219 Matching Results

Search Results

Advanced search parameters have been applied.

in creator/contributor: "United States. Department of Energy. Office of Advanced Scientific Computing Research."

open access

Integrated Performance Monitoring of a Cosmology Application onLeading HEC Platforms

The Cosmic Microwave Background (CMB) is an exquisitely sensitive probe of the fundamental parameters of cosmology. Extracting this information is computationally intensive, requiring massively parallel computing and sophisticated numerical algorithms. In this work we present MAD bench, a lightweight version of the MADCAP CMB power spectrum estimation code that retains the operational complexity and integrated system requirements. In addition, to quantify communication behavior across a variety… more

Date: April 1, 2005

Creator: Borrill, Julian; Carter, Jonathan; Oliker, Leonid; Skinner,David & Biswas, Rupak

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

System utilization benchmark on the Cray T3E and IBM SP

Obtaining maximum utilization of parallel systems continues to be an active area of research and development. This article outlines a new benchmark, called the Effective System Performance (ESP) test, designed to provide a utilization metric that is transferable between systems and illuminate the effects of various scheduling parameters. Results with discussion are presented for the Cray T3E and IBM SP systems together with insights obtained from simulation.

Date: February 28, 2000

Creator: Wong, Adrian; Oliker, Leonid; Kramer, William; Kaltz, Teresa & Bailey, David

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Low Mach Number Modeling of Type Ia Supernovae. II. EnergyEvolution

The convective period leading up to a Type Ia supernova (SNIa) explosion is characterized by very low Mach number flows, requiringhydrodynamical methods well-suited to long-time integration. We continuethe development of the low Mach number equation set for stellar scaleflows by incorporating the effects of heat release due to externalsources. Low Mach number hydrodynamics equations with a time-dependentbackground state are derived, and a numerical method based on theapproximate projection form… more

Date: March 28, 2006

Creator: Almgren, Ann S.; Bell, John B.; Rendleman, Charles A. & Zingale,Mike

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Performance Modeling and Optimization of a High Energy Colliding Beam Simulation Code

An accurate modeling of the beam-beam interaction is essential to maximizing the luminosity in existing and future colliders. BeamBeam3D was the first parallel code that can be used to study this interaction fully self-consistently on high-performance computing platforms. Various all-to-all personalized communication (AAPC) algorithms dominate its communication patterns, for which we developed a sequence of performance models using a series of micro-benchmarks. We find that for SMP based system… more

Date: June 1, 2006

Creator: Shan, Hongzhang; Strohmaier, Erich; Qiang, Ji; Bailey, David H. & Yelick, Kathy

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Efficient Analysis of Live and Historical Streaming Data and itsApplication to Cybersecurity

Applications that query data streams in order to identifytrends, patterns, or anomalies can often benefit from comparing the livestream data with archived historical stream data. However, searching thishistorical data in real time has been considered so far to beprohibitively expensive. One of the main bottlenecks is the update costsof the indices over the archived data. In this paper, we address thisproblem by using our highly-efficient bitmap indexing technology (calledFastBit) and demonstrat… more

Date: April 6, 2007

Creator: Reiss, Frederick; Stockinger, Kurt; Wu, Kesheng; Shoshani, Arie & Hellerstein, Joseph M.

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Characterizations of a CERN NbTi Reference Wire at LBNL

We report on the measurement of two NbTi reference samples,obtained from CERN through BNL, wire number02R00056A01UX.265. The purposeof these characterizations is two-fold: 1) To establish aninter-laboratory comparisonof short sample tests and analysis betweenLBNL, BNL and Fermilab within the LARP collaboration. Due to differencesin reaction and mounting procedures and their resulting straindifferences, Nb3Sn is not suited for this purpose. 2) To determine theaccuracy of LBNL's system with regar… more

Date: February 1, 2007

Creator: Godeke, A.; Dietderich, D.R.; Higley, H.C. & Liggins, N.L.

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

HDF5-FastQuery: An API for Simplifying Access to Data Storage,Retrieval, Indexing and Querying

This work focuses on research and development activities that bridge a gap between fundamental data management technology index, query, storage and retrieval and use of such technology in computational and computer science algorithms and applications. The work has resulted in a streamlined applications programming interface (API) that simplifies data storage and retrieval using the HDF5 data I/O library, and eases use of the FastBit compressed bitmap indexing software for data indexing/querying… more

Date: June 15, 2006

Creator: Bethel, E. Wes; Gosink, Luke; Shalf, John; Stockinger, Kurt & Wu,Kesheng

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

Detecting Distributed Scans Using High-Performance Query-DrivenVisualization

Modern forensic analytics applications, like network trafficanalysis, perform high-performance hypothesis testing, knowledgediscovery and data mining on very large datasets. One essential strategyto reduce the time required for these operations is to select only themost relevant data records for a given computation. In this paper, wepresent a set of parallel algorithms that demonstrate how an efficientselection mechanism -- bitmap indexing -- significantly speeds up acommon analysist ask, namel… more

Date: September 1, 2006

Creator: Stockinger, Kurt; Bethel, E. Wes; Campbell, Scott; Dart, Eli & Wu,Kesheng

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

TOP500 Sublist for November 2001

18th Edition of TOP500 List of World's Fastest Supercomputers Released MANNHEIM, GERMANY; KNOXVILLE, TENN.; BERKELEY, CALIF. In what has become a much-anticipated event in the world of high-performance computing, the 18th edition of the TOP500 list of the world's fastest supercomputers was released today (November 9, 2001). The latest edition of the twice-yearly ranking finds IBM as the leader in the field, with 32 percent in terms of installed systems and 37 percent in terms of total performan… more

Date: November 9, 2001

Creator: Strohmaier, Erich; Meuer, Hans W.; Dongarra, Jack J. & Simon,Horst D.

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

17th Edition of TOP500 List of World's Fastest SupercomputersReseased

17th Edition of TOP500 List of World's Fastest Supercomputers Released MANNHEIM, GERMANY; KNOXVILLE, TENN.; BERKELEY, CALIF. In what has become a much-anticipated event in the world of high-performance computing, the 17th edition of the TOP500 list of the world's fastest supercomputers was released today (June 21). The latest edition of the twice-yearly ranking finds IBM as the leader in the field, with 40 percent in terms of installed systems and 43 percent in terms of total performance of all… more

Date: June 21, 2001

Creator: Strohmaier, Erich; Meuer, Hans W.; Dongarra, Jack J. & Simon,Horst D.

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

Grid Collector: Using an event catalog to speed up user analysisin distributed environment

Nuclear and High Energy Physics experiments such as STAR at BNL are generating millions of files with Peta Bytes of data each year. In most cases, analysis programs have to read all events in a file in order to find the interesting ones. Since the interesting events may be a small fraction of events in the file, a significant portion of the computer time is wasted on reading the unwanted events. To address this issue, we developed a software system called Grid Collector. The core of Grid Collec… more

Date: November 1, 2004

Creator: Wu, Kesheng; Shoshani, Arie; Zhang, Wei-Ming; Lauret, Jerome & Perevoztchikov, Victor

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

The Performance Effect of Multi-core on ScientificApplications

The historical trend of increasing single CPU performancehas given way to roadmap of increasing core count. The challenge ofeffectively utilizing these multi-core chips is just starting to beexplored by vendors and application developers alike. In this study, wepresent some performance measurements of several complete scientificapplications on single and dual core Cray XT3 and XT4 systems with a viewto characterizing the effects of switching to multi-core chips. Weconsider effects within a node… more

Date: May 14, 2007

Creator: Carter, Jonathan; He, Yun; Shalf, John; Shan, Hongzhang; Strohmaier, Erich & Wasserman, Harvey

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Variable Interactions in Query-Driven Visualization

One fundamental element of scientific inquiry is discoveringrelationships, particularly the interactions between different variablesin observed or simulated phenomena. Building upon our prior work in thefield of Query-Driven Visualization, where visual data analysisprocessing is focused on subsets of large data deemed to be"scientifically interesting," this new work focuses on a novel knowledgediscovery capability suitable for use with petascale class datasets. Itenables visual presentation of … more

Date: October 25, 2007

Creator: Bethel, E. Wes; Gosink, Luke J.; Anderson, John C. & Joy, Kenneth I.

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

Visualization and Analysis of 3D Gene Expression Data

Recent methods for extracting precise measurements ofspatial gene expression patterns from three-dimensional (3D) image dataopens the way for new analysis of the complex gene regulatory networkscontrolling animal development. To support analysis of this novel andhighly complex data we developed PointCloudXplore (PCX), an integratedvisualization framework that supports dedicated multi-modal, physical andinformation visualization views along with algorithms to aid in analyzingthe relationships be… more

Date: October 25, 2007

Creator: Bethel, E. Wes; Rubel, Oliver; Weber, Gunther H.; Hamann, Bernd & Hagen, Hans

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

Numerical simulation of low Mach number reacting flows

Using examples from active research areas in combustion andastrophysics, we demonstrate a computationally efficient numericalapproach for simulating multiscale low Mach number reacting flows. Themethod enables simulations that incorporate an unprecedented range oftemporal and spatial scales, while at the same time, allows an extremelyhigh degree of reaction fidelity. Sample applications demonstrate theefficiency of the approach with respect to a traditional time-explicitintegration method, and … more

Date: June 20, 2007

Creator: Bell, John B.; Aspden, Andrew J.; Day, Marcus S. & Lijewski,Michael J.

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Derivative-free optimization methods for surface structuredetermination of nanosystems

Many properties of nanostructures depend on the atomicconfiguration at the surface. One common technique used for determiningthis surface structure is based on the low energy electron diffraction(LEED) method, which uses a high-fidelity physics model to compareexperimental results with spectra computed via a computer simulation.While this approach is highly effective, the computational cost of thesimulations can be prohibitive for large systems. In this work, wepropose the use of a direct searc… more

Date: October 18, 2007

Creator: Meza, Juan C.; Garcia-Lekue, Arantzazu; Abramson, Mark A. & Dennis, John E.

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Sub Angstrom imaging of dislocation core structures: How well areexperiments comparable with theory?

During the past 50 years Transmission Electron Microscopy (TEM) has evolved from an imaging tool to a quantitative method that approaches the ultimate goal of understanding the atomic structure of materials atom by atom in three dimensions both experimentally and theoretically. Today's TEM abilities are tested in the special case of a Ga terminated 30 degree partial dislocation in GaAs:Be where it is shown that a combination of high-resolution phase contrast imaging, Scanning TEM, and local Ele… more

Date: December 16, 2005

Creator: Kisielowski, C.; Freitag, B.; Xu, X.; Beckman, S.P. & Chrzan, D.C.

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Parallel Scaling Characteristics of Selected NERSC User ProjectCodes

This report documents parallel scaling characteristics of NERSC user project codes between Fiscal Year 2003 and the first half of Fiscal Year 2004 (Oct 2002-March 2004). The codes analyzed cover 60% of all the CPU hours delivered during that time frame on seaborg, a 6080 CPU IBM SP and the largest parallel computer at NERSC. The scale in terms of concurrency and problem size of the workload is analyzed. Drawing on batch queue logs, performance data and feedback from researchers we detail the mo… more

Date: March 5, 2005

Creator: Skinner, David; Verdier, Francesca; Anand, Harsh; Carter,Jonathan; Durst, Mark & Gerber, Richard

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

Performance and scaling of locally-structured grid methods forpartial differential equations

In this paper, we discuss some of the issues in obtaining high performance for block-structured adaptive mesh refinement software for partial differential equations. We show examples in which AMR scales to thousands of processors. We also discuss a number of metrics for performance and scalability that can provide a basis for understanding the advantages and disadvantages of this approach.

Date: July 19, 2007

Creator: Colella, Phillip; Bell, John; Keen, Noel; Ligocki, Terry; Lijewski, Michael & Van Straalen, Brian

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Fine-grained authorization for job and resource management usingakenti and the globus toolkit(R)

As the Grid paradigm is adopted as a standard way of sharing remote resources across organizational domains, the need for fine-grained access control to these resources increases. This paper presents an authorization solution for job submission and control, developed as part of the National Fusion Collaboratory, that uses the Globus Toolkit 2 and the Akenti authorization service in order to perform fine-grained authorization of job and resource management requests in a Gridenvironment. At job s… more

Date: July 1, 2003

Creator: Thompson, Mary R.; Essiari, Abdelilah; Keahey, Kate; Welch, Von; Lang, S. & Liu, Bo

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

High Performance Visualization using Query-Driven Visualizationand Analytics

Query-driven visualization and analytics is a unique approach for high-performance visualization that offers new capabilities for knowledge discovery and hypothesis testing. The new capabilities akin to finding needles in haystacks are the result of combining technologies from the fields of scientific visualization and scientific data management. This approach is crucial for rapid data analysis and visualization in the petascale regime. This article describes how query-driven visualization is a… more

Date: June 15, 2006

Creator: Bethel, E. Wes; Campbell, Scott; Dart, Eli; Shalf, John; Stockinger, Kurt & Wu, Kesheng

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

Efficient Electron Injection Into Plasma Waves Using Higher-Orderlaser Modes

Using higher-order transverse laser modes as drivers forplasma wave excitation, and, in particular, using a ring laser beam withmaximum intensity off-axis, results in reversal of the focusinganddefocusing phase regions in a laser wakefield accelerator. Thisresults in improved performance of self-trapping and laser injectionschemes. Specifically, the trapping threshold required foropticalinjection is decreased and the maximum energy gain of the trappedelectrons is increased. This scheme could al… more

Date: August 2, 2006

Creator: Michel, P.; Esarey, E.; Schroeder, C. B.; Shadwick, B. A. & Leemans, W. P.

Item Type: Article

Partner: UNT Libraries Government Documents Department

open access

Analysis, tuning and comparison of two general sparse solvers for distributed memory computers

We describe the work performed in the context of a Franco-Berkeley funded project between NERSC-LBNL located in Berkeley (USA) and CERFACS-ENSEEIHT located in Toulouse (France). We discuss both the tuning and performance analysis of two distributed memory sparse solvers (superlu from Berkeley and mumps from Toulouse) on the 512 processor Cray T3E from NERSC (Lawrence Berkeley National Laboratory). This project gave us the opportunity to improve the algorithms and add new features to the codes. … more

Date: June 30, 2000

Creator: Amestoy, P. R.; Duff, I. S.; L'Excellent, J. Y. & Li, X. S.

Item Type: Report

Partner: UNT Libraries Government Documents Department

open access

The use of bulk states to accelerate the band edge statecalculation of a semiconductor quantum dot

We present a new technique to accelerate the convergence of the folded spectrum method in empirical pseudopotential band edge state calculations for colloidal quantum dots. We use bulk band states of the materials constituent of the quantum dot to construct initial vectors and a preconditioner. We apply these to accelerate the convergence of the folded spectrum method for the interior states at the top of the valence and the bottom of the conduction band. For large CdSe quantum dots, the number… more

Date: May 10, 2006

Creator: Vomel, Christof; Tomov, Stanimire Z.; Wang, Lin-Wang; Marques,Osni A. & Dongarra, Jack J.

Item Type: Article

Partner: UNT Libraries Government Documents Department