A-Z Index | Phone Book | Careers

InTheLoop | 01.19.2010

January 19, 2010

Cecilia Aragon Receives PECASE Award from President Obama

As announced last July, Cecilia Aragon of CRD’s Advanced Computing for Science Department was among the 100 researchers named by President Barack Obama to receive the prestigious Presidential Early Career Award for Scientists and Engineers (PECASE), the highest honor bestowed by the United States government on early-career researchers.

The awards were presented last Wednesday, January 13, in a ceremony in the East Room of the White House. The White House Blog has an article about the award ceremony, including a photo of the recipients with President Obama. You can find Aragon in the front row on the left side, wearing a red turtleneck.

ALS Group Is Establishing New Collaboration with CRD and NERSC

The Advanced Light Source (ALS) Experimental Systems group here at Berkeley Lab has approached the Computational Research and NERSC divisions about collaborating to address mathematical and computational problems they are facing. They have identified a set of problems that they would like to team with mathematicians and computational researchers to address. This presentation gives an introduction to many of these problems.

We will be holding a one-day meeting of CS scientists interested in helping address these problems and the ALS scientists who are facing these challenges. The meeting will be 9:00 am to 3:30 pm on Wednesday, January 27, in Perseverance Hall.

If you are interested in attending, please add yourself to the mailing list als-crd-computing@lists.lbl.gov by subscribing here. If you have questions about the meeting, please contact Deb Agarwal.

Hybrid Multicore Consortium Is Holding First Workshop

The Hybrid Multicore Consortium (co-chaired by Associate Lab Director Horst Simon) is holding its first annual workshop tomorrow and Wednesday (January 20–21) at the Hyatt Regency San Francisco Airport Hotel. The Consortium’s goal is to address the migration of existing applications to accelerator-based systems and thereby maximize the investments in these systems. The main focus is on identifying obstacles to making emerging, large-scale systems based on accelerator technologies production-ready for high-end scientific calculations.

Advanced Subsurface Computing Team Holds Kick-Off Meeting

The DOE Advanced Subsurface Computing for Environmental Management (ASCEM) project will hold its kick-off meeting this week, January 20–21, in the Berkeley Lab Building 50 Auditorium.

ASCEM brings together DOE’s best national laboratory expertise and experience to advance computer modeling capabilities for contaminant fate and transport and degradation of engineered materials to address DOE complex-wide environmental challenges for waste disposal and environmental cleanup. They will accomplish their goals using an open-source platform with state-of-the-art high performance computing, and by producing transformational next-generation simulation software to address prediction, risk reduction, and decision-making support.

Juan Meza of CRD will be one of the discussion leaders for technical and programmatic integration and for the implementation action plan.

Cray XT5 Workshop Has Room for More Participants

There is still room for more participants at the Cray XT5 Workshop to be held on February 1–3, 2010, at Sutardja Dai Hall on the UC Berkeley campus. The workshop will be presented by NERSC along with the Oak Ridge Leadership Computing Facility (OLCF) and the National Institute for Computational Science (NICS) at the University of Tennessee and Oak Ridge National Laboratory. The workshop is designed to provide an in-depth introduction to using the world’s newest and largest Cray XT5 systems to users who already have some high performance computing experience. Go here to register.

Job Openings in ESnet and NERSC

ESnet has an immediate opening for a Chief Information Strategist. This member of the executive team will provide technical guidance to the Department Head regarding IT initiatives, playing a major role in shaping organizational strategies toward the integration of emerging technologies and services (such as cloud services, web 2.0, etc.) into the ESnet infrastructure to meet both the organization's business needs and the community’s scientific requirements; work closely with the vendor community and ESnet group leads and product managers in the identification, planning, and delivery of new end-user services by managing cross-departmental projects and driving collaboration across ESnet teams in order to meet a shared vision; and participate in ESnet’s community activities through technical papers, presentations and the development of peer to peer relationships with staff at other DOE sites and industry. Go here for job details.

ESnet’s Advanced Network Technologies Group is seeking a Software and Network Engineer to work on the OSCARS and perfSONAR project. This engineer will work on a wide array of problems, including software development, installation, configuration, and testing, and performance testing and analysis. Go here for job details.

NERSC’s Network and Security Group has an opening for a Computer Security Analyst who will be responsible for developing and monitoring computer security on workstations, servers, and high performance clusters and supercomputers, as well as detecting, investigating, and resolving intrusions. Go here for job details.

Four out of eight openings are still available for postdoctoral fellows in the NERSC Division to address the challenges of petascale computing on new multicore architectures. The fellows will work with high-profile applications in the areas of bioscience, fusion, climate, and material science as well as in the development of scalable algorithms and novel language implementations for modern petascale systems. Go here for 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.

David Paul Is Elected President of SPXXL User Group

David Paul of NERSC’s Systems Department has been elected president of SPXXL, a user group for sites which have large installations of IBM equipment. The focus of the SPXXL group is on large-scale scientific/technical computing using IBM hardware.

Margie Wylie Joins CS Communications Team

Margie Wylie, who has more than 15 years as a science and technology writer, has joined the Computing Sciences communications team. Margie will focus mainly on communications projects in support of NERSC and will divide her time between the Hill and OSF. During her career, Margie helped launch CNET News, was a technology editor for the San Jose Mercury News, and spent seven years as a national correspondent for science and technology for the Newhouse News Service. Most recently, she was senior editor at Tendo Communications in San Francisco, providing communications support for a number of clients, including HP and HP Labs. She is also familiar with Berkeley Lab, having worked on several projects for the Creative Services Office.

Petabyte-Scale Analytics: Cloudera and Facebook on Hadoop and Hive

The ACM SFBay Data Mining Special Interest Group invites you to hear Amr Awadallah, CTO and founder of Cloudera, and Ashish Thusoo, founder of Facebook’s Hive project, talk about how Hadoop and Hive enable analytics on a petabyte scale. The free talks will begin at 6:30 pm on Monday, January 25, at LinkedIn, 2027 Stierlin Ct., Mountain View, CA. For more information, go here.

This Week’s Computing Sciences Seminars

Globus’ Future (Grid Meets Cloud)
Tuesday, January 19, 1:00–2:00 pm, 50F-1647 and 943-254
Steve Tuecke, University of Chicago and Argonne National Laboratory

Globus is open source grid software and online software-as-a-service that addresses many challenging problems in distributed resource sharing for scientific computing applications, including security, resource discovery, distributed job management, and distributed data management. Globus provides the foundation to most of the world’s large-scale grid infrastructures for science. The Globus team recently announced a high-level plan for Globus’ future. This talk will delve into this plan more deeply, in each area discussing rationale, alternatives considered, decisions, and future plans.

LAPACK Seminar: Expanders and Communication-Avoiding Algorithms
Wednesday, Jan. 20, 11:10 am–12:00 pm, 740 Evans Hall, UC Berkeley
Oded Schwartz, TU Berlin

Algorithms spend time on performing arithmetic computations, but often more on moving data, between the levels of a memory hierarchy and between parallel computing entities. Judging by the hardware evolution of the last few decades, the fraction of running time spent on communication is expected to increase, and with it the demand for communication-avoiding algorithms. We use geometric, combinatorial, and algebraic ideas and techniques, some of which are known in the context of expander graphs, to construct provably communication-optimal algorithms.

Energy Efficient Electronics: Searching for the Milli-Volt Switch
Wednesday, Jan. 20, 12:00–1:00 pm, Banatao Aud., Sutardja Dai Hall, UC Berkeley
Eli Yablonovitch, UC Berkeley
Broadcast live on-line at mms://media.citris.berkeley.edu/webcast

Because of miniaturization represented by Moore’s Law, the energy efficiency of information processing steadily improves. We anticipate that the energy required to process a single bit of information will eventually become as tiny as 1 electron volt per function. Inevitably, most logic functions, including storage and readout, will eventually be that efficient.

However, there is one information-processing-function that bucks this trend. That is communication, especially over short distances. Our best projections of improvements in the short distance communication function show that it will still require hundreds of thousands of electron volts just to move one bit of information 10 micrometers. This energy per bit discrepancy for communications is caused by the difference in voltage scale between the wires and the transistor switches. Transistors are thermally activated, leading to a required voltage >>kT/q. Wires are long, and they have a low impedance, allowing them to operate efficiently even at ~1 millivolt.

The challenge, then, is to replace transistors with a new low-voltage switch that is better matched to the wires. I will present some of the technical options for such a new switch.

The Future of DRAM Technology
Friday, Jan. 22, 1:00–2:00 pm, 521 Cory Hall (Hogan Room), UC Berkeley
Gill Lee, Director of Memory Technology, Applied Materials, Santa Clara, CA

DRAM has long been one of the key technology drivers in the ever shrinking semiconductor technology, and DRAM products have been essential components in the modern industry. In the past, the DRAM industry has successfully developed new technologies that are necessary for the continued scaling of the array access transistor and the storage node capacitor in timely and cost effective manners. As the DRAM industry approaches the 30nm generation, the physical limitation combined with the cost challenges lead to the fundamental review of basic architecture to seek its continuous scaling, and the DRAM industry has been developing new technology rather successfully employing new architectures. However, for the scaling to successfully go beyond the 30nm generation, the DRAM technology must come up with a series of new innovations in order to overcome the ever growing technical and economical issues. This presentation will discuss the recent history of the DRAM industry, the technology roadmap, the cell innovations, the array transistor scaling, and the storage capacitor scaling, and then cautiously project the future of DRAM technology.

Link of the Week: Is Politics Mathematically Predictable?

Bruce Bueno de Mesquita, according to the New York Times Magazine,

is one of the world’s most prominent applied game theorists. A professor at New York University and a senior fellow at the Hoover Institution at Stanford, he is well known academically for his work on “political survival,” or how leaders build coalitions to stay in power. But among national-security types and corporate decision makers, he is even better known for his prognostications. For 29 years, Bueno de Mesquita has been developing and honing a computer model that predicts the outcome of any situation in which parties can be described as trying to persuade or coerce one another.

A Times review of Bueno de Mesquita’s new book, “The Predictioneer’s Game: Using the Logic of Brazen Self-Interest to See and Shape the Future,” says:

His simulations rely on four factors: who has a stake; what each of these people wants; how much they care; and how much influence they have on others. He surveys experts on the topic, assigns numerical values to the four factors, plugs the data into a computer and waits for his software to spit out the future.

In a November 2009 article in Foreign Policy, Bueno de Mesquita explained why he thought the Copenhagen conference would fail, and why he’s still optimistic that the global warming problem will be solved. And in a TED video from February 2009, he predicts Iran’s future.

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.