2011

October

ASCR Monthly Computing News Report - October 2011



The monthly survey of computing news of interest to ASCR is compiled by Jon Bashor (JBashor@lbl.gov) with news provided by ASCR Program Managers and Argonne, Fermi, Lawrence Berkeley, Lawrence Livermore, Los Alamos, Oak Ridge, Pacific Northwest and Sandia National labs. Contact information and links to additional information, where available, are included with each article.
 
In this issue:
 
 
 
 

RESEARCH NEWS:

LLNL’s Mirin Doubles Performance of Community Atmosphere Model on ALCF’s Intrepid
Under the auspices of a Scientific Application Partnership affiliated with the Scientific Discovery for Advanced Computing (SciDAC) project “A Scalable and Extensible Earth System Model for Climate Change Science,” researcher Art Mirin of Lawrence Livermore National Laboratory (LLNL) has doubled the performance of the Community Atmosphere Model (CAM) using the newly supported spectral element (HOMME) dynamical core on the Argonne Leadership Computing Facility’s Intrepid Blue Gene P machine. Performance comparisons were carried out with the standard CAM5 physics and exclusive of the land model (aqua-planet mode). When invoking comprehensive chemistry, the speed increase is even larger. This has come about through improvements in hybrid parallelism, enabling the code to utilize, for the first time, multiple CPUs per spectral element. CAM is the atmospheric component of the Community Earth System Model (CESM), which is being used to carry out simulations for the Intergovernmental Panel on Climate Change (IPCC) fifth assessment. The highly scalable spectral element dynamical core is slated to be designated the dynamical core of choice in the upcoming CAM5.2 release.
 
Jaguar Shows How Proteins Help DNA Replicate Past a Damaged Site
Ultraviolet light, oxidants and environmental toxins constantly assault the genome of a cell. Consequences in the absence of DNA repair could be severe—accelerated aging, degenerative disease or cancer. Fortunately, cells have evolved sophisticated mechanisms for dealing with DNA damage, stabilizing their genomes, and ensuring their survival. Recently, a multi-institutional research team led by Ivaylo Ivanov of Georgia State University has employed the Jaguar supercomputer at Oak Ridge National Laboratory (ORNL) and X-rays a billion times brighter than the sun, produced at Lawrence Berkeley National Laboratory, to illuminate how DNA replication continues past a damaged site so a lesion can be repaired later. The combination of computation and experiment reveals conformations that ubiquitin (Ub), a small protein that binds and orients DNA-editing enzymes, can assume when it associates with a molecular “tool belt” called proliferating cell nuclear antigen (PCNA). The results appear in the October 17, 2011, online issue of Proceedings of the National Academy of Sciences.
 
The researchers received an INCITE allocation of 4 million processor hours in 2010 and 2011, which they ran on ORNL’s Jaguar Cray XT5 supercomputer. Next they aim to develop and apply novel multiscale computational protocols, which would allow integrative modeling of complex biological assemblies. Results from this line of research, specifically for DNA replication and repair complexes, could lead to biomedical advances in the diagnosis, prognosis, and treatment of cancer and inherited disorders.
 
Georgia State University, the Cleon C. Arrington Research Initiation Grant Program, the National Cancer Institute, the National Institute of General Medical Sciences, and the National Science Foundation supported the work.
Read more about Ivanov’s workExternal link
 
NERSC Science Gateway a “Google of Material Properties”
New materials are crucial to building a clean energy economy—for everything from batteries to photovoltaics to lighter weight vehicles—but today the development cycle is too slow: around 18 years from conception to commercialization. To speed up this process, a team of researchers from Berkeley Lab and the Massachusetts Institute of Technology (MIT) teamed up to develop a new computational tool. Called the Materials Project, it launched in October.
 
The Materials Project employs an approach to materials science inspired by genomics. But rather than sequencing genomes, researchers are using supercomputers to characterize the properties of inorganic compounds, such as their stability, voltage, capacity, and oxidation state. The results are then organized into a database with a user-friendly web interface that gives all researchers free and easy access and searching. The tool, which sits on the National Energy Research Scientific Computing Center’s (NERSC’s) science gateway infrastructure, was developed with support from the Department of Energy and a Laboratory Directed Research and Development Grant from Berkeley Lab..
 
Understanding Oil Plume Behavior in a Stratified and Rotating Ocean
A key mystery for scientists is understanding the flow patterns, mixing behavior, surface presence and distribution of buoyant plumes of oil in a stratified and rotating environment such as the ocean. Knowledge of this behavior is directly applicable to understanding how the Deepwater Horizon oil spill distributed within the Gulf of Mexico. Studying the behavior of buoyant plumes, like those of the spill, could correlate the observations of oil on the ocean surface with the amount of oil that actually spilled.
 
Tamay Ozgokmen from the University of Miami, in collaboration with Argonne National Laboratory researchers, is doing the first-ever simulations of the buoyant plumes in a stratified and rotating environment. This project uses Nek5000, an application to which the Argonne Leadership Computing Facility has contributed significantly, including achieving 19 percent of peak on 262K cores.
 
Initial results showed that it can be difficult for the plume to cross stratification barriers caused by pressure and temperature variations. Additional results showed behavior of the plume after the spill was shut off. Further studies will quantitatively explore the dispersion behavior and rotational behavior of the plume. The research will improve the ability to evaluate oil releases at underwater drilling sites and perhaps mitigate consequences at the surface.
Oil Plume Side view of a buoyant plume interacting with ocean flows near the surface. Note the vertical coherence of the plume and its inability to cross the base of the oceanic surface mixed layer. Image credit: Tamay Ozgokmen, University of Miami; Paul Fischer and Aleks Obabko, Argonne National Laboratory; and Hank Childs, Lawrence Berkeley National Laboratory.
For more information, contact Tamay Ozgokmen, University of Miami (tozgokmen@rsmas.miami.edu)
 
Public-Private Collaborative Demo Leverages ESnet's ANI Testbed
Researchers at DOE’s Energy Sciences Network (ESnet), Orange Silicon Valley, and Bay Microsystems have collaborated to showcase the world’s first 40 Gbps (gigabits per second) wide area network demonstration of remote direct memory access (RDMA) over InfiniBand. While RDMA over InfiniBand is not a new concept, this experiment marks the first time that it has been demonstrated at 40 Gbps data rates over long distances, in this case about200 miles.
 
RDMA works by enabling network adapters to transfer data to or from application memory, eliminating the overhead of copying data between application memory and the data buffers in the operating system. When an application performs an RDMA operation, the application data is delivered directly to the network eliminating the additional latency the transfer would incur if the data were to be copied into the operating system memory buffers. This dramatically increases the application-messaging rate and increases the utilization of available network bandwidth.
 
The long-haul RDMA demonstration is part of a research project being conducted at Brookhaven National Laboratory (BNL) in New York and leverages ESnet’s Advanced Networking Initiative 100 Gbps testbed. The testbed is being made available to researchers both in the public and private sector as a first of its kind platform to test different and potentially disruptive approaches to new network protocols and architectures in a greater than 10 Gbps network environment. The testbed is currently available in the Long Island, New York region but will soon have a national footprint to enable experimentation at even greater distances.
 
Award-Winning Application Uses Jaguar to Analyze Promising Materials
A team led by ORNL’s Markus Eisenbach is using an application that took the 2009 ACM Gordon Bell Prize as the world’s most advanced scientific computing application to simulate the magnetic properties of promising materials, focusing in particular on the magnetocaloric effect. Its work is detailed in three recent papers in the Journal of Applied Physics.
 
There are at least three substantial challenges to using the magnetocaloric effect commercially: a material must show a large enough shift in temperature as it moves in and out of the magnetic field; it must show that effect near a target temperature; and it must be readily available. The most promising materials so far—including gadolinium—are rare earth metals found primarily in China. As a result, their availability for future applications in the United States is in question.
 
In other words, the ideal material has not been found. That’s where Eisenbach’s team and its application, WL-LSMS, comes in. WL-LSMS calculates the magnetic properties of promising materials, including their Curie temperatures, from basic laws of physics. In the Journal of Applied Physics articles, published in April 2011, the team reviewed its experience calculating the properties of three materials: iron, cementite, and an alloy of nickel, manganese and gallium. The results are very promising.
 
Eisenbach noted that these calculations are important for more than just magnetic refrigeration. For example, they can help researchers understand the properties of different types of steel, a pursuit whose payoff may be the creation of lighter, stronger and more reliable materials (for example, within a nuclear reactor containment vessel). In this case, he said, the magnetic properties of steel are part of a much larger exploration well beyond the capabilities of current supercomputers.
 
Berkeley Lab Computing Tools Speed Search for New Porous Materials
In an article published in the October 2011 issue of SIAM News, chemist Maciej Haranczyk and applied mathematicians Chris Rycroft and James Sethian of Lawrence Berkeley National Laboratory’s (Berkeley Lab) Computational Research Division describe the suite of tools they have created to speed up the evaluation of new porous materials. These synthetically created materials can play key roles in physical and chemical processes, including petroleum refinement, water softening, and separations. One class, known as zeolites, has a commercial impact of about $350 billion annually.
 
SIAM News is the monthly newsmagazine of the Society for Industrial and Applied Mathematics.
 
Researchers in ANL’s Mathematics and Computer Science Division Receive INCITE Time
Four researchers in the Mathematics and Computer Science Division at Argonne National Laboratory have been awarded computing time on Argonne’s Blue Gene/P as part of the U.S. Department of Energy (DOE) Innovative and Novel Computational Impact on Theory and Experiment (INCITE) program. Using the computer allotments, the researchers will conduct advanced simulation and analysis, devise novel algorithms, and develop scalable system software needed to fully utilize the power of leadership-class computing facilities. The projects were selected competitively based on their potential to advance scientific discovery. One of the projects is new, and three are renewals.
  • Mihai Anitescu, a computational mathematician, was awarded 10 million processor-hours on the Blue Gene/P for optimizing complex energy systems under uncertainty.
  • Paul Fischer, a senior computational scientist, was awarded 25 million processor-hours on the Blue Gene/P to continue his work on the simulation and analysis of fast neutron reactors.
  • Ewing (“Rusty”) Lusk, an Argonne distinguished fellow, was awarded 5 million processor-hours on the Blue Gene/P to continue improving the performance and productivity of key system software components.
  • Rob Jacob, a computational climate scientist, is continuing his work with colleagues from atmospheric studies and several other national laboratories and research institutions on cutting-edge climate science research. The project, awarded 30 million processor-hours on the Blue Gene/P and 56 million processor-hours on the Cray XT, involves global high-resolution simulations. Jacob’s research focuses on evaluations of the Community Atmosphere Model Version 5 to simulate extreme climate events.

PEOPLE:

Argonne’s Barry Smith and Lois Curfman McInnes Win E.O. Lawrence Award
Barry F. Smith and Lois Curfman McInnes

Argonne's Barry Smith and Lois Curfman McInnes, winners of the 2011 E.O. Lawrence Award.

Argonne National Laboratory researchers Barry Smith and Lois Curfman McInnes have been named winners of the U.S. Department of Energy’s Ernest Orlando Lawrence Award, which honors midcareer scientists and engineers for exceptional contributions in research and development. The award citation honors the breakthrough work of Smith and McInnes in developing PETSc, the Portable, Extensible Toolkit for Scientific computation. PETSc provides robust, scalable software for solving partial differential equations. Since such equations are ubiquitous in computational models in science and engineering, the PETSc library has had a major impact in a wide variety of critical application areas, including acoustics, arterial flow, air pollution, combustion, computational fluid dynamics, earthquake simulation, electromagnetics, fusion, ice dynamics, nanomaterials, and parallel reservoir simulation.
 
The Lawrence Awards are DOE’s highest honors and include a gold medal, a citation, and $20,000, which will be presented at a ceremony in Washington, D.C., early in 2012.
 
RHIC/ATLAS Computing Facility Team Receives Secretary’s Achievement Honor Award
Energy Secretary Steven Chu selected the staff of the RHIC/ATLAS Computing Facility (RACF) at Brookhaven National Laboratory — which manages vast amounts of data for two large-scale global physics experiments — as a recipient of the Secretary’s Achievement Honor Award. The award recognizes the RACF team’s “outstanding performance” in serving the experimental physics programs at the Relativistic Heavy Ion Collider (RHIC) — a particle accelerator located at Brookhaven Lab where scientists from around the world explore fundamental forces, the properties of matter, and the conditions of the early universe by colliding heavy ions such as gold — and the ATLAS experiment, located at the Large Hadron Collider at CERN, the European particle physics laboratory, which aims to discover why some particles have mass and the source of dark matter.
 
The Honor Awards represent the highest internal non-monetary recognition given to DOE employees and contractors for providing exceptional service to the Department and the American people. The Achievement Honor Award is given to groups or teams for their outstanding accomplishments and contributions. The RACF team is one of nine groups and several individuals recognized this year at a ceremony held October 27 at DOE headquarters in Washington, D.C.
 
RACF Team with Secretary Chu
Energy Secretary Steven Chu (center) with members of the RACF team (left to right: Kevin Casella, John Fetzko, Michael Ernst, Richard Hogue, Tomasz Wlodek, Costin Caramarcu, Ofer Rind, David Yu). Photo courtesy Department of Energy.
 
Argonne Summer Intern Wins First Place for Student Posters at Recent Conference
Drew Wicke, a student intern at Argonne National Laboratory this past summer, won first place for student posters at the Consortium for Computing Sciences in Colleges Eastern Conference (CCSCE) held in Arlington, Va., Oct. 14–15. Wicke worked with Argonne computer scientist Paul Hovland on developing a tool to improve the performance of the calculation of a derivative when using an operator overloading automatic differentiation library such as Sacado. Automatic differentiation (AD) is used in diverse applications, from artificial intelligence to weather modeling. One way to implement AD is operator overloading. This method, which alters the meaning of mathematical operators in order to compute the derivative, allows for maintainable code but sacrifices the speed of computation. To increase the speed, one can perform derivative computation only for active variables.
 
To this end, Wicke devised a tool that first creates a simplified anatomy of a program represented as a tree of connected nodes. This tree is converted to an intermediate form that an existing toolkit can use to identify active variables. The tool then changes the types of active variables identified to Sacado derivative types. The new tool can replace the manual approach, which is slow and overestimates the number of active variables. Moreover, it can be adapted for any operator overloading AD implementation. Thus, the scientific community can use this tool to produce more efficient code.
 
Berkeley Lab’s Taghrid Samak Mentors Women in Morocco through TechWomen Program
Taghrid Samak
Taghrid Samak, a postdoctoral fellow in Berkeley Lab’s Computational Research Division and a native of Alexandria, Egypt, has been volunteering as a cultural mentor in the TechWomen program, a U.S. Department of State initiative to mentor women who are technical leaders from the Middle East and North Africa. On October 14–22, Samak and other TechWomen mentors traveled to Morocco to share technical knowledge, establish professional partnerships, reconnect with mentees, and participate in networking events, seminars, and tailored meetings. The visit included Marrakech, Casablanca, and Rabat.
 
Samak did a technical presentation on large scale scientific workflow management at Universite Mohammedia Hassan II. She also participated in panels on technical careers at ENSA (National School of Applied Sciences) and Khalil Gibran School. The delegation also met with Fatima Zahra Mansouri, the first female mayor of the town of Marrakech, and other political leaders.
 
The TechWomen delegation visited many women's cooperatives and associations for helping women, including Wafa Association of Artisan Women, Association MOUASSAT, and Association Solidarité Féminine. They also met high school girls from rural areas and talked to them about science and math leading to technical careers.
 
LBNL’s David Bailey on Experimental Mathematics: Computing Power Leads to Insights
In an article called “Exploratory Experimentation and Computation,” appearing in the November 2011 issue of the Notices of the American Mathematical Society, Berkeley Lab’s David H. Bailey and his colleague Jonathan M. Borwein describe how modern computer technology has vastly expanded our ability to discover new mathematical results. In addition to discussing state-of-the-art uses of computers in mathematics, the article also touches on the need to refashion mathematics education to give students the tools of experimental mathematics.
 
Berkeley Lab’s Michael Wehner Gives Invited Talk at Climate Change Beijing
Michael Wehner,astaff scientist in Berkeley Lab’s Computational Research Division, gave an invited talk called “Projections of Extreme Weather in a Changing Climate: Balancing Confidence and Uncertainty” at Climate Change BeijingExternal link, an international climate change conference hosted by the Chinese Academy of Sciences, the National Science Foundation of China and CSIRO, Australia. As part of this conference, the world’s leading climate scientists, industry leaders, government representatives, students and members of the general public met October 18-20 in Beijing, China to discuss the most important environmental issues of our time. The Chinese Academy of Sciences has established the conference to promote information sharing and action, with eminent speakers catalyzing scientific advances and collaboration between national and international participants.
 
Wehner’s current research concerns the behavior of extreme weather events in a changing climate, especially heat waves, intense precipitation, drought and tropical cyclones. He has been selected as a lead author for the upcoming Fifth Assessment Report of the Intergovernmental Panel on Climate Change and was also a member of the lead author team for the 2009 White House report “Global Climate Change Impacts in the United StatesExternal link.”
 
OLCF’s Jack Wells Speaks at Summit on Government–Industry Collaborations
On Oct. 5 and 6, the Oak Ridge Leadership Computing Facility’s (OLCF’s) Jack Wells participated in the General Electric (GE) Technology Summit to explore partnering opportunities between the company and America’s national laboratories. Hosted by GE Global Research with Battelle Memorial Institute and held at the GE Global Research Center in Niskayuna, N.Y., the summit featured lab tours; a keynote speech by Karina Edmonds, technology transfer coordinator for the DOE; and panel discussions about research central to GE’s business success, such as solar and wind technologies, the smart grid, advanced materials, and high-performance computing (HPC). The event was a good case study of how companies can gain access to government resources and in doing so enhance their global competitiveness.
 
Wells spoke on a panel about collaborative opportunities in HPC at his ORNL facility. He highlighted three pathways by which industrial users can gain access to OLCF supercomputers. Approximately 60 percent of time available on Jaguar, America’s fastest supercomputer, is allocated through INCITE, a program co-managed for DOE by the Argonne and Oak Ridge Leadership Computing Facilities, whereas 30 percent is allocated through the Office of Advanced Scientific Computing Research Leadership Computing Challenge (ALCC) and 10 percent through Director’s Discretion. “If there’s a national need, certainly there are mechanisms for utilizing this machine,” Wells said.
 
Overseeing the summit were GE Global Research’s Gary Leonard, technology director, and Mark Little, senior vice president and director. Attendees included GE researchers and executives as well as representatives of Battelle and the national labs, such as User Services and Outreach Manger David Martin of the Argonne Leadership Computing Facility and Corporate Fellow Amit Goyal of ORNL’s Materials Science and Technology Division. DOE representatives from both Office of Science and National Nuclear Security Administration labs spoke about advanced research conducted by their organizations.
 

FACILITIES/INFRASTRUCTURE:

ESnet, Internet2 Complete 100G Network Deployment
Two of the nation’s leading research networks—the DOE’s Energy Sciences Network (ESnet) and Internet2—announced in October that they have completed the world’s first transcontinental deployment of 100 Gigabit per second (Gbps) using coherent technology. Built on Ciena’s 6500 Packet-Optical Platform, the new 8.8 Terabit per second network is equipped with 100 Gbps optical backbone connections. Those connections are now operational between New York, Washington, D.C., Cleveland, Chicago, Kansas City, Denver, Salt Lake City, and Sunnyvale, spanning a distance nearly 4000 miles.
 
Both ESnet and Internet2 are upgrading their respective networks to new 100 Gbps technology on a nationwide scale to ensure they keep pace with the exponential growth in scientific research traffic being driven by the nation’s research labs and universities. ESnet—managed by Lawrence Berkeley National Laboratory (Berkeley Lab)—is a national network that connects thousands of DOE Office of Science researchers at more than 40 different U.S. laboratories and supercomputing facilities and links them to research partners around the world.
 
Pioneering Supercomputer QCDOC Retires, Regenerates in ‘Next-Generation’ QCDCQ
On May 26, 2005, a new supercomputer, a pioneering giant of its time, was unveiled at Brookhaven National Laboratory at a dedication ceremony attended by physicists from around the world. That supercomputer was called QCDOC, for quantum chromodynamics (QCD) on a chip, capable of handling the complex calculations of QCD, the theory that describes the nature and interactions of the basic building blocks of the universe. Now, after a career of state-of-the-art physics calculations, QCDOC has been retired — and will soon be replaced by a new, next-generation machine.
 
The RIKEN Brookhaven Research Center, Columbia University, and BNL, together with the University of Edinburgh, a collaborator in the United Kingdom KQCD group, are developing an even more powerful supercomputer, QCDCQ (QCD with Chiral Quarks). This machine will have 75 to 150 Tflops of sustained speed — key to RBRC’s continuing international leadership in lattice QCD. The researchers will also work with colleagues at the T.J. Watson Laboratory of IBM — the same colleagues who transformed the technology of QCDSP and QCDOC into IBM’s Blue Gene product. So QCDCQ will benefit from advantages of IBM’s next-generation supercomputer, which will be available in prototype form at RBRC and Edinburgh between one and two years before larger installation of commercial versions are available.
 
QCDOC
In front of the disassembled parts of the now retired supercomputer QCDOC are: (front, from left, holding the motherboard) Norman Christ, Columbia University (CU); Robert Mawhinney, CU; and Taku Izubuchi, RIKEN BNL Research Center (RBRC); along with the BNL Physics Department High Energy Theory group (HET): (from left) Heng-Tong Ding, BNL Physics Lattice Gauge Theory group (LGT); Hiroshi Ohno, LGT; Frithjof Karsch, LGT; Taichi Kawanai, RBRC and HET; Nicholas Samios, RBRC; Masakiyo Kitazawa, Osaka University; Michael Creutz, HET/LGT; Swagato Mukherjee, LGT; Christoph Lehner, RBRC; Amarjit Soni, HET; Chulwoo Jung; HET; Tomomi Ishikawa, RHIC and RBRC; Qi Liu, CU; Eigo Shintani, RBRC.
 
Two ESnet Projects Are Honored with Internet2 IDEA Awards
Two of ESnet’s projects, OSCARS and MAVEN, have received IDEA (Internet2 Driving Exemplary Applications) awards in Internet2’s 2011 annual competition for innovative network applications that have had the most positive impact and potential for adoption within the research and education community. Internet2 recognized OSCARS (On-Demand Secure Circuits and Advance Reservation System), developed by the ESnet team led by Chin Guok, including Evangelos Chaniotakis, Andrew Lake, Eric Pouyoul and Mary Thompson. Contributing partners also included Internet2, USC ISI and DANTE.
 
ESnet’s MAVEN (Monitoring and Visualization of Energy consumed by Networks) proof of concept application was also recognized with an IDEA award in the student category. MAVEN was prototyped by Baris Aksanli during his summer internship at ESnet. Baris is a Ph.D student at the University of California, San Diego conducting research at the System Energy Efficiency Lab with his thesis advisor, Dr. Tajana Rosing. Baris worked closely with his summer advisor, Inder Monga, and Jon Dugan to implement MAVEN as part of ESnet’s new Green Networking Initiative.
 
ESnet, or the Energy Sciences Network, is managed by Lawrence Berkeley National Laboratory for the DOE Office of Science and provides a high-bandwidth networking linking thousands of researchers at more than 40 DOE sites.
 

OUTREACH & EDUCATION:

Conference-Goers Examine Energy Challenges via Petascale Computing
More than 100 participants from government, industry, and academia attended the 2011 Computational Sciences and Engineering conference to discuss strategies for optimizing high-performance computing resources used in advanced modeling and simulation of grand challenges in energy. The conference, an annual event conceived in 2003 and hosted by ORNL’s Computing and Computational Sciences Directorate, took place Sept. 13–16 in Gatlinburg, Tenn. Presentations on the conference theme, “Virtualizing Energy,” covered energy topics including photovoltaics, small modular nuclear reactors, clean coal and gas technology, wind power, batteries, energy-efficient buildings, infrastructure, transportation, and the national power grid.
 
“The conference series provides an exceptional venue for presenting and discussing high-end computational science as well as the computer systems that support it,” said Buddy Bland, Director of Oak Ridge Leadership Computing Facility (OLCF). At the OLCF, changes are taking place to upgrade the Jaguar supercomputer and transform it into Titan, a Cray XK6 system expected to perform up to 20 petaflops (quadrillion calculations per second) by 2013.
 
The 2012 event will be held September 5–7, at the Park Vista. For more information on the conference, and a listing of presentations, please see the following link:
 
Berkeley Lab Staff Share Expertise at VisWeek Conferences
VisWeek 2011, held October 23–28 in Providence, RI, is the premier forum for visualization advances for academia, government, and industry, bringing together researchers and practitioners with a shared interest in tools, techniques, technology and theory. The week is organized around three separate conferences: IEEE Visualization, IEEE Information Visualization, and IEEE Visual Analytics Science and Technology.
 
David Camp of Berkeley Lab’s Computational Research Division (CRD) gave two talks that were co-authored with Hank Childs along with researchers from other institutions: “Streamline Integration Using MPI-Hybrid Parallelism on a Large Multicore Architecture,” and “Evaluating the Benefits of an Extended Memory Hierarchy for Parallel Streamline Algorithms.” Gunther Weber chaired a session on “Statistics, Geometry and Signal Processing.” And Kesheng John Wu presented a paper on “Parallel In Situ Indexing for Data-Intensive Computing,” co-authored with Jinoh Kim and Arie Shoshani of CRD and collaborators from other institutions.
 
Getting Started at the ALCF
The Getting Started Workshop, held October 4–5 at the Argonne Leadership Computing Facility (ALCF), provided 23 ALCF users, potential users, and postdocs with key information on services and resources, as well as the techniques and knowledge needed to use the systems at the ALCF.
 
Staff presented the following topics and provided assisted hands-on exercises where applicable:
  • Blue Gene/P architecture
  • ALCF infrastructure
  • Software environment
  • Debugging
  • Visualization systems and services
  • RepastHPC, a high-performance computing implementation of the Repast (Java) toolkit for agent-based modeling
  • Globus Online
Contact: David Martin (dem@alcf.anl.gov) or Chel Heinzel (chel@alcf.anl.gov)
 
NERSC Staff Contribute to HPSS User Forum
The HPSS User Forum (HUF 2011) was held October 18-21 at Indiana University in Bloomington. HUF 2011 is the annual gathering for the HPSS community, bringing together new and existing HPSS users from around the globe to discuss best practices, new implementations, and future directions and releases. Mike Welcome of NERSC gave a presentation on "MPS-Advice, Changes and Future Direction," and Nick Balthaser gave the NERSC Site Report.
 

 

 

 

 

 

 

Last modified: 3/18/2013 10:12:33 AM