
  • 2:30-3:00 pm: Harish Bhat, assistant professor of applied mathematics at UC Merced, will discuss “Data-Driven Modeling and Prediction of Startup Company Exits.”

3:00–4:00 pm: Trends in NeuroScience

  • 3:00–3:30 pm: Bruno Olshausen, director of the Redwood Center for Theoretical Neuroscience at UC Berkeley, will discuss “Finding Patterns of Activity in Large-Scale Neural Recordings.”
  • 3:30–4:00 pm: Fritz Sommer, associate adjunct professor at the Redwood Center for Theoretical Neuroscience and faculty member at the University of Ulm, Germany, will discuss “Online Repositories for Neuroscience Enable Concerted Efforts to Understand the Brain.”


This Week’s Computing Sciences Seminars

LAPACK Seminar: Detecting Low-Rank Submatrices: Some Methods and Applications
Wednesday, April 20, 11:10 am–12 pm, 380 Soda Hall, UC Berkeley
Aaditya Rangan, NYU

Many techniques for matrix-compression, such as matrix-skeletonization, take advantage of the reduction in dimensionality which can be attained when the matrices in question have structurally evident low-rank sub-blocks. A natural question when dealing with a matrix of unknown structure is: How can one detect the submatrices of low rank? In this talk I will describe some techniques for detecting low-rank submatrices. I will also present a few examples where these techniques can be used for matrix-compression, and as tools for data-analysis.

Block Red-Black Ordering for Parallel IC/ILU Preconditioning and Multigrid Poisson Solver
Thursday, April 21, 11:00 am–12:00 pm, 50B-4205
Takeshi Iwashita, Academic Center for Computing and Media Studies, Kyoto University

This talk consists of three parts. In the first part (main part), a parallel ordering technique for parallelization of IC/ILU preconditioning is introduced. The parallel ordering is called “block red-black ordering.” The technique has the advantage that only one synchronization point exists in each parallelized substitution. The numerical tests show that the parallel ordering technique achieves a high parallel speed-up rate due to fast convergence, small synchronization costs, and effective utilization of the data cache on a non-vector parallel computer. The details of this part can be seen in [1].

Next, I briefly introduce an analytic index for convergence for parallel orderings. The proposed index, S.R.I., which is based on the remainder matrix, is easily computed and has a unique value for a fixed ordering. Nodes are classified into seven groups, and the effect of each group on convergence is estimated. More details of the work are shown in [2].

The third part of the talk is about my latest result. My student and I recently developed a Poisson solver library based on a geometrical multigrid method. By using the block red-black ordering for parallelization of Gauss-Seidel smoother, we attained the better performance than a red-black GS smoother. I briefly introduce the overview of the solver and how to use it.

[1] T. Iwashita and M. Shimasaki, “Block Red-Black Ordering: A New Ordering Strategy for Parallelization of ICCG Method,”' International Journal of Parallel Programming, Vol. 31, No. 1, (2003), pp. 55-75.

[2] T. Iwashita, Y. Nakanishi and M. Shimasaki “Comparison Criteria for Parallel Orderings in ILU Preconditioning,” SIAM Journal on Scientific Computing, Vol. 26, No. 4, (2005), pp.1234-1260.

Lessons from the WILD Room, an Interactive Multi-Surface Environment
Thursday, April 21, 4:00–5:00 pm, 521 Cory Hall, UC Berkeley
Michel Beaudouin-Lafon, University of Paris-Sud

Creating the next generation of interactive systems requires experimental platforms that let us explore novel forms of interaction in real settings. The WILD room (Wall-size Interaction with Large Datasets, http://www.lri.fr/~mbl/WILD) is a high-performance interactive visualization environment for exploring the notion of multi-surface interaction. WILD combines an ultra-high resolution wall display, a multitouch table, a motion tracking system and various mobile devices. Our target users are scientists who are confronted with massive amounts of data, including astrophysicists, biologists and neuroscientists. I will describe the design trade-offs and lessons learned during the development of this platform with respect to hardware, interaction, software engineering, and participatory design of applications.


Link of the Week: Death Anxiety Shapes Views on Evolution

It may be the foundation of modern biology, but fewer than 40 percent of Americans say they believe in the theory of evolution. While frustrated scientists sometimes blame religion for this knowledge gap, newly published research suggests the key factor isn’t faith per se but rather a benefit it provides that Darwin does not: A sense that our all-too-short lives have meaning. But the research also shows that science can be successfully presented as a source of meaning in response to an existential threat. 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.