High-performance computing — an overview

Science.gov (United States)

Marksteiner, Peter

1996-08-01

An overview of high-performance computing (HPC) is given. Different types of computer architectures used in HPC are discussed: vector supercomputers, high-performance RISC processors, various parallel computers like symmetric multiprocessors, workstation clusters, massively parallel processors. Software tools and programming techniques used in HPC are reviewed: vectorizing compilers, optimization and vector tuning, optimization for RISC processors; parallel programming techniques like shared-memory parallelism, message passing and data parallelism; and numerical libraries.

High Performance Computing in Science and Engineering '16 : Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2016

CERN Document Server

Kröner, Dietmar; Resch, Michael

2016-01-01

This book presents the state-of-the-art in supercomputer simulation. It includes the latest findings from leading researchers using systems from the High Performance Computing Center Stuttgart (HLRS) in 2016. The reports cover all fields of computational science and engineering ranging from CFD to computational physics and from chemistry to computer science with a special emphasis on industrially relevant applications. Presenting findings of one of Europe’s leading systems, this volume covers a wide variety of applications that deliver a high level of sustained performance. The book covers the main methods in high-performance computing. Its outstanding results in achieving the best performance for production codes are of particular interest for both scientists and engineers. The book comes with a wealth of color illustrations and tables of results.

High-performance computing in seismology

Energy Technology Data Exchange (ETDEWEB)

NONE

1996-09-01

The scientific, technical, and economic importance of the issues discussed here presents a clear agenda for future research in computational seismology. In this way these problems will drive advances in high-performance computing in the field of seismology. There is a broad community that will benefit from this work, including the petroleum industry, research geophysicists, engineers concerned with seismic hazard mitigation, and governments charged with enforcing a comprehensive test ban treaty. These advances may also lead to new applications for seismological research. The recent application of high-resolution seismic imaging of the shallow subsurface for the environmental remediation industry is an example of this activity. This report makes the following recommendations: (1) focused efforts to develop validated documented software for seismological computations should be supported, with special emphasis on scalable algorithms for parallel processors; (2) the education of seismologists in high-performance computing technologies and methodologies should be improved; (3) collaborations between seismologists and computational scientists and engineers should be increased; (4) the infrastructure for archiving, disseminating, and processing large volumes of seismological data should be improved.

High performance computing in Windows Azure cloud

OpenAIRE

Ambruš, Dejan

2013-01-01

High performance, security, availability, scalability, flexibility and lower costs of maintenance have essentially contributed to the growing popularity of cloud computing in all spheres of life, especially in business. In fact cloud computing offers even more than this. With usage of virtual computing clusters a runtime environment for high performance computing can be efficiently implemented also in a cloud. There are many advantages but also some disadvantages of cloud computing, some ...

High Performance Computing in Science and Engineering '02 : Transactions of the High Performance Computing Center

CERN Document Server

Jäger, Willi

2003-01-01

This book presents the state-of-the-art in modeling and simulation on supercomputers. Leading German research groups present their results achieved on high-end systems of the High Performance Computing Center Stuttgart (HLRS) for the year 2002. Reports cover all fields of supercomputing simulation ranging from computational fluid dynamics to computer science. Special emphasis is given to industrially relevant applications. Moreover, by presenting results for both vector sytems and micro-processor based systems the book allows to compare performance levels and usability of a variety of supercomputer architectures. It therefore becomes an indispensable guidebook to assess the impact of the Japanese Earth Simulator project on supercomputing in the years to come.

Detecting Distributed Scans Using High-Performance Query-DrivenVisualization

Energy Technology Data Exchange (ETDEWEB)

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

2006-09-01

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, namely, computing conditional histogram on verylarge datasets. We present a thorough study of the performancecharacteristics of the parallel conditional histogram algorithms. Asacase study, we compute conditional histograms for detecting distributedscans hidden in a dataset consisting of approximately 2.5 billion networkconnection records. We show that these conditional histograms can becomputed on interactive timescale (i.e., in seconds). We also show how toprogressively modify the selection criteria to narrow the analysis andfind the sources of the distributed scans.

A Heterogeneous High-Performance System for Computational and Computer Science

Science.gov (United States)

2016-11-15

expand the research infrastructure at the institution but also to enhance the high -performance computing training provided to both undergraduate and... cloud computing, supercomputing, and the availability of cheap memory and storage led to enormous amounts of data to be sifted through in forensic... High -Performance Computing (HPC) tools that can be integrated with existing curricula and support our research to modernize and dramatically advance

Quantum Accelerators for High-performance Computing Systems

Energy Technology Data Exchange (ETDEWEB)

Humble, Travis S. [ORNL; Britt, Keith A. [ORNL; Mohiyaddin, Fahd A. [ORNL

2017-11-01

We define some of the programming and system-level challenges facing the application of quantum processing to high-performance computing. Alongside barriers to physical integration, prominent differences in the execution of quantum and conventional programs challenges the intersection of these computational models. Following a brief overview of the state of the art, we discuss recent advances in programming and execution models for hybrid quantum-classical computing. We discuss a novel quantum-accelerator framework that uses specialized kernels to offload select workloads while integrating with existing computing infrastructure. We elaborate on the role of the host operating system to manage these unique accelerator resources, the prospects for deploying quantum modules, and the requirements placed on the language hierarchy connecting these different system components. We draw on recent advances in the modeling and simulation of quantum computing systems with the development of architectures for hybrid high-performance computing systems and the realization of software stacks for controlling quantum devices. Finally, we present simulation results that describe the expected system-level behavior of high-performance computing systems composed from compute nodes with quantum processing units. We describe performance for these hybrid systems in terms of time-to-solution, accuracy, and energy consumption, and we use simple application examples to estimate the performance advantage of quantum acceleration.

How to build a high-performance compute cluster for the Grid

CERN Document Server

Reinefeld, A

2001-01-01

The success of large-scale multi-national projects like the forthcoming analysis of the LHC particle collision data at CERN relies to a great extent on the ability to efficiently utilize computing and data-storage resources at geographically distributed sites. Currently, much effort is spent on the design of Grid management software (Datagrid, Globus, etc.), while the effective integration of computing nodes has been largely neglected up to now. This is the focus of our work. We present a framework for a high- performance cluster that can be used as a reliable computing node in the Grid. We outline the cluster architecture, the management of distributed data and the seamless integration of the cluster into the Grid environment. (11 refs).

High-Performance Compute Infrastructure in Astronomy: 2020 Is Only Months Away

Science.gov (United States)

Berriman, B.; Deelman, E.; Juve, G.; Rynge, M.; Vöckler, J. S.

2012-09-01

, and so the costs of running applications vary widely according to how they use resources. The cloud is well suited to processing CPU-bound (and memory bound) workflows such as the periodogram code, given the relatively low cost of processing in comparison with I/O operations. I/O-bound applications such as Montage perform best on high-performance clusters with fast networks and parallel file-systems. Science-driven Cyberinfrastructure: Montage has been widely used as a driver application to develop workflow management services, such as task scheduling in distributed environments, designing fault tolerance techniques for job schedulers, and developing workflow orchestration techniques. Running Parallel Applications Across Distributed Cloud Environments: Data processing will eventually take place in parallel distributed across cyber infrastructure environments having different architectures. We have used the Pegasus Work Management System (WMS) to successfully run applications across three very different environments: TeraGrid, OSG (Open Science Grid), and FutureGrid. Provisioning resources across different grids and clouds (also referred to as Sky Computing), involves establishing a distributed environment, where issues of, e.g, remote job submission, data management, and security need to be addressed. This environment also requires building virtual machine images that can run in different environments. Usually, each cloud provides basic images that can be customized with additional software and services. In most of our work, we provisioned compute resources using a custom application, called Wrangler. Pegasus WMS abstracts the architectures of the compute environments away from the end-user, and can be considered a first-generation tool suitable for scientists to run their applications on disparate environments.

Contemporary high performance computing from petascale toward exascale

CERN Document Server

Vetter, Jeffrey S

2013-01-01

Contemporary High Performance Computing: From Petascale toward Exascale focuses on the ecosystems surrounding the world's leading centers for high performance computing (HPC). It covers many of the important factors involved in each ecosystem: computer architectures, software, applications, facilities, and sponsors. The first part of the book examines significant trends in HPC systems, including computer architectures, applications, performance, and software. It discusses the growth from terascale to petascale computing and the influence of the TOP500 and Green500 lists. The second part of the

High performance computing in linear control

International Nuclear Information System (INIS)

Datta, B.N.

1993-01-01

Remarkable progress has been made in both theory and applications of all important areas of control. The theory is rich and very sophisticated. Some beautiful applications of control theory are presently being made in aerospace, biomedical engineering, industrial engineering, robotics, economics, power systems, etc. Unfortunately, the same assessment of progress does not hold in general for computations in control theory. Control Theory is lagging behind other areas of science and engineering in this respect. Nowadays there is a revolution going on in the world of high performance scientific computing. Many powerful computers with vector and parallel processing have been built and have been available in recent years. These supercomputers offer very high speed in computations. Highly efficient software, based on powerful algorithms, has been developed to use on these advanced computers, and has also contributed to increased performance. While workers in many areas of science and engineering have taken great advantage of these hardware and software developments, control scientists and engineers, unfortunately, have not been able to take much advantage of these developments

A Distributed Computational Infrastructure for Science and Education

Directory of Open Access Journals (Sweden)

Rustam K. Bazarov

2014-06-01

Full Text Available Researchers have lately been paying increasingly more attention to parallel and distributed algorithms for solving high-dimensionality problems. In this regard, the issue of acquiring or renting computational resources becomes a topical one for employees of scientific and educational institutions. This article examines technology and methods for organizing a distributed computational infrastructure. The author addresses the experience of creating a high-performance system powered by existing clusterization and grid computing technology. The approach examined in the article helps minimize financial costs, aggregate territorially distributed computational resources and ensures a more rational use of available computer equipment, eliminating its downtimes.

High Performance Computing in Science and Engineering '14

CERN Document Server

Kröner, Dietmar; Resch, Michael

2015-01-01

This book presents the state-of-the-art in supercomputer simulation. It includes the latest findings from leading researchers using systems from the High Performance Computing Center Stuttgart (HLRS). The reports cover all fields of computational science and engineering ranging from CFD to computational physics and from chemistry to computer science with a special emphasis on industrially relevant applications. Presenting findings of one of Europe’s leading systems, this volume covers a wide variety of applications that deliver a high level of sustained performance. The book covers the main methods in high-performance computing. Its outstanding results in achieving the best performance for production codes are of particular interest for both scientists and   engineers. The book comes with a wealth of color illustrations and tables of results.  

High-performance computing for airborne applications

International Nuclear Information System (INIS)

Quinn, Heather M.; Manuzatto, Andrea; Fairbanks, Tom; Dallmann, Nicholas; Desgeorges, Rose

2010-01-01

Recently, there has been attempts to move common satellite tasks to unmanned aerial vehicles (UAVs). UAVs are significantly cheaper to buy than satellites and easier to deploy on an as-needed basis. The more benign radiation environment also allows for an aggressive adoption of state-of-the-art commercial computational devices, which increases the amount of data that can be collected. There are a number of commercial computing devices currently available that are well-suited to high-performance computing. These devices range from specialized computational devices, such as field-programmable gate arrays (FPGAs) and digital signal processors (DSPs), to traditional computing platforms, such as microprocessors. Even though the radiation environment is relatively benign, these devices could be susceptible to single-event effects. In this paper, we will present radiation data for high-performance computing devices in a accelerated neutron environment. These devices include a multi-core digital signal processor, two field-programmable gate arrays, and a microprocessor. From these results, we found that all of these devices are suitable for many airplane environments without reliability problems.

PGHPF – An Optimizing High Performance Fortran Compiler for Distributed Memory Machines

Directory of Open Access Journals (Sweden)

Zeki Bozkus

1997-01-01

Full Text Available High Performance Fortran (HPF is the first widely supported, efficient, and portable parallel programming language for shared and distributed memory systems. HPF is realized through a set of directive-based extensions to Fortran 90. It enables application developers and Fortran end-users to write compact, portable, and efficient software that will compile and execute on workstations, shared memory servers, clusters, traditional supercomputers, or massively parallel processors. This article describes a production-quality HPF compiler for a set of parallel machines. Compilation techniques such as data and computation distribution, communication generation, run-time support, and optimization issues are elaborated as the basis for an HPF compiler implementation on distributed memory machines. The performance of this compiler on benchmark programs demonstrates that high efficiency can be achieved executing HPF code on parallel architectures.

Department of Energy research in utilization of high-performance computers

International Nuclear Information System (INIS)

Buzbee, B.L.; Worlton, W.J.; Michael, G.; Rodrigue, G.

1980-08-01

Department of Energy (DOE) and other Government research laboratories depend on high-performance computer systems to accomplish their programmatic goals. As the most powerful computer systems become available, they are acquired by these laboratories so that advances can be made in their disciplines. These advances are often the result of added sophistication to numerical models, the execution of which is made possible by high-performance computer systems. However, high-performance computer systems have become increasingly complex, and consequently it has become increasingly difficult to realize their potential performance. The result is a need for research on issues related to the utilization of these systems. This report gives a brief description of high-performance computers, and then addresses the use of and future needs for high-performance computers within DOE, the growing complexity of applications within DOE, and areas of high-performance computer systems warranting research. 1 figure

Optical interconnection networks for high-performance computing systems

International Nuclear Information System (INIS)

Biberman, Aleksandr; Bergman, Keren

2012-01-01

Enabled by silicon photonic technology, optical interconnection networks have the potential to be a key disruptive technology in computing and communication industries. The enduring pursuit of performance gains in computing, combined with stringent power constraints, has fostered the ever-growing computational parallelism associated with chip multiprocessors, memory systems, high-performance computing systems and data centers. Sustaining these parallelism growths introduces unique challenges for on- and off-chip communications, shifting the focus toward novel and fundamentally different communication approaches. Chip-scale photonic interconnection networks, enabled by high-performance silicon photonic devices, offer unprecedented bandwidth scalability with reduced power consumption. We demonstrate that the silicon photonic platforms have already produced all the high-performance photonic devices required to realize these types of networks. Through extensive empirical characterization in much of our work, we demonstrate such feasibility of waveguides, modulators, switches and photodetectors. We also demonstrate systems that simultaneously combine many functionalities to achieve more complex building blocks. We propose novel silicon photonic devices, subsystems, network topologies and architectures to enable unprecedented performance of these photonic interconnection networks. Furthermore, the advantages of photonic interconnection networks extend far beyond the chip, offering advanced communication environments for memory systems, high-performance computing systems, and data centers. (review article)

Distributed simulation of large computer systems

International Nuclear Information System (INIS)

Marzolla, M.

2001-01-01

Sequential simulation of large complex physical systems is often regarded as a computationally expensive task. In order to speed-up complex discrete-event simulations, the paradigm of Parallel and Distributed Discrete Event Simulation (PDES) has been introduced since the late 70s. The authors analyze the applicability of PDES to the modeling and analysis of large computer system; such systems are increasingly common in the area of High Energy and Nuclear Physics, because many modern experiments make use of large 'compute farms'. Some feasibility tests have been performed on a prototype distributed simulator

Debugging a high performance computing program

Science.gov (United States)

Gooding, Thomas M.

2013-08-20

Methods, apparatus, and computer program products are disclosed for debugging a high performance computing program by gathering lists of addresses of calling instructions for a plurality of threads of execution of the program, assigning the threads to groups in dependence upon the addresses, and displaying the groups to identify defective threads.

STEMsalabim: A high-performance computing cluster friendly code for scanning transmission electron microscopy image simulations of thin specimens

International Nuclear Information System (INIS)

Oelerich, Jan Oliver; Duschek, Lennart; Belz, Jürgen; Beyer, Andreas; Baranovskii, Sergei D.; Volz, Kerstin

2017-01-01

Highlights: • We present STEMsalabim, a modern implementation of the multislice algorithm for simulation of STEM images. • Our package is highly parallelizable on high-performance computing clusters, combining shared and distributed memory architectures. • With STEMsalabim, computationally and memory expensive STEM image simulations can be carried out within reasonable time. - Abstract: We present a new multislice code for the computer simulation of scanning transmission electron microscope (STEM) images based on the frozen lattice approximation. Unlike existing software packages, the code is optimized to perform well on highly parallelized computing clusters, combining distributed and shared memory architectures. This enables efficient calculation of large lateral scanning areas of the specimen within the frozen lattice approximation and fine-grained sweeps of parameter space.

STEMsalabim: A high-performance computing cluster friendly code for scanning transmission electron microscopy image simulations of thin specimens

Energy Technology Data Exchange (ETDEWEB)

Oelerich, Jan Oliver, E-mail: jan.oliver.oelerich@physik.uni-marburg.de; Duschek, Lennart; Belz, Jürgen; Beyer, Andreas; Baranovskii, Sergei D.; Volz, Kerstin

2017-06-15

Highlights: • We present STEMsalabim, a modern implementation of the multislice algorithm for simulation of STEM images. • Our package is highly parallelizable on high-performance computing clusters, combining shared and distributed memory architectures. • With STEMsalabim, computationally and memory expensive STEM image simulations can be carried out within reasonable time. - Abstract: We present a new multislice code for the computer simulation of scanning transmission electron microscope (STEM) images based on the frozen lattice approximation. Unlike existing software packages, the code is optimized to perform well on highly parallelized computing clusters, combining distributed and shared memory architectures. This enables efficient calculation of large lateral scanning areas of the specimen within the frozen lattice approximation and fine-grained sweeps of parameter space.

High-performance scientific computing in the cloud

Science.gov (United States)

Jorissen, Kevin; Vila, Fernando; Rehr, John

2011-03-01

Cloud computing has the potential to open up high-performance computational science to a much broader class of researchers, owing to its ability to provide on-demand, virtualized computational resources. However, before such approaches can become commonplace, user-friendly tools must be developed that hide the unfamiliar cloud environment and streamline the management of cloud resources for many scientific applications. We have recently shown that high-performance cloud computing is feasible for parallelized x-ray spectroscopy calculations. We now present benchmark results for a wider selection of scientific applications focusing on electronic structure and spectroscopic simulation software in condensed matter physics. These applications are driven by an improved portable interface that can manage virtual clusters and run various applications in the cloud. We also describe a next generation of cluster tools, aimed at improved performance and a more robust cluster deployment. Supported by NSF grant OCI-1048052.

Coping with distributed computing

International Nuclear Information System (INIS)

Cormell, L.

1992-09-01

The rapid increase in the availability of high performance, cost-effective RISC/UNIX workstations has been both a blessing and a curse. The blessing of having extremely powerful computing engines available on the desk top is well-known to many users. The user has tremendous freedom, flexibility, and control of his environment. That freedom can, however, become the curse of distributed computing. The user must become a system manager to some extent, he must worry about backups, maintenance, upgrades, etc. Traditionally these activities have been the responsibility of a central computing group. The central computing group, however, may find that it can no longer provide all of the traditional services. With the plethora of workstations now found on so many desktops throughout the entire campus or lab, the central computing group may be swamped by support requests. This talk will address several of these computer support and management issues by providing some examples of the approaches taken at various HEP institutions. In addition, a brief review of commercial directions or products for distributed computing and management will be given

Research Activity in Computational Physics utilizing High Performance Computing: Co-authorship Network Analysis

Science.gov (United States)

Ahn, Sul-Ah; Jung, Youngim

2016-10-01

The research activities of the computational physicists utilizing high performance computing are analyzed by bibliometirc approaches. This study aims at providing the computational physicists utilizing high-performance computing and policy planners with useful bibliometric results for an assessment of research activities. In order to achieve this purpose, we carried out a co-authorship network analysis of journal articles to assess the research activities of researchers for high-performance computational physics as a case study. For this study, we used journal articles of the Scopus database from Elsevier covering the time period of 2004-2013. We extracted the author rank in the physics field utilizing high-performance computing by the number of papers published during ten years from 2004. Finally, we drew the co-authorship network for 45 top-authors and their coauthors, and described some features of the co-authorship network in relation to the author rank. Suggestions for further studies are discussed.

Multicore Challenges and Benefits for High Performance Scientific Computing

Directory of Open Access Journals (Sweden)

Ida M.B. Nielsen

2008-01-01

Full Text Available Until recently, performance gains in processors were achieved largely by improvements in clock speeds and instruction level parallelism. Thus, applications could obtain performance increases with relatively minor changes by upgrading to the latest generation of computing hardware. Currently, however, processor performance improvements are realized by using multicore technology and hardware support for multiple threads within each core, and taking full advantage of this technology to improve the performance of applications requires exposure of extreme levels of software parallelism. We will here discuss the architecture of parallel computers constructed from many multicore chips as well as techniques for managing the complexity of programming such computers, including the hybrid message-passing/multi-threading programming model. We will illustrate these ideas with a hybrid distributed memory matrix multiply and a quantum chemistry algorithm for energy computation using Møller–Plesset perturbation theory.

Implementing an Affordable High-Performance Computing for Teaching-Oriented Computer Science Curriculum

Science.gov (United States)

Abuzaghleh, Omar; Goldschmidt, Kathleen; Elleithy, Yasser; Lee, Jeongkyu

2013-01-01

With the advances in computing power, high-performance computing (HPC) platforms have had an impact on not only scientific research in advanced organizations but also computer science curriculum in the educational community. For example, multicore programming and parallel systems are highly desired courses in the computer science major. However,…

High-Throughput Computing on High-Performance Platforms: A Case Study

Energy Technology Data Exchange (ETDEWEB)

Oleynik, D [University of Texas at Arlington; Panitkin, S [Brookhaven National Laboratory (BNL); Matteo, Turilli [Rutgers University; Angius, Alessio [Rutgers University; Oral, H Sarp [ORNL; De, K [University of Texas at Arlington; Klimentov, A [Brookhaven National Laboratory (BNL); Wells, Jack C. [ORNL; Jha, S [Rutgers University

2017-10-01

The computing systems used by LHC experiments has historically consisted of the federation of hundreds to thousands of distributed resources, ranging from small to mid-size resource. In spite of the impressive scale of the existing distributed computing solutions, the federation of small to mid-size resources will be insufficient to meet projected future demands. This paper is a case study of how the ATLAS experiment has embraced Titan -- a DOE leadership facility in conjunction with traditional distributed high- throughput computing to reach sustained production scales of approximately 52M core-hours a years. The three main contributions of this paper are: (i) a critical evaluation of design and operational considerations to support the sustained, scalable and production usage of Titan; (ii) a preliminary characterization of a next generation executor for PanDA to support new workloads and advanced execution modes; and (iii) early lessons for how current and future experimental and observational systems can be integrated with production supercomputers and other platforms in a general and extensible manner.

High performance parallel computers for science

International Nuclear Information System (INIS)

Nash, T.; Areti, H.; Atac, R.; Biel, J.; Cook, A.; Deppe, J.; Edel, M.; Fischler, M.; Gaines, I.; Hance, R.

1989-01-01

This paper reports that Fermilab's Advanced Computer Program (ACP) has been developing cost effective, yet practical, parallel computers for high energy physics since 1984. The ACP's latest developments are proceeding in two directions. A Second Generation ACP Multiprocessor System for experiments will include $3500 RISC processors each with performance over 15 VAX MIPS. To support such high performance, the new system allows parallel I/O, parallel interprocess communication, and parallel host processes. The ACP Multi-Array Processor, has been developed for theoretical physics. Each $4000 node is a FORTRAN or C programmable pipelined 20 Mflops (peak), 10 MByte single board computer. These are plugged into a 16 port crossbar switch crate which handles both inter and intra crate communication. The crates are connected in a hypercube. Site oriented applications like lattice gauge theory are supported by system software called CANOPY, which makes the hardware virtually transparent to users. A 256 node, 5 GFlop, system is under construction

A Weibull distribution accrual failure detector for cloud computing.

Science.gov (United States)

Liu, Jiaxi; Wu, Zhibo; Wu, Jin; Dong, Jian; Zhao, Yao; Wen, Dongxin

2017-01-01

Failure detectors are used to build high availability distributed systems as the fundamental component. To meet the requirement of a complicated large-scale distributed system, accrual failure detectors that can adapt to multiple applications have been studied extensively. However, several implementations of accrual failure detectors do not adapt well to the cloud service environment. To solve this problem, a new accrual failure detector based on Weibull Distribution, called the Weibull Distribution Failure Detector, has been proposed specifically for cloud computing. It can adapt to the dynamic and unexpected network conditions in cloud computing. The performance of the Weibull Distribution Failure Detector is evaluated and compared based on public classical experiment data and cloud computing experiment data. The results show that the Weibull Distribution Failure Detector has better performance in terms of speed and accuracy in unstable scenarios, especially in cloud computing.

High Performance Computing in Science and Engineering '99 : Transactions of the High Performance Computing Center

CERN Document Server

Jäger, Willi

2000-01-01

The book contains reports about the most significant projects from science and engineering of the Federal High Performance Computing Center Stuttgart (HLRS). They were carefully selected in a peer-review process and are showcases of an innovative combination of state-of-the-art modeling, novel algorithms and the use of leading-edge parallel computer technology. The projects of HLRS are using supercomputer systems operated jointly by university and industry and therefore a special emphasis has been put on the industrial relevance of results and methods.

Embedded High Performance Scalable Computing Systems

National Research Council Canada - National Science Library

Ngo, David

2003-01-01

The Embedded High Performance Scalable Computing Systems (EHPSCS) program is a cooperative agreement between Sanders, A Lockheed Martin Company and DARPA that ran for three years, from Apr 1995 - Apr 1998...

GPU-based high-performance computing for radiation therapy

International Nuclear Information System (INIS)

Jia, Xun; Jiang, Steve B; Ziegenhein, Peter

2014-01-01

Recent developments in radiotherapy therapy demand high computation powers to solve challenging problems in a timely fashion in a clinical environment. The graphics processing unit (GPU), as an emerging high-performance computing platform, has been introduced to radiotherapy. It is particularly attractive due to its high computational power, small size, and low cost for facility deployment and maintenance. Over the past few years, GPU-based high-performance computing in radiotherapy has experienced rapid developments. A tremendous amount of study has been conducted, in which large acceleration factors compared with the conventional CPU platform have been observed. In this paper, we will first give a brief introduction to the GPU hardware structure and programming model. We will then review the current applications of GPU in major imaging-related and therapy-related problems encountered in radiotherapy. A comparison of GPU with other platforms will also be presented. (topical review)

Distributed GPU Computing in GIScience

Science.gov (United States)

Jiang, Y.; Yang, C.; Huang, Q.; Li, J.; Sun, M.

2013-12-01

Geoscientists strived to discover potential principles and patterns hidden inside ever-growing Big Data for scientific discoveries. To better achieve this objective, more capable computing resources are required to process, analyze and visualize Big Data (Ferreira et al., 2003; Li et al., 2013). Current CPU-based computing techniques cannot promptly meet the computing challenges caused by increasing amount of datasets from different domains, such as social media, earth observation, environmental sensing (Li et al., 2013). Meanwhile CPU-based computing resources structured as cluster or supercomputer is costly. In the past several years with GPU-based technology matured in both the capability and performance, GPU-based computing has emerged as a new computing paradigm. Compare to traditional computing microprocessor, the modern GPU, as a compelling alternative microprocessor, has outstanding high parallel processing capability with cost-effectiveness and efficiency(Owens et al., 2008), although it is initially designed for graphical rendering in visualization pipe. This presentation reports a distributed GPU computing framework for integrating GPU-based computing within distributed environment. Within this framework, 1) for each single computer, computing resources of both GPU-based and CPU-based can be fully utilized to improve the performance of visualizing and processing Big Data; 2) within a network environment, a variety of computers can be used to build up a virtual super computer to support CPU-based and GPU-based computing in distributed computing environment; 3) GPUs, as a specific graphic targeted device, are used to greatly improve the rendering efficiency in distributed geo-visualization, especially for 3D/4D visualization. Key words: Geovisualization, GIScience, Spatiotemporal Studies Reference : 1. Ferreira de Oliveira, M. C., & Levkowitz, H. (2003). From visual data exploration to visual data mining: A survey. Visualization and Computer Graphics, IEEE

High Performance Computing in Science and Engineering '98 : Transactions of the High Performance Computing Center

CERN Document Server

Jäger, Willi

1999-01-01

The book contains reports about the most significant projects from science and industry that are using the supercomputers of the Federal High Performance Computing Center Stuttgart (HLRS). These projects are from different scientific disciplines, with a focus on engineering, physics and chemistry. They were carefully selected in a peer-review process and are showcases for an innovative combination of state-of-the-art physical modeling, novel algorithms and the use of leading-edge parallel computer technology. As HLRS is in close cooperation with industrial companies, special emphasis has been put on the industrial relevance of results and methods.

High-Performance Java Codes for Computational Fluid Dynamics

Science.gov (United States)

Riley, Christopher; Chatterjee, Siddhartha; Biswas, Rupak; Biegel, Bryan (Technical Monitor)

2001-01-01

The computational science community is reluctant to write large-scale computationally -intensive applications in Java due to concerns over Java's poor performance, despite the claimed software engineering advantages of its object-oriented features. Naive Java implementations of numerical algorithms can perform poorly compared to corresponding Fortran or C implementations. To achieve high performance, Java applications must be designed with good performance as a primary goal. This paper presents the object-oriented design and implementation of two real-world applications from the field of Computational Fluid Dynamics (CFD): a finite-volume fluid flow solver (LAURA, from NASA Langley Research Center), and an unstructured mesh adaptation algorithm (2D_TAG, from NASA Ames Research Center). This work builds on our previous experience with the design of high-performance numerical libraries in Java. We examine the performance of the applications using the currently available Java infrastructure and show that the Java version of the flow solver LAURA performs almost within a factor of 2 of the original procedural version. Our Java version of the mesh adaptation algorithm 2D_TAG performs within a factor of 1.5 of its original procedural version on certain platforms. Our results demonstrate that object-oriented software design principles are not necessarily inimical to high performance.

Use of high performance computing to examine the effectiveness of aquifer remediation

International Nuclear Information System (INIS)

Tompson, A.F.B.; Ashby, S.F.; Falgout, R.D.; Smith, S.G.; Fogwell, T.W.; Loosmore, G.A.

1994-06-01

Large-scale simulation of fluid flow and chemical migration is being used to study the effectiveness of pump-and-treat restoration of a contaminated, saturated aquifer. A three-element approach focusing on geostatistical representations of heterogeneous aquifers, high-performance computing strategies for simulating flow, migration, and reaction processes in large three-dimensional systems, and highly-resolved simulations of flow and chemical migration in porous formations will be discussed. Results from a preliminary application of this approach to examine pumping behavior at a real, heterogeneous field site will be presented. Future activities will emphasize parallel computations in larger, dynamic, and nonlinear (two-phase) flow problems as well as improved interpretive methods for defining detailed material property distributions

Distributed computing at the SSCL

International Nuclear Information System (INIS)

Cormell, L.; White, R.

1993-05-01

The rapid increase in the availability of high performance, cost- effective RISC/UNIX workstations has been both a blessing and a curse. The blessing of having extremely powerful computing engines available on the desk top is well-known to many users. The user has tremendous freedom, flexibility, and control of his environment. That freedom can, however, become the curse of distributed computing. The user must become a system manager to some extent, he must worry about backups, maintenance, upgrades, etc. Traditionally these activities have been the responsibility of a central computing group. The central computing group, however, may find that it can no linger provide all of the traditional services. With the plethora of workstations now found on so many desktops throughout the entire campus or lab, the central computing group may be swamped by support requests. This talk will address several of these computer support and management issues by discussing the approach taken at the Superconducting Super Collider Laboratory. In addition, a brief review of the future directions of commercial products for distributed computing and management will be given

Distributed computing at the SSCL

International Nuclear Information System (INIS)

Cormell, L.R.; White, R.C.

1994-01-01

The rapid increase in the availability of high performance, cost-effective RISC/UNIX workstations has been both a blessing and a curse. The blessing of having extremely powerful computing engines available on the desk top is well-known to many users. The user has tremendous freedom, flexibility, and control of his environment. That freedom can, however, become the curse of distributed computing. The user must become a system manager to some extent, he must worry about backups, maintenance, upgrades, etc. Traditionally these activities have been the responsibility of central computing group. The central computing group, however, may find that it can no longer provide all of the traditional services. With the plethora of workstations now found on so many desktops throughout the entire campus or lab, the central computing group may be swamped by support requests. This talk will address several of these computer support and management issues by discussing the approach taken at the Superconducting Super Collider Laboratory (SSCL). In addition, a brief review of the future directions of commercial products for distributed computing and management will be given

Quantum Accelerators for High-Performance Computing Systems

OpenAIRE

Britt, Keith A.; Mohiyaddin, Fahd A.; Humble, Travis S.

2017-01-01

We define some of the programming and system-level challenges facing the application of quantum processing to high-performance computing. Alongside barriers to physical integration, prominent differences in the execution of quantum and conventional programs challenges the intersection of these computational models. Following a brief overview of the state of the art, we discuss recent advances in programming and execution models for hybrid quantum-classical computing. We discuss a novel quantu...

High threshold distributed quantum computing with three-qubit nodes

International Nuclear Information System (INIS)

Li Ying; Benjamin, Simon C

2012-01-01

In the distributed quantum computing paradigm, well-controlled few-qubit ‘nodes’ are networked together by connections which are relatively noisy and failure prone. A practical scheme must offer high tolerance to errors while requiring only simple (i.e. few-qubit) nodes. Here we show that relatively modest, three-qubit nodes can support advanced purification techniques and so offer robust scalability: the infidelity in the entanglement channel may be permitted to approach 10% if the infidelity in local operations is of order 0.1%. Our tolerance of network noise is therefore an order of magnitude beyond prior schemes, and our architecture remains robust even in the presence of considerable decoherence rates (memory errors). We compare the performance with that of schemes involving nodes of lower and higher complexity. Ion traps, and NV-centres in diamond, are two highly relevant emerging technologies: they possess the requisite properties of good local control, rapid and reliable readout, and methods for entanglement-at-a-distance. (paper)

ATLAS Distributed Computing

CERN Document Server

Schovancova, J; The ATLAS collaboration

2011-01-01

The poster details the different aspects of the ATLAS Distributed Computing experience after the first year of LHC data taking. We describe the performance of the ATLAS distributed computing system and the lessons learned during the 2010 run, pointing out parts of the system which were in a good shape, and also spotting areas which required improvements. Improvements ranged from hardware upgrade on the ATLAS Tier-0 computing pools to improve data distribution rates, tuning of FTS channels between CERN and Tier-1s, and studying data access patterns for Grid analysis to improve the global processing rate. We show recent software development driven by operational needs with emphasis on data management and job execution in the ATLAS production system.

Fast Performance Computing Model for Smart Distributed Power Systems

Directory of Open Access Journals (Sweden)

Umair Younas

2017-06-01

Full Text Available Plug-in Electric Vehicles (PEVs are becoming the more prominent solution compared to fossil fuels cars technology due to its significant role in Greenhouse Gas (GHG reduction, flexible storage, and ancillary service provision as a Distributed Generation (DG resource in Vehicle to Grid (V2G regulation mode. However, large-scale penetration of PEVs and growing demand of energy intensive Data Centers (DCs brings undesirable higher load peaks in electricity demand hence, impose supply-demand imbalance and threaten the reliability of wholesale and retail power market. In order to overcome the aforementioned challenges, the proposed research considers smart Distributed Power System (DPS comprising conventional sources, renewable energy, V2G regulation, and flexible storage energy resources. Moreover, price and incentive based Demand Response (DR programs are implemented to sustain the balance between net demand and available generating resources in the DPS. In addition, we adapted a novel strategy to implement the computational intensive jobs of the proposed DPS model including incoming load profiles, V2G regulation, battery State of Charge (SOC indication, and fast computation in decision based automated DR algorithm using Fast Performance Computing resources of DCs. In response, DPS provide economical and stable power to DCs under strict power quality constraints. Finally, the improved results are verified using case study of ISO California integrated with hybrid generation.

High performance computing on vector systems

CERN Document Server

Roller, Sabine

2008-01-01

Presents the developments in high-performance computing and simulation on modern supercomputer architectures. This book covers trends in hardware and software development in general and specifically the vector-based systems and heterogeneous architectures. It presents innovative fields like coupled multi-physics or multi-scale simulations.

High Performance Computing Modernization Program Kerberos Throughput Test Report

Science.gov (United States)

2017-10-26

Naval Research Laboratory Washington, DC 20375-5320 NRL/MR/5524--17-9751 High Performance Computing Modernization Program Kerberos Throughput Test ...NUMBER 5d. PROJECT NUMBER 5e. TASK NUMBER 5f. WORK UNIT NUMBER 2. REPORT TYPE1. REPORT DATE (DD-MM-YYYY) 4. TITLE AND SUBTITLE 6. AUTHOR(S) 8. PERFORMING...PAGE 18. NUMBER OF PAGES 17. LIMITATION OF ABSTRACT High Performance Computing Modernization Program Kerberos Throughput Test Report Daniel G. Gdula* and

CUDA/GPU Technology : Parallel Programming For High Performance Scientific Computing

OpenAIRE

YUHENDRA; KUZE, Hiroaki; JOSAPHAT, Tetuko Sri Sumantyo

2009-01-01

[ABSTRACT]Graphics processing units (GP Us) originally designed for computer video cards have emerged as the most powerful chip in a high-performance workstation. In the high performance computation capabilities, graphic processing units (GPU) lead to much more powerful performance than conventional CPUs by means of parallel processing. In 2007, the birth of Compute Unified Device Architecture (CUDA) and CUDA-enabled GPUs by NVIDIA Corporation brought a revolution in the general purpose GPU a...

Software Systems for High-performance Quantum Computing

Energy Technology Data Exchange (ETDEWEB)

Humble, Travis S [ORNL; Britt, Keith A [ORNL

2016-01-01

Quantum computing promises new opportunities for solving hard computational problems, but harnessing this novelty requires breakthrough concepts in the design, operation, and application of computing systems. We define some of the challenges facing the development of quantum computing systems as well as software-based approaches that can be used to overcome these challenges. Following a brief overview of the state of the art, we present models for the quantum programming and execution models, the development of architectures for hybrid high-performance computing systems, and the realization of software stacks for quantum networking. This leads to a discussion of the role that conventional computing plays in the quantum paradigm and how some of the current challenges for exascale computing overlap with those facing quantum computing.

Distributed quantum computing with single photon sources

International Nuclear Information System (INIS)

Beige, A.; Kwek, L.C.

2005-01-01

Full text: Distributed quantum computing requires the ability to perform nonlocal gate operations between the distant nodes (stationary qubits) of a large network. To achieve this, it has been proposed to interconvert stationary qubits with flying qubits. In contrast to this, we show that distributed quantum computing only requires the ability to encode stationary qubits into flying qubits but not the conversion of flying qubits into stationary qubits. We describe a scheme for the realization of an eventually deterministic controlled phase gate by performing measurements on pairs of flying qubits. Our scheme could be implemented with a linear optics quantum computing setup including sources for the generation of single photons on demand, linear optics elements and photon detectors. In the presence of photon loss and finite detector efficiencies, the scheme could be used to build large cluster states for one way quantum computing with a high fidelity. (author)

Energy efficient distributed computing systems

CERN Document Server

Lee, Young-Choon

2012-01-01

The energy consumption issue in distributed computing systems raises various monetary, environmental and system performance concerns. Electricity consumption in the US doubled from 2000 to 2005.  From a financial and environmental standpoint, reducing the consumption of electricity is important, yet these reforms must not lead to performance degradation of the computing systems.  These contradicting constraints create a suite of complex problems that need to be resolved in order to lead to 'greener' distributed computing systems.  This book brings together a group of outsta

Micromagnetics on high-performance workstation and mobile computational platforms

Science.gov (United States)

Fu, S.; Chang, R.; Couture, S.; Menarini, M.; Escobar, M. A.; Kuteifan, M.; Lubarda, M.; Gabay, D.; Lomakin, V.

2015-05-01

The feasibility of using high-performance desktop and embedded mobile computational platforms is presented, including multi-core Intel central processing unit, Nvidia desktop graphics processing units, and Nvidia Jetson TK1 Platform. FastMag finite element method-based micromagnetic simulator is used as a testbed, showing high efficiency on all the platforms. Optimization aspects of improving the performance of the mobile systems are discussed. The high performance, low cost, low power consumption, and rapid performance increase of the embedded mobile systems make them a promising candidate for micromagnetic simulations. Such architectures can be used as standalone systems or can be built as low-power computing clusters.

A Linear Algebra Framework for Static High Performance Fortran Code Distribution

Directory of Open Access Journals (Sweden)

Corinne Ancourt

1997-01-01

Full Text Available High Performance Fortran (HPF was developed to support data parallel programming for single-instruction multiple-data (SIMD and multiple-instruction multiple-data (MIMD machines with distributed memory. The programmer is provided a familiar uniform logical address space and specifies the data distribution by directives. The compiler then exploits these directives to allocate arrays in the local memories, to assign computations to elementary processors, and to migrate data between processors when required. We show here that linear algebra is a powerful framework to encode HPF directives and to synthesize distributed code with space-efficient array allocation, tight loop bounds, and vectorized communications for INDEPENDENT loops. The generated code includes traditional optimizations such as guard elimination, message vectorization and aggregation, and overlap analysis. The systematic use of an affine framework makes it possible to prove the compilation scheme correct.

Monitoring SLAC High Performance UNIX Computing Systems

International Nuclear Information System (INIS)

Lettsome, Annette K.

2005-01-01

Knowledge of the effectiveness and efficiency of computers is important when working with high performance systems. The monitoring of such systems is advantageous in order to foresee possible misfortunes or system failures. Ganglia is a software system designed for high performance computing systems to retrieve specific monitoring information. An alternative storage facility for Ganglia's collected data is needed since its default storage system, the round-robin database (RRD), struggles with data integrity. The creation of a script-driven MySQL database solves this dilemma. This paper describes the process took in the creation and implementation of the MySQL database for use by Ganglia. Comparisons between data storage by both databases are made using gnuplot and Ganglia's real-time graphical user interface

Simulation model of load balancing in distributed computing systems

Science.gov (United States)

Botygin, I. A.; Popov, V. N.; Frolov, S. G.

2017-02-01

The availability of high-performance computing, high speed data transfer over the network and widespread of software for the design and pre-production in mechanical engineering have led to the fact that at the present time the large industrial enterprises and small engineering companies implement complex computer systems for efficient solutions of production and management tasks. Such computer systems are generally built on the basis of distributed heterogeneous computer systems. The analytical problems solved by such systems are the key models of research, but the system-wide problems of efficient distribution (balancing) of the computational load and accommodation input, intermediate and output databases are no less important. The main tasks of this balancing system are load and condition monitoring of compute nodes, and the selection of a node for transition of the user’s request in accordance with a predetermined algorithm. The load balancing is one of the most used methods of increasing productivity of distributed computing systems through the optimal allocation of tasks between the computer system nodes. Therefore, the development of methods and algorithms for computing optimal scheduling in a distributed system, dynamically changing its infrastructure, is an important task.

High Performance Computing Software Applications for Space Situational Awareness

Science.gov (United States)

Giuliano, C.; Schumacher, P.; Matson, C.; Chun, F.; Duncan, B.; Borelli, K.; Desonia, R.; Gusciora, G.; Roe, K.

The High Performance Computing Software Applications Institute for Space Situational Awareness (HSAI-SSA) has completed its first full year of applications development. The emphasis of our work in this first year was in improving space surveillance sensor models and image enhancement software. These applications are the Space Surveillance Network Analysis Model (SSNAM), the Air Force Space Fence simulation (SimFence), and physically constrained iterative de-convolution (PCID) image enhancement software tool. Specifically, we have demonstrated order of magnitude speed-up in those codes running on the latest Cray XD-1 Linux supercomputer (Hoku) at the Maui High Performance Computing Center. The software applications improvements that HSAI-SSA has made, has had significant impact to the warfighter and has fundamentally changed the role of high performance computing in SSA.

High performance statistical computing with parallel R: applications to biology and climate modelling

International Nuclear Information System (INIS)

Samatova, Nagiza F; Branstetter, Marcia; Ganguly, Auroop R; Hettich, Robert; Khan, Shiraj; Kora, Guruprasad; Li, Jiangtian; Ma, Xiaosong; Pan, Chongle; Shoshani, Arie; Yoginath, Srikanth

2006-01-01

Ultrascale computing and high-throughput experimental technologies have enabled the production of scientific data about complex natural phenomena. With this opportunity, comes a new problem - the massive quantities of data so produced. Answers to fundamental questions about the nature of those phenomena remain largely hidden in the produced data. The goal of this work is to provide a scalable high performance statistical data analysis framework to help scientists perform interactive analyses of these raw data to extract knowledge. Towards this goal we have been developing an open source parallel statistical analysis package, called Parallel R, that lets scientists employ a wide range of statistical analysis routines on high performance shared and distributed memory architectures without having to deal with the intricacies of parallelizing these routines

DURIP: High Performance Computing in Biomathematics Applications

Science.gov (United States)

2017-05-10

Mathematics and Statistics (AMS) at the University of California, Santa Cruz (UCSC) to conduct research and research-related education in areas of...Computing in Biomathematics Applications Report Title The goal of this award was to enhance the capabilities of the Department of Applied Mathematics and...DURIP: High Performance Computing in Biomathematics Applications The goal of this award was to enhance the capabilities of the Department of Applied

AHPCRC - Army High Performance Computing Research Center

Science.gov (United States)

2010-01-01

computing. Of particular interest is the ability of a distrib- uted jamming network (DJN) to jam signals in all or part of a sensor or communications net...and reasoning, assistive technologies. FRIEDRICH (FRITZ) PRINZ Finmeccanica Professor of Engineering, Robert Bosch Chair, Department of Engineering...High Performance Computing Research Center www.ahpcrc.org BARBARA BRYAN AHPCRC Research and Outreach Manager, HPTi (650) 604-3732 bbryan@hpti.com Ms

Towards Portable Large-Scale Image Processing with High-Performance Computing.

Science.gov (United States)

Huo, Yuankai; Blaber, Justin; Damon, Stephen M; Boyd, Brian D; Bao, Shunxing; Parvathaneni, Prasanna; Noguera, Camilo Bermudez; Chaganti, Shikha; Nath, Vishwesh; Greer, Jasmine M; Lyu, Ilwoo; French, William R; Newton, Allen T; Rogers, Baxter P; Landman, Bennett A

2018-05-03

High-throughput, large-scale medical image computing demands tight integration of high-performance computing (HPC) infrastructure for data storage, job distribution, and image processing. The Vanderbilt University Institute for Imaging Science (VUIIS) Center for Computational Imaging (CCI) has constructed a large-scale image storage and processing infrastructure that is composed of (1) a large-scale image database using the eXtensible Neuroimaging Archive Toolkit (XNAT), (2) a content-aware job scheduling platform using the Distributed Automation for XNAT pipeline automation tool (DAX), and (3) a wide variety of encapsulated image processing pipelines called "spiders." The VUIIS CCI medical image data storage and processing infrastructure have housed and processed nearly half-million medical image volumes with Vanderbilt Advanced Computing Center for Research and Education (ACCRE), which is the HPC facility at the Vanderbilt University. The initial deployment was natively deployed (i.e., direct installations on a bare-metal server) within the ACCRE hardware and software environments, which lead to issues of portability and sustainability. First, it could be laborious to deploy the entire VUIIS CCI medical image data storage and processing infrastructure to another HPC center with varying hardware infrastructure, library availability, and software permission policies. Second, the spiders were not developed in an isolated manner, which has led to software dependency issues during system upgrades or remote software installation. To address such issues, herein, we describe recent innovations using containerization techniques with XNAT/DAX which are used to isolate the VUIIS CCI medical image data storage and processing infrastructure from the underlying hardware and software environments. The newly presented XNAT/DAX solution has the following new features: (1) multi-level portability from system level to the application level, (2) flexible and dynamic software

Enabling high performance computational science through combinatorial algorithms

International Nuclear Information System (INIS)

Boman, Erik G; Bozdag, Doruk; Catalyurek, Umit V; Devine, Karen D; Gebremedhin, Assefaw H; Hovland, Paul D; Pothen, Alex; Strout, Michelle Mills

2007-01-01

The Combinatorial Scientific Computing and Petascale Simulations (CSCAPES) Institute is developing algorithms and software for combinatorial problems that play an enabling role in scientific and engineering computations. Discrete algorithms will be increasingly critical for achieving high performance for irregular problems on petascale architectures. This paper describes recent contributions by researchers at the CSCAPES Institute in the areas of load balancing, parallel graph coloring, performance improvement, and parallel automatic differentiation

Enabling high performance computational science through combinatorial algorithms

Energy Technology Data Exchange (ETDEWEB)

Boman, Erik G [Discrete Algorithms and Math Department, Sandia National Laboratories (United States); Bozdag, Doruk [Biomedical Informatics, and Electrical and Computer Engineering, Ohio State University (United States); Catalyurek, Umit V [Biomedical Informatics, and Electrical and Computer Engineering, Ohio State University (United States); Devine, Karen D [Discrete Algorithms and Math Department, Sandia National Laboratories (United States); Gebremedhin, Assefaw H [Computer Science and Center for Computational Science, Old Dominion University (United States); Hovland, Paul D [Mathematics and Computer Science Division, Argonne National Laboratory (United States); Pothen, Alex [Computer Science and Center for Computational Science, Old Dominion University (United States); Strout, Michelle Mills [Computer Science, Colorado State University (United States)

2007-07-15

The Combinatorial Scientific Computing and Petascale Simulations (CSCAPES) Institute is developing algorithms and software for combinatorial problems that play an enabling role in scientific and engineering computations. Discrete algorithms will be increasingly critical for achieving high performance for irregular problems on petascale architectures. This paper describes recent contributions by researchers at the CSCAPES Institute in the areas of load balancing, parallel graph coloring, performance improvement, and parallel automatic differentiation.

GRID computing for experimental high energy physics

International Nuclear Information System (INIS)

Moloney, G.R.; Martin, L.; Seviour, E.; Taylor, G.N.; Moorhead, G.F.

2002-01-01

Full text: The Large Hadron Collider (LHC), to be completed at the CERN laboratory in 2006, will generate 11 petabytes of data per year. The processing of this large data stream requires a large, distributed computing infrastructure. A recent innovation in high performance distributed computing, the GRID, has been identified as an important tool in data analysis for the LHC. GRID computing has actual and potential application in many fields which require computationally intensive analysis of large, shared data sets. The Australian experimental High Energy Physics community has formed partnerships with the High Performance Computing community to establish a GRID node at the University of Melbourne. Through Australian membership of the ATLAS experiment at the LHC, Australian researchers have an opportunity to be involved in the European DataGRID project. This presentation will include an introduction to the GRID, and it's application to experimental High Energy Physics. We will present the results of our studies, including participation in the first LHC data challenge

Functionality and Performance Visualization of the Distributed High Quality Volume Renderer (HVR)

KAUST Repository

Shaheen, Sara

2012-07-01

Volume rendering systems are designed to provide means to enable scientists and a variety of experts to interactively explore volume data through 3D views of the volume. However, volume rendering techniques are computationally intensive tasks. Moreover, parallel distributed volume rendering systems and multi-threading architectures were suggested as natural solutions to provide an acceptable volume rendering performance for very large volume data sizes, such as Electron Microscopy data (EM). This in turn adds another level of complexity when developing and manipulating volume rendering systems. Given that distributed parallel volume rendering systems are among the most complex systems to develop, trace and debug, it is obvious that traditional debugging tools do not provide enough support. As a consequence, there is a great demand to provide tools that are able to facilitate the manipulation of such systems. This can be achieved by utilizing the power of compute graphics in designing visual representations that reflect how the system works and that visualize the current performance state of the system.The work presented is categorized within the field of software Visualization, where Visualization is used to serve visualizing and understanding various software. In this thesis, a number of visual representations that reflect a number of functionality and performance aspects of the distributed HVR, a high quality volume renderer system that uses various techniques to visualize large volume sizes interactively. This work is provided to visualize different stages of the parallel volume rendering pipeline of HVR. This is along with means of performance analysis through a number of flexible and dynamic visualizations that reflect the current state of the system and enables manipulation of them at runtime. Those visualization are aimed to facilitate debugging, understanding and analyzing the distributed HVR.

COMPUTERS: Teraflops for Europe; EEC Working Group on High Performance Computing

Energy Technology Data Exchange (ETDEWEB)

Anon.

1991-03-15

In little more than a decade, simulation on high performance computers has become an essential tool for theoretical physics, capable of solving a vast range of crucial problems inaccessible to conventional analytic mathematics. In many ways, computer simulation has become the calculus for interacting many-body systems, a key to the study of transitions from isolated to collective behaviour.

COMPUTERS: Teraflops for Europe; EEC Working Group on High Performance Computing

International Nuclear Information System (INIS)

Anon.

1991-01-01

In little more than a decade, simulation on high performance computers has become an essential tool for theoretical physics, capable of solving a vast range of crucial problems inaccessible to conventional analytic mathematics. In many ways, computer simulation has become the calculus for interacting many-body systems, a key to the study of transitions from isolated to collective behaviour

Enabling High-Performance Computing as a Service

KAUST Repository

AbdelBaky, Moustafa; Parashar, Manish; Kim, Hyunjoo; Jordan, Kirk E.; Sachdeva, Vipin; Sexton, James; Jamjoom, Hani; Shae, Zon-Yin; Pencheva, Gergina; Tavakoli, Reza; Wheeler, Mary F.

2012-01-01

With the right software infrastructure, clouds can provide scientists with as a service access to high-performance computing resources. An award-winning prototype framework transforms the Blue Gene/P system into an elastic cloud to run a

Distributed and cloud computing from parallel processing to the Internet of Things

CERN Document Server

Hwang, Kai; Fox, Geoffrey C

2012-01-01

Distributed and Cloud Computing, named a 2012 Outstanding Academic Title by the American Library Association's Choice publication, explains how to create high-performance, scalable, reliable systems, exposing the design principles, architecture, and innovative applications of parallel, distributed, and cloud computing systems. Starting with an overview of modern distributed models, the book provides comprehensive coverage of distributed and cloud computing, including: Facilitating management, debugging, migration, and disaster recovery through virtualization Clustered systems for resear

High Performance Data Transfer for Distributed Data Intensive Sciences

Energy Technology Data Exchange (ETDEWEB)

Fang, Chin [Zettar Inc., Mountain View, CA (United States); Cottrell, R ' Les' A. [SLAC National Accelerator Lab., Menlo Park, CA (United States); Hanushevsky, Andrew B. [SLAC National Accelerator Lab., Menlo Park, CA (United States); Kroeger, Wilko [SLAC National Accelerator Lab., Menlo Park, CA (United States); Yang, Wei [SLAC National Accelerator Lab., Menlo Park, CA (United States)

2017-03-06

We report on the development of ZX software providing high performance data transfer and encryption. The design scales in: computation power, network interfaces, and IOPS while carefully balancing the available resources. Two U.S. patent-pending algorithms help tackle data sets containing lots of small files and very large files, and provide insensitivity to network latency. It has a cluster-oriented architecture, using peer-to-peer technologies to ease deployment, operation, usage, and resource discovery. Its unique optimizations enable effective use of flash memory. Using a pair of existing data transfer nodes at SLAC and NERSC, we compared its performance to that of bbcp and GridFTP and determined that they were comparable. With a proof of concept created using two four-node clusters with multiple distributed multi-core CPUs, network interfaces and flash memory, we achieved 155Gbps memory-to-memory over a 2x100Gbps link aggregated channel and 70Gbps file-to-file with encryption over a 5000 mile 100Gbps link.

Event parallelism: Distributed memory parallel computing for high energy physics experiments

International Nuclear Information System (INIS)

Nash, T.

1989-05-01

This paper describes the present and expected future development of distributed memory parallel computers for high energy physics experiments. It covers the use of event parallel microprocessor farms, particularly at Fermilab, including both ACP multiprocessors and farms of MicroVAXES. These systems have proven very cost effective in the past. A case is made for moving to the more open environment of UNIX and RISC processors. The 2nd Generation ACP Multiprocessor System, which is based on powerful RISC systems, is described. Given the promise of still more extraordinary increases in processor performance, a new emphasis on point to point, rather than bussed, communication will be required. Developments in this direction are described. 6 figs

Event parallelism: Distributed memory parallel computing for high energy physics experiments

International Nuclear Information System (INIS)

Nash, T.

1989-01-01

This paper describes the present and expected future development of distributed memory parallel computers for high energy physics experiments. It covers the use of event parallel microprocessor farms, particularly at Fermilab, including both ACP multiprocessors and farms of MicroVAXES. These systems have proven very cost effective in the past. A case is made for moving to the more open environment of UNIX and RISC processors. The 2nd Generation ACP Multiprocessor System, which is based on powerful RISC systems, is described. Given the promise of still more extraordinary increases in processor performance, a new emphasis on point to point, rather than bussed, communication will be required. Developments in this direction are described. (orig.)

Event parallelism: Distributed memory parallel computing for high energy physics experiments

Science.gov (United States)

Nash, Thomas

1989-12-01

This paper describes the present and expected future development of distributed memory parallel computers for high energy physics experiments. It covers the use of event parallel microprocessor farms, particularly at Fermilab, including both ACP multiprocessors and farms of MicroVAXES. These systems have proven very cost effective in the past. A case is made for moving to the more open environment of UNIX and RISC processors. The 2nd Generation ACP Multiprocessor System, which is based on powerful RISC system, is described. Given the promise of still more extraordinary increases in processor performance, a new emphasis on point to point, rather than bussed, communication will be required. Developments in this direction are described.

ABINIT: Plane-Wave-Based Density-Functional Theory on High Performance Computers

Science.gov (United States)

Torrent, Marc

2014-03-01

For several years, a continuous effort has been produced to adapt electronic structure codes based on Density-Functional Theory to the future computing architectures. Among these codes, ABINIT is based on a plane-wave description of the wave functions which allows to treat systems of any kind. Porting such a code on petascale architectures pose difficulties related to the many-body nature of the DFT equations. To improve the performances of ABINIT - especially for what concerns standard LDA/GGA ground-state and response-function calculations - several strategies have been followed: A full multi-level parallelisation MPI scheme has been implemented, exploiting all possible levels and distributing both computation and memory. It allows to increase the number of distributed processes and could not be achieved without a strong restructuring of the code. The core algorithm used to solve the eigen problem (``Locally Optimal Blocked Congugate Gradient''), a Blocked-Davidson-like algorithm, is based on a distribution of processes combining plane-waves and bands. In addition to the distributed memory parallelization, a full hybrid scheme has been implemented, using standard shared-memory directives (openMP/openACC) or porting some comsuming code sections to Graphics Processing Units (GPU). As no simple performance model exists, the complexity of use has been increased; the code efficiency strongly depends on the distribution of processes among the numerous levels. ABINIT is able to predict the performances of several process distributions and automatically choose the most favourable one. On the other hand, a big effort has been carried out to analyse the performances of the code on petascale architectures, showing which sections of codes have to be improved; they all are related to Matrix Algebra (diagonalisation, orthogonalisation). The different strategies employed to improve the code scalability will be described. They are based on an exploration of new diagonalization

ATLAS Distributed Computing Automation

CERN Document Server

Schovancova, J; The ATLAS collaboration; Borrego, C; Campana, S; Di Girolamo, A; Elmsheuser, J; Hejbal, J; Kouba, T; Legger, F; Magradze, E; Medrano Llamas, R; Negri, G; Rinaldi, L; Sciacca, G; Serfon, C; Van Der Ster, D C

2012-01-01

The ATLAS Experiment benefits from computing resources distributed worldwide at more than 100 WLCG sites. The ATLAS Grid sites provide over 100k CPU job slots, over 100 PB of storage space on disk or tape. Monitoring of status of such a complex infrastructure is essential. The ATLAS Grid infrastructure is monitored 24/7 by two teams of shifters distributed world-wide, by the ATLAS Distributed Computing experts, and by site administrators. In this paper we summarize automation efforts performed within the ATLAS Distributed Computing team in order to reduce manpower costs and improve the reliability of the system. Different aspects of the automation process are described: from the ATLAS Grid site topology provided by the ATLAS Grid Information System, via automatic site testing by the HammerCloud, to automatic exclusion from production or analysis activities.

High-performance computing in accelerating structure design and analysis

International Nuclear Information System (INIS)

Li Zenghai; Folwell, Nathan; Ge Lixin; Guetz, Adam; Ivanov, Valentin; Kowalski, Marc; Lee, Lie-Quan; Ng, Cho-Kuen; Schussman, Greg; Stingelin, Lukas; Uplenchwar, Ravindra; Wolf, Michael; Xiao, Liling; Ko, Kwok

2006-01-01

Future high-energy accelerators such as the Next Linear Collider (NLC) will accelerate multi-bunch beams of high current and low emittance to obtain high luminosity, which put stringent requirements on the accelerating structures for efficiency and beam stability. While numerical modeling has been quite standard in accelerator R and D, designing the NLC accelerating structure required a new simulation capability because of the geometric complexity and level of accuracy involved. Under the US DOE Advanced Computing initiatives (first the Grand Challenge and now SciDAC), SLAC has developed a suite of electromagnetic codes based on unstructured grids and utilizing high-performance computing to provide an advanced tool for modeling structures at accuracies and scales previously not possible. This paper will discuss the code development and computational science research (e.g. domain decomposition, scalable eigensolvers, adaptive mesh refinement) that have enabled the large-scale simulations needed for meeting the computational challenges posed by the NLC as well as projects such as the PEP-II and RIA. Numerical results will be presented to show how high-performance computing has made a qualitative improvement in accelerator structure modeling for these accelerators, either at the component level (single cell optimization), or on the scale of an entire structure (beam heating and long-range wakefields)

Enabling High-Performance Computing as a Service

KAUST Repository

AbdelBaky, Moustafa

2012-10-01

With the right software infrastructure, clouds can provide scientists with as a service access to high-performance computing resources. An award-winning prototype framework transforms the Blue Gene/P system into an elastic cloud to run a representative HPC application. © 2012 IEEE.

Distributed-memory matrix computations

DEFF Research Database (Denmark)

Balle, Susanne Mølleskov

1995-01-01

The main goal of this project is to investigate, develop, and implement algorithms for numerical linear algebra on parallel computers in order to acquire expertise in methods for parallel computations. An important motivation for analyzaing and investigating the potential for parallelism in these......The main goal of this project is to investigate, develop, and implement algorithms for numerical linear algebra on parallel computers in order to acquire expertise in methods for parallel computations. An important motivation for analyzaing and investigating the potential for parallelism...... in these algorithms is that many scientific applications rely heavily on the performance of the involved dense linear algebra building blocks. Even though we consider the distributed-memory as well as the shared-memory programming paradigm, the major part of the thesis is dedicated to distributed-memory architectures....... We emphasize distributed-memory massively parallel computers - such as the Connection Machines model CM-200 and model CM-5/CM-5E - available to us at UNI-C and at Thinking Machines Corporation. The CM-200 was at the time this project started one of the few existing massively parallel computers...

High-Performance Monitoring Architecture for Large-Scale Distributed Systems Using Event Filtering

Science.gov (United States)

Maly, K.

1998-01-01

Monitoring is an essential process to observe and improve the reliability and the performance of large-scale distributed (LSD) systems. In an LSD environment, a large number of events is generated by the system components during its execution or interaction with external objects (e.g. users or processes). Monitoring such events is necessary for observing the run-time behavior of LSD systems and providing status information required for debugging, tuning and managing such applications. However, correlated events are generated concurrently and could be distributed in various locations in the applications environment which complicates the management decisions process and thereby makes monitoring LSD systems an intricate task. We propose a scalable high-performance monitoring architecture for LSD systems to detect and classify interesting local and global events and disseminate the monitoring information to the corresponding end- points management applications such as debugging and reactive control tools to improve the application performance and reliability. A large volume of events may be generated due to the extensive demands of the monitoring applications and the high interaction of LSD systems. The monitoring architecture employs a high-performance event filtering mechanism to efficiently process the large volume of event traffic generated by LSD systems and minimize the intrusiveness of the monitoring process by reducing the event traffic flow in the system and distributing the monitoring computation. Our architecture also supports dynamic and flexible reconfiguration of the monitoring mechanism via its Instrumentation and subscription components. As a case study, we show how our monitoring architecture can be utilized to improve the reliability and the performance of the Interactive Remote Instruction (IRI) system which is a large-scale distributed system for collaborative distance learning. The filtering mechanism represents an Intrinsic component integrated

Evaluation of high-performance computing software

Energy Technology Data Exchange (ETDEWEB)

Browne, S.; Dongarra, J. [Univ. of Tennessee, Knoxville, TN (United States); Rowan, T. [Oak Ridge National Lab., TN (United States)

1996-12-31

The absence of unbiased and up to date comparative evaluations of high-performance computing software complicates a user`s search for the appropriate software package. The National HPCC Software Exchange (NHSE) is attacking this problem using an approach that includes independent evaluations of software, incorporation of author and user feedback into the evaluations, and Web access to the evaluations. We are applying this approach to the Parallel Tools Library (PTLIB), a new software repository for parallel systems software and tools, and HPC-Netlib, a high performance branch of the Netlib mathematical software repository. Updating the evaluations with feed-back and making it available via the Web helps ensure accuracy and timeliness, and using independent reviewers produces unbiased comparative evaluations difficult to find elsewhere.

Analysis and modeling of social influence in high performance computing workloads

KAUST Repository

Zheng, Shuai

2011-01-01

Social influence among users (e.g., collaboration on a project) creates bursty behavior in the underlying high performance computing (HPC) workloads. Using representative HPC and cluster workload logs, this paper identifies, analyzes, and quantifies the level of social influence across HPC users. We show the existence of a social graph that is characterized by a pattern of dominant users and followers. This pattern also follows a power-law distribution, which is consistent with those observed in mainstream social networks. Given its potential impact on HPC workloads prediction and scheduling, we propose a fast-converging, computationally-efficient online learning algorithm for identifying social groups. Extensive evaluation shows that our online algorithm can (1) quickly identify the social relationships by using a small portion of incoming jobs and (2) can efficiently track group evolution over time. © 2011 Springer-Verlag.

Distributed MRI reconstruction using Gadgetron-based cloud computing.

Science.gov (United States)

Xue, Hui; Inati, Souheil; Sørensen, Thomas Sangild; Kellman, Peter; Hansen, Michael S

2015-03-01

To expand the open source Gadgetron reconstruction framework to support distributed computing and to demonstrate that a multinode version of the Gadgetron can be used to provide nonlinear reconstruction with clinically acceptable latency. The Gadgetron framework was extended with new software components that enable an arbitrary number of Gadgetron instances to collaborate on a reconstruction task. This cloud-enabled version of the Gadgetron was deployed on three different distributed computing platforms ranging from a heterogeneous collection of commodity computers to the commercial Amazon Elastic Compute Cloud. The Gadgetron cloud was used to provide nonlinear, compressed sensing reconstruction on a clinical scanner with low reconstruction latency (eg, cardiac and neuroimaging applications). The proposed setup was able to handle acquisition and 11 -SPIRiT reconstruction of nine high temporal resolution real-time, cardiac short axis cine acquisitions, covering the ventricles for functional evaluation, in under 1 min. A three-dimensional high-resolution brain acquisition with 1 mm(3) isotropic pixel size was acquired and reconstructed with nonlinear reconstruction in less than 5 min. A distributed computing enabled Gadgetron provides a scalable way to improve reconstruction performance using commodity cluster computing. Nonlinear, compressed sensing reconstruction can be deployed clinically with low image reconstruction latency. © 2014 Wiley Periodicals, Inc.

High Performance Data Distribution for Scientific Community

Science.gov (United States)

Tirado, Juan M.; Higuero, Daniel; Carretero, Jesus

2010-05-01

Institutions such as NASA, ESA or JAXA find solutions to distribute data from their missions to the scientific community, and their long term archives. This is a complex problem, as it includes a vast amount of data, several geographically distributed archives, heterogeneous architectures with heterogeneous networks, and users spread around the world. We propose a novel architecture (HIDDRA) that solves this problem aiming to reduce user intervention in data acquisition and processing. HIDDRA is a modular system that provides a highly efficient parallel multiprotocol download engine, using a publish/subscribe policy which helps the final user to obtain data of interest transparently. Our system can deal simultaneously with multiple protocols (HTTP,HTTPS, FTP, GridFTP among others) to obtain the maximum bandwidth, reducing the workload in data server and increasing flexibility. It can also provide high reliability and fault tolerance, as several sources of data can be used to perform one file download. HIDDRA architecture can be arranged into a data distribution network deployed on several sites that can cooperate to provide former features. HIDDRA has been addressed by the 2009 e-IRG Report on Data Management as a promising initiative for data interoperability. Our first prototype has been evaluated in collaboration with the ESAC centre in Villafranca del Castillo (Spain) that shows a high scalability and performance, opening a wide spectrum of opportunities. Some preliminary results have been published in the Journal of Astrophysics and Space Science [1]. [1] D. Higuero, J.M. Tirado, J. Carretero, F. Félix, and A. de La Fuente. HIDDRA: a highly independent data distribution and retrieval architecture for space observation missions. Astrophysics and Space Science, 321(3):169-175, 2009

P3T+: A Performance Estimator for Distributed and Parallel Programs

Directory of Open Access Journals (Sweden)

T. Fahringer

2000-01-01

Full Text Available Developing distributed and parallel programs on today's multiprocessor architectures is still a challenging task. Particular distressing is the lack of effective performance tools that support the programmer in evaluating changes in code, problem and machine sizes, and target architectures. In this paper we introduce P3T+ which is a performance estimator for mostly regular HPF (High Performance Fortran programs but partially covers also message passing programs (MPI. P3T+ is unique by modeling programs, compiler code transformations, and parallel and distributed architectures. It computes at compile-time a variety of performance parameters including work distribution, number of transfers, amount of data transferred, transfer times, computation times, and number of cache misses. Several novel technologies are employed to compute these parameters: loop iteration spaces, array access patterns, and data distributions are modeled by employing highly effective symbolic analysis. Communication is estimated by simulating the behavior of a communication library used by the underlying compiler. Computation times are predicted through pre-measured kernels on every target architecture of interest. We carefully model most critical architecture specific factors such as cache lines sizes, number of cache lines available, startup times, message transfer time per byte, etc. P3T+ has been implemented and is closely integrated with the Vienna High Performance Compiler (VFC to support programmers develop parallel and distributed applications. Experimental results for realistic kernel codes taken from real-world applications are presented to demonstrate both accuracy and usefulness of P3T+.

A Framework for Debugging Geoscience Projects in a High Performance Computing Environment

Science.gov (United States)

Baxter, C.; Matott, L.

2012-12-01

High performance computing (HPC) infrastructure has become ubiquitous in today's world with the emergence of commercial cloud computing and academic supercomputing centers. Teams of geoscientists, hydrologists and engineers can take advantage of this infrastructure to undertake large research projects - for example, linking one or more site-specific environmental models with soft computing algorithms, such as heuristic global search procedures, to perform parameter estimation and predictive uncertainty analysis, and/or design least-cost remediation systems. However, the size, complexity and distributed nature of these projects can make identifying failures in the associated numerical experiments using conventional ad-hoc approaches both time- consuming and ineffective. To address these problems a multi-tiered debugging framework has been developed. The framework allows for quickly isolating and remedying a number of potential experimental failures, including: failures in the HPC scheduler; bugs in the soft computing code; bugs in the modeling code; and permissions and access control errors. The utility of the framework is demonstrated via application to a series of over 200,000 numerical experiments involving a suite of 5 heuristic global search algorithms and 15 mathematical test functions serving as cheap analogues for the simulation-based optimization of pump-and-treat subsurface remediation systems.

High performance computing in power and energy systems

Energy Technology Data Exchange (ETDEWEB)

Khaitan, Siddhartha Kumar [Iowa State Univ., Ames, IA (United States); Gupta, Anshul (eds.) [IBM Watson Research Center, Yorktown Heights, NY (United States)

2013-07-01

The twin challenge of meeting global energy demands in the face of growing economies and populations and restricting greenhouse gas emissions is one of the most daunting ones that humanity has ever faced. Smart electrical generation and distribution infrastructure will play a crucial role in meeting these challenges. We would need to develop capabilities to handle large volumes of data generated by the power system components like PMUs, DFRs and other data acquisition devices as well as by the capacity to process these data at high resolution via multi-scale and multi-period simulations, cascading and security analysis, interaction between hybrid systems (electric, transport, gas, oil, coal, etc.) and so on, to get meaningful information in real time to ensure a secure, reliable and stable power system grid. Advanced research on development and implementation of market-ready leading-edge high-speed enabling technologies and algorithms for solving real-time, dynamic, resource-critical problems will be required for dynamic security analysis targeted towards successful implementation of Smart Grid initiatives. This books aims to bring together some of the latest research developments as well as thoughts on the future research directions of the high performance computing applications in electric power systems planning, operations, security, markets, and grid integration of alternate sources of energy, etc.

High Performance Computing Operations Review Report

Energy Technology Data Exchange (ETDEWEB)

Cupps, Kimberly C. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

2013-12-19

The High Performance Computing Operations Review (HPCOR) meeting—requested by the ASC and ASCR program headquarters at DOE—was held November 5 and 6, 2013, at the Marriott Hotel in San Francisco, CA. The purpose of the review was to discuss the processes and practices for HPC integration and its related software and facilities. Experiences and lessons learned from the most recent systems deployed were covered in order to benefit the deployment of new systems.

DDT: A Research Tool for Automatic Data Distribution in High Performance Fortran

Directory of Open Access Journals (Sweden)

Eduard AyguadÉ

1997-01-01

Full Text Available This article describes the main features and implementation of our automatic data distribution research tool. The tool (DDT accepts programs written in Fortran 77 and generates High Performance Fortran (HPF directives to map arrays onto the memories of the processors and parallelize loops, and executable statements to remap these arrays. DDT works by identifying a set of computational phases (procedures and loops. The algorithm builds a search space of candidate solutions for these phases which is explored looking for the combination that minimizes the overall cost; this cost includes data movement cost and computation cost. The movement cost reflects the cost of accessing remote data during the execution of a phase and the remapping costs that have to be paid in order to execute the phase with the selected mapping. The computation cost includes the cost of executing a phase in parallel according to the selected mapping and the owner computes rule. The tool supports interprocedural analysis and uses control flow information to identify how phases are sequenced during the execution of the application.

The tracking performance of distributed recoverable flight control systems subject to high intensity radiated fields

Science.gov (United States)

Wang, Rui

It is known that high intensity radiated fields (HIRF) can produce upsets in digital electronics, and thereby degrade the performance of digital flight control systems. Such upsets, either from natural or man-made sources, can change data values on digital buses and memory and affect CPU instruction execution. HIRF environments are also known to trigger common-mode faults, affecting nearly-simultaneously multiple fault containment regions, and hence reducing the benefits of n-modular redundancy and other fault-tolerant computing techniques. Thus, it is important to develop models which describe the integration of the embedded digital system, where the control law is implemented, as well as the dynamics of the closed-loop system. In this dissertation, theoretical tools are presented to analyze the relationship between the design choices for a class of distributed recoverable computing platforms and the tracking performance degradation of a digital flight control system implemented on such a platform while operating in a HIRF environment. Specifically, a tractable hybrid performance model is developed for a digital flight control system implemented on a computing platform inspired largely by the NASA family of fault-tolerant, reconfigurable computer architectures known as SPIDER (scalable processor-independent design for enhanced reliability). The focus will be on the SPIDER implementation, which uses the computer communication system known as ROBUS-2 (reliable optical bus). A physical HIRF experiment was conducted at the NASA Langley Research Center in order to validate the theoretical tracking performance degradation predictions for a distributed Boeing 747 flight control system subject to a HIRF environment. An extrapolation of these results for scenarios that could not be physically tested is also presented.

High Performance Computing in Science and Engineering '08 : Transactions of the High Performance Computing Center

CERN Document Server

Kröner, Dietmar; Resch, Michael

2009-01-01

The discussions and plans on all scienti?c, advisory, and political levels to realize an even larger “European Supercomputer” in Germany, where the hardware costs alone will be hundreds of millions Euro – much more than in the past – are getting closer to realization. As part of the strategy, the three national supercomputing centres HLRS (Stuttgart), NIC/JSC (Julic ¨ h) and LRZ (Munich) have formed the Gauss Centre for Supercomputing (GCS) as a new virtual organization enabled by an agreement between the Federal Ministry of Education and Research (BMBF) and the state ministries for research of Baden-Wurttem ¨ berg, Bayern, and Nordrhein-Westfalen. Already today, the GCS provides the most powerful high-performance computing - frastructure in Europe. Through GCS, HLRS participates in the European project PRACE (Partnership for Advances Computing in Europe) and - tends its reach to all European member countries. These activities aligns well with the activities of HLRS in the European HPC infrastructur...

High performance computing in science and engineering '09: transactions of the High Performance Computing Center, Stuttgart (HLRS) 2009

National Research Council Canada - National Science Library

Nagel, Wolfgang E; Kröner, Dietmar; Resch, Michael

2010-01-01

...), NIC/JSC (J¨ u lich), and LRZ (Munich). As part of that strategic initiative, in May 2009 already NIC/JSC has installed the first phase of the GCS HPC Tier-0 resources, an IBM Blue Gene/P with roughly 300.000 Cores, this time in J¨ u lich, With that, the GCS provides the most powerful high-performance computing infrastructure in Europe alread...

ATLAS Distributed Computing Experience and Performance During the LHC Run-2

Science.gov (United States)

Filipčič, A.; ATLAS Collaboration

2017-10-01

ATLAS Distributed Computing during LHC Run-1 was challenged by steadily increasing computing, storage and network requirements. In addition, the complexity of processing task workflows and their associated data management requirements led to a new paradigm in the ATLAS computing model for Run-2, accompanied by extensive evolution and redesign of the workflow and data management systems. The new systems were put into production at the end of 2014, and gained robustness and maturity during 2015 data taking. ProdSys2, the new request and task interface; JEDI, the dynamic job execution engine developed as an extension to PanDA; and Rucio, the new data management system, form the core of Run-2 ATLAS distributed computing engine. One of the big changes for Run-2 was the adoption of the Derivation Framework, which moves the chaotic CPU and data intensive part of the user analysis into the centrally organized train production, delivering derived AOD datasets to user groups for final analysis. The effectiveness of the new model was demonstrated through the delivery of analysis datasets to users just one week after data taking, by completing the calibration loop, Tier-0 processing and train production steps promptly. The great flexibility of the new system also makes it possible to execute part of the Tier-0 processing on the grid when Tier-0 resources experience a backlog during high data-taking periods. The introduction of the data lifetime model, where each dataset is assigned a finite lifetime (with extensions possible for frequently accessed data), was made possible by Rucio. Thanks to this the storage crises experienced in Run-1 have not reappeared during Run-2. In addition, the distinction between Tier-1 and Tier-2 disk storage, now largely artificial given the quality of Tier-2 resources and their networking, has been removed through the introduction of dynamic ATLAS clouds that group the storage endpoint nucleus and its close-by execution satellite sites. All stable

NCI's High Performance Computing (HPC) and High Performance Data (HPD) Computing Platform for Environmental and Earth System Data Science

Science.gov (United States)

Evans, Ben; Allen, Chris; Antony, Joseph; Bastrakova, Irina; Gohar, Kashif; Porter, David; Pugh, Tim; Santana, Fabiana; Smillie, Jon; Trenham, Claire; Wang, Jingbo; Wyborn, Lesley

2015-04-01

The National Computational Infrastructure (NCI) has established a powerful and flexible in-situ petascale computational environment to enable both high performance computing and Data-intensive Science across a wide spectrum of national environmental and earth science data collections - in particular climate, observational data and geoscientific assets. This paper examines 1) the computational environments that supports the modelling and data processing pipelines, 2) the analysis environments and methods to support data analysis, and 3) the progress so far to harmonise the underlying data collections for future interdisciplinary research across these large volume data collections. NCI has established 10+ PBytes of major national and international data collections from both the government and research sectors based on six themes: 1) weather, climate, and earth system science model simulations, 2) marine and earth observations, 3) geosciences, 4) terrestrial ecosystems, 5) water and hydrology, and 6) astronomy, social and biosciences. Collectively they span the lithosphere, crust, biosphere, hydrosphere, troposphere, and stratosphere. The data is largely sourced from NCI's partners (which include the custodians of many of the major Australian national-scale scientific collections), leading research communities, and collaborating overseas organisations. New infrastructures created at NCI mean the data collections are now accessible within an integrated High Performance Computing and Data (HPC-HPD) environment - a 1.2 PFlop supercomputer (Raijin), a HPC class 3000 core OpenStack cloud system and several highly connected large-scale high-bandwidth Lustre filesystems. The hardware was designed at inception to ensure that it would allow the layered software environment to flexibly accommodate the advancement of future data science. New approaches to software technology and data models have also had to be developed to enable access to these large and exponentially

The contribution of high-performance computing and modelling for industrial development

CSIR Research Space (South Africa)

Sithole, Happy

2017-10-01

Full Text Available Performance Computing and Modelling for Industrial Development Dr Happy Sithole and Dr Onno Ubbink 2 Strategic context • High-performance computing (HPC) combined with machine Learning and artificial intelligence present opportunities to non...

The path toward HEP High Performance Computing

International Nuclear Information System (INIS)

Apostolakis, John; Brun, René; Gheata, Andrei; Wenzel, Sandro; Carminati, Federico

2014-01-01

High Energy Physics code has been known for making poor use of high performance computing architectures. Efforts in optimising HEP code on vector and RISC architectures have yield limited results and recent studies have shown that, on modern architectures, it achieves a performance between 10% and 50% of the peak one. Although several successful attempts have been made to port selected codes on GPUs, no major HEP code suite has a 'High Performance' implementation. With LHC undergoing a major upgrade and a number of challenging experiments on the drawing board, HEP cannot any longer neglect the less-than-optimal performance of its code and it has to try making the best usage of the hardware. This activity is one of the foci of the SFT group at CERN, which hosts, among others, the Root and Geant4 project. The activity of the experiments is shared and coordinated via a Concurrency Forum, where the experience in optimising HEP code is presented and discussed. Another activity is the Geant-V project, centred on the development of a highperformance prototype for particle transport. Achieving a good concurrency level on the emerging parallel architectures without a complete redesign of the framework can only be done by parallelizing at event level, or with a much larger effort at track level. Apart the shareable data structures, this typically implies a multiplication factor in terms of memory consumption compared to the single threaded version, together with sub-optimal handling of event processing tails. Besides this, the low level instruction pipelining of modern processors cannot be used efficiently to speedup the program. We have implemented a framework that allows scheduling vectors of particles to an arbitrary number of computing resources in a fine grain parallel approach. The talk will review the current optimisation activities within the SFT group with a particular emphasis on the development perspectives towards a simulation framework able to profit

High performance computing and communications: FY 1997 implementation plan

Energy Technology Data Exchange (ETDEWEB)

NONE

1996-12-01

The High Performance Computing and Communications (HPCC) Program was formally authorized by passage, with bipartisan support, of the High-Performance Computing Act of 1991, signed on December 9, 1991. The original Program, in which eight Federal agencies participated, has now grown to twelve agencies. This Plan provides a detailed description of the agencies` FY 1996 HPCC accomplishments and FY 1997 HPCC plans. Section 3 of this Plan provides an overview of the HPCC Program. Section 4 contains more detailed definitions of the Program Component Areas, with an emphasis on the overall directions and milestones planned for each PCA. Appendix A provides a detailed look at HPCC Program activities within each agency.

High performance computing and communications: FY 1996 implementation plan

Energy Technology Data Exchange (ETDEWEB)

NONE

1995-05-16

The High Performance Computing and Communications (HPCC) Program was formally authorized by passage of the High Performance Computing Act of 1991, signed on December 9, 1991. Twelve federal agencies, in collaboration with scientists and managers from US industry, universities, and research laboratories, have developed the Program to meet the challenges of advancing computing and associated communications technologies and practices. This plan provides a detailed description of the agencies` HPCC implementation plans for FY 1995 and FY 1996. This Implementation Plan contains three additional sections. Section 3 provides an overview of the HPCC Program definition and organization. Section 4 contains a breakdown of the five major components of the HPCC Program, with an emphasis on the overall directions and milestones planned for each one. Section 5 provides a detailed look at HPCC Program activities within each agency.

A performance model for the communication in fast multipole methods on high-performance computing platforms

KAUST Repository

Ibeid, Huda

2016-03-04

Exascale systems are predicted to have approximately 1 billion cores, assuming gigahertz cores. Limitations on affordable network topologies for distributed memory systems of such massive scale bring new challenges to the currently dominant parallel programing model. Currently, there are many efforts to evaluate the hardware and software bottlenecks of exascale designs. It is therefore of interest to model application performance and to understand what changes need to be made to ensure extrapolated scalability. The fast multipole method (FMM) was originally developed for accelerating N-body problems in astrophysics and molecular dynamics but has recently been extended to a wider range of problems. Its high arithmetic intensity combined with its linear complexity and asynchronous communication patterns make it a promising algorithm for exascale systems. In this paper, we discuss the challenges for FMM on current parallel computers and future exascale architectures, with a focus on internode communication. We focus on the communication part only; the efficiency of the computational kernels are beyond the scope of the present study. We develop a performance model that considers the communication patterns of the FMM and observe a good match between our model and the actual communication time on four high-performance computing (HPC) systems, when latency, bandwidth, network topology, and multicore penalties are all taken into account. To our knowledge, this is the first formal characterization of internode communication in FMM that validates the model against actual measurements of communication time. The ultimate communication model is predictive in an absolute sense; however, on complex systems, this objective is often out of reach or of a difficulty out of proportion to its benefit when there exists a simpler model that is inexpensive and sufficient to guide coding decisions leading to improved scaling. The current model provides such guidance.

High performance computing in science and engineering Garching/Munich 2016

Energy Technology Data Exchange (ETDEWEB)

Wagner, Siegfried; Bode, Arndt; Bruechle, Helmut; Brehm, Matthias (eds.)

2016-11-01

Computer simulations are the well-established third pillar of natural sciences along with theory and experimentation. Particularly high performance computing is growing fast and constantly demands more and more powerful machines. To keep pace with this development, in spring 2015, the Leibniz Supercomputing Centre installed the high performance computing system SuperMUC Phase 2, only three years after the inauguration of its sibling SuperMUC Phase 1. Thereby, the compute capabilities were more than doubled. This book covers the time-frame June 2014 until June 2016. Readers will find many examples of outstanding research in the more than 130 projects that are covered in this book, with each one of these projects using at least 4 million core-hours on SuperMUC. The largest scientific communities using SuperMUC in the last two years were computational fluid dynamics simulations, chemistry and material sciences, astrophysics, and life sciences.

Interactive Data Exploration for High-Performance Fluid Flow Computations through Porous Media

KAUST Repository

Perovic, Nevena

2014-09-01

© 2014 IEEE. Huge data advent in high-performance computing (HPC) applications such as fluid flow simulations usually hinders the interactive processing and exploration of simulation results. Such an interactive data exploration not only allows scientiest to \\'play\\' with their data but also to visualise huge (distributed) data sets in both an efficient and easy way. Therefore, we propose an HPC data exploration service based on a sliding window concept, that enables researches to access remote data (available on a supercomputer or cluster) during simulation runtime without exceeding any bandwidth limitations between the HPC back-end and the user front-end.

Benchmarking high performance computing architectures with CMS’ skeleton framework

Science.gov (United States)

Sexton-Kennedy, E.; Gartung, P.; Jones, C. D.

2017-10-01

In 2012 CMS evaluated which underlying concurrency technology would be the best to use for its multi-threaded framework. The available technologies were evaluated on the high throughput computing systems dominating the resources in use at that time. A skeleton framework benchmarking suite that emulates the tasks performed within a CMSSW application was used to select Intel’s Thread Building Block library, based on the measured overheads in both memory and CPU on the different technologies benchmarked. In 2016 CMS will get access to high performance computing resources that use new many core architectures; machines such as Cori Phase 1&2, Theta, Mira. Because of this we have revived the 2012 benchmark to test it’s performance and conclusions on these new architectures. This talk will discuss the results of this exercise.

Contemporary high performance computing from petascale toward exascale

CERN Document Server

Vetter, Jeffrey S

2015-01-01

A continuation of Contemporary High Performance Computing: From Petascale toward Exascale, this second volume continues the discussion of HPC flagship systems, major application workloads, facilities, and sponsors. The book includes of figures and pictures that capture the state of existing systems: pictures of buildings, systems in production, floorplans, and many block diagrams and charts to illustrate system design and performance.

Resilient and Robust High Performance Computing Platforms for Scientific Computing Integrity

Energy Technology Data Exchange (ETDEWEB)

Jin, Yier [Univ. of Central Florida, Orlando, FL (United States)

2017-07-14

As technology advances, computer systems are subject to increasingly sophisticated cyber-attacks that compromise both their security and integrity. High performance computing platforms used in commercial and scientific applications involving sensitive, or even classified data, are frequently targeted by powerful adversaries. This situation is made worse by a lack of fundamental security solutions that both perform efficiently and are effective at preventing threats. Current security solutions fail to address the threat landscape and ensure the integrity of sensitive data. As challenges rise, both private and public sectors will require robust technologies to protect its computing infrastructure. The research outcomes from this project try to address all these challenges. For example, we present LAZARUS, a novel technique to harden kernel Address Space Layout Randomization (KASLR) against paging-based side-channel attacks. In particular, our scheme allows for fine-grained protection of the virtual memory mappings that implement the randomization. We demonstrate the effectiveness of our approach by hardening a recent Linux kernel with LAZARUS, mitigating all of the previously presented side-channel attacks on KASLR. Our extensive evaluation shows that LAZARUS incurs only 0.943% overhead for standard benchmarks, and is therefore highly practical. We also introduced HA2lloc, a hardware-assisted allocator that is capable of leveraging an extended memory management unit to detect memory errors in the heap. We also perform testing using HA2lloc in a simulation environment and find that the approach is capable of preventing common memory vulnerabilities.

A high performance scientific cloud computing environment for materials simulations

Science.gov (United States)

Jorissen, K.; Vila, F. D.; Rehr, J. J.

2012-09-01

We describe the development of a scientific cloud computing (SCC) platform that offers high performance computation capability. The platform consists of a scientific virtual machine prototype containing a UNIX operating system and several materials science codes, together with essential interface tools (an SCC toolset) that offers functionality comparable to local compute clusters. In particular, our SCC toolset provides automatic creation of virtual clusters for parallel computing, including tools for execution and monitoring performance, as well as efficient I/O utilities that enable seamless connections to and from the cloud. Our SCC platform is optimized for the Amazon Elastic Compute Cloud (EC2). We present benchmarks for prototypical scientific applications and demonstrate performance comparable to local compute clusters. To facilitate code execution and provide user-friendly access, we have also integrated cloud computing capability in a JAVA-based GUI. Our SCC platform may be an alternative to traditional HPC resources for materials science or quantum chemistry applications.

Implementing Molecular Dynamics for Hybrid High Performance Computers - 1. Short Range Forces

International Nuclear Information System (INIS)

Brown, W. Michael; Wang, Peng; Plimpton, Steven J.; Tharrington, Arnold N.

2011-01-01

The use of accelerators such as general-purpose graphics processing units (GPGPUs) have become popular in scientific computing applications due to their low cost, impressive floating-point capabilities, high memory bandwidth, and low electrical power requirements. Hybrid high performance computers, machines with more than one type of floating-point processor, are now becoming more prevalent due to these advantages. In this work, we discuss several important issues in porting a large molecular dynamics code for use on parallel hybrid machines - (1) choosing a hybrid parallel decomposition that works on central processing units (CPUs) with distributed memory and accelerator cores with shared memory, (2) minimizing the amount of code that must be ported for efficient acceleration, (3) utilizing the available processing power from both many-core CPUs and accelerators, and (4) choosing a programming model for acceleration. We present our solution to each of these issues for short-range force calculation in the molecular dynamics package LAMMPS. We describe algorithms for efficient short range force calculation on hybrid high performance machines. We describe a new approach for dynamic load balancing of work between CPU and accelerator cores. We describe the Geryon library that allows a single code to compile with both CUDA and OpenCL for use on a variety of accelerators. Finally, we present results on a parallel test cluster containing 32 Fermi GPGPUs and 180 CPU cores.

High Performance Computing Multicast

Science.gov (United States)

2012-02-01

A History of the Virtual Synchrony Replication Model,” in Replication: Theory and Practice, Charron-Bost, B., Pedone, F., and Schiper, A. (Eds...Performance Computing IP / IPv4 Internet Protocol (version 4.0) IPMC Internet Protocol MultiCast LAN Local Area Network MCMD Dr. Multicast MPI

A high performance scientific cloud computing environment for materials simulations

OpenAIRE

Jorissen, Kevin; Vila, Fernando D.; Rehr, John J.

2011-01-01

We describe the development of a scientific cloud computing (SCC) platform that offers high performance computation capability. The platform consists of a scientific virtual machine prototype containing a UNIX operating system and several materials science codes, together with essential interface tools (an SCC toolset) that offers functionality comparable to local compute clusters. In particular, our SCC toolset provides automatic creation of virtual clusters for parallel computing, including...

The path toward HEP High Performance Computing

CERN Document Server

Apostolakis, John; Carminati, Federico; Gheata, Andrei; Wenzel, Sandro

2014-01-01

High Energy Physics code has been known for making poor use of high performance computing architectures. Efforts in optimising HEP code on vector and RISC architectures have yield limited results and recent studies have shown that, on modern architectures, it achieves a performance between 10% and 50% of the peak one. Although several successful attempts have been made to port selected codes on GPUs, no major HEP code suite has a 'High Performance' implementation. With LHC undergoing a major upgrade and a number of challenging experiments on the drawing board, HEP cannot any longer neglect the less-than-optimal performance of its code and it has to try making the best usage of the hardware. This activity is one of the foci of the SFT group at CERN, which hosts, among others, the Root and Geant4 project. The activity of the experiments is shared and coordinated via a Concurrency Forum, where the experience in optimising HEP code is presented and discussed. Another activity is the Geant-V project, centred on th...

Comparison of High-Fidelity Computational Tools for Wing Design of a Distributed Electric Propulsion Aircraft

Science.gov (United States)

Deere, Karen A.; Viken, Sally A.; Carter, Melissa B.; Viken, Jeffrey K.; Derlaga, Joseph M.; Stoll, Alex M.

2017-01-01

A variety of tools, from fundamental to high order, have been used to better understand applications of distributed electric propulsion to aid the wing and propulsion system design of the Leading Edge Asynchronous Propulsion Technology (LEAPTech) project and the X-57 Maxwell airplane. Three high-fidelity, Navier-Stokes computational fluid dynamics codes used during the project with results presented here are FUN3D, STAR-CCM+, and OVERFLOW. These codes employ various turbulence models to predict fully turbulent and transitional flow. Results from these codes are compared for two distributed electric propulsion configurations: the wing tested at NASA Armstrong on the Hybrid-Electric Integrated Systems Testbed truck, and the wing designed for the X-57 Maxwell airplane. Results from these computational tools for the high-lift wing tested on the Hybrid-Electric Integrated Systems Testbed truck and the X-57 high-lift wing presented compare reasonably well. The goal of the X-57 wing and distributed electric propulsion system design achieving or exceeding the required ?? (sub L) = 3.95 for stall speed was confirmed with all of the computational codes.

High-performance computing for structural mechanics and earthquake/tsunami engineering

CERN Document Server

Hori, Muneo; Ohsaki, Makoto

2016-01-01

Huge earthquakes and tsunamis have caused serious damage to important structures such as civil infrastructure elements, buildings and power plants around the globe.  To quantitatively evaluate such damage processes and to design effective prevention and mitigation measures, the latest high-performance computational mechanics technologies, which include telascale to petascale computers, can offer powerful tools. The phenomena covered in this book include seismic wave propagation in the crust and soil, seismic response of infrastructure elements such as tunnels considering soil-structure interactions, seismic response of high-rise buildings, seismic response of nuclear power plants, tsunami run-up over coastal towns and tsunami inundation considering fluid-structure interactions. The book provides all necessary information for addressing these phenomena, ranging from the fundamentals of high-performance computing for finite element methods, key algorithms of accurate dynamic structural analysis, fluid flows ...

Understanding and Improving the Performance Consistency of Distributed Computing Systems

NARCIS (Netherlands)

Yigitbasi, M.N.

2012-01-01

With the increasing adoption of distributed systems in both academia and industry, and with the increasing computational and storage requirements of distributed applications, users inevitably demand more from these systems. Moreover, users also depend on these systems for latency and throughput

High performance in software development

CERN Multimedia

CERN. Geneva; Haapio, Petri; Liukkonen, Juha-Matti

2015-01-01

What are the ingredients of high-performing software? Software development, especially for large high-performance systems, is one the most complex tasks mankind has ever tried. Technological change leads to huge opportunities but challenges our old ways of working. Processing large data sets, possibly in real time or with other tight computational constraints, requires an efficient solution architecture. Efficiency requirements span from the distributed storage and large-scale organization of computation and data onto the lowest level of processor and data bus behavior. Integrating performance behavior over these levels is especially important when the computation is resource-bounded, as it is in numerics: physical simulation, machine learning, estimation of statistical models, etc. For example, memory locality and utilization of vector processing are essential for harnessing the computing power of modern processor architectures due to the deep memory hierarchies of modern general-purpose computers. As a r...

LHCb Distributed Data Analysis on the Computing Grid

CERN Document Server

Paterson, S; Parkes, C

2006-01-01

LHCb is one of the four Large Hadron Collider (LHC) experiments based at CERN, the European Organisation for Nuclear Research. The LHC experiments will start taking an unprecedented amount of data when they come online in 2007. Since no single institute has the compute resources to handle this data, resources must be pooled to form the Grid. Where the Internet has made it possible to share information stored on computers across the world, Grid computing aims to provide access to computing power and storage capacity on geographically distributed systems. LHCb software applications must work seamlessly on the Grid allowing users to efficiently access distributed compute resources. It is essential to the success of the LHCb experiment that physicists can access data from the detector, stored in many heterogeneous systems, to perform distributed data analysis. This thesis describes the work performed to enable distributed data analysis for the LHCb experiment on the LHC Computing Grid.

High performance computing system in the framework of the Higgs boson studies

CERN Document Server

Belyaev, Nikita; The ATLAS collaboration

2017-01-01

The Higgs boson physics is one of the most important and promising fields of study in modern High Energy Physics. To perform precision measurements of the Higgs boson properties, the use of fast and efficient instruments of Monte Carlo event simulation is required. Due to the increasing amount of data and to the growing complexity of the simulation software tools, the computing resources currently available for Monte Carlo simulation on the LHC GRID are not sufficient. One of the possibilities to address this shortfall of computing resources is the usage of institutes computer clusters, commercial computing resources and supercomputers. In this paper, a brief description of the Higgs boson physics, the Monte-Carlo generation and event simulation techniques are presented. A description of modern high performance computing systems and tests of their performance are also discussed. These studies have been performed on the Worldwide LHC Computing Grid and Kurchatov Institute Data Processing Center, including Tier...

A Software Rejuvenation Framework for Distributed Computing

Science.gov (United States)

Chau, Savio

2009-01-01

A performability-oriented conceptual framework for software rejuvenation has been constructed as a means of increasing levels of reliability and performance in distributed stateful computing. As used here, performability-oriented signifies that the construction of the framework is guided by the concept of analyzing the ability of a given computing system to deliver services with gracefully degradable performance. The framework is especially intended to support applications that involve stateful replicas of server computers.

Scientific Grand Challenges: Forefront Questions in Nuclear Science and the Role of High Performance Computing

International Nuclear Information System (INIS)

Khaleel, Mohammad A.

2009-01-01

This report is an account of the deliberations and conclusions of the workshop on 'Forefront Questions in Nuclear Science and the Role of High Performance Computing' held January 26-28, 2009, co-sponsored by the U.S. Department of Energy (DOE) Office of Nuclear Physics (ONP) and the DOE Office of Advanced Scientific Computing (ASCR). Representatives from the national and international nuclear physics communities, as well as from the high performance computing community, participated. The purpose of this workshop was to (1) identify forefront scientific challenges in nuclear physics and then determine which-if any-of these could be aided by high performance computing at the extreme scale; (2) establish how and why new high performance computing capabilities could address issues at the frontiers of nuclear science; (3) provide nuclear physicists the opportunity to influence the development of high performance computing; and (4) provide the nuclear physics community with plans for development of future high performance computing capability by DOE ASCR.

Scientific Grand Challenges: Forefront Questions in Nuclear Science and the Role of High Performance Computing

Energy Technology Data Exchange (ETDEWEB)

Khaleel, Mohammad A.

2009-10-01

This report is an account of the deliberations and conclusions of the workshop on "Forefront Questions in Nuclear Science and the Role of High Performance Computing" held January 26-28, 2009, co-sponsored by the U.S. Department of Energy (DOE) Office of Nuclear Physics (ONP) and the DOE Office of Advanced Scientific Computing (ASCR). Representatives from the national and international nuclear physics communities, as well as from the high performance computing community, participated. The purpose of this workshop was to 1) identify forefront scientific challenges in nuclear physics and then determine which-if any-of these could be aided by high performance computing at the extreme scale; 2) establish how and why new high performance computing capabilities could address issues at the frontiers of nuclear science; 3) provide nuclear physicists the opportunity to influence the development of high performance computing; and 4) provide the nuclear physics community with plans for development of future high performance computing capability by DOE ASCR.

High performance parallel computers for science: New developments at the Fermilab advanced computer program

International Nuclear Information System (INIS)

Nash, T.; Areti, H.; Atac, R.

1988-08-01

Fermilab's Advanced Computer Program (ACP) has been developing highly cost effective, yet practical, parallel computers for high energy physics since 1984. The ACP's latest developments are proceeding in two directions. A Second Generation ACP Multiprocessor System for experiments will include $3500 RISC processors each with performance over 15 VAX MIPS. To support such high performance, the new system allows parallel I/O, parallel interprocess communication, and parallel host processes. The ACP Multi-Array Processor, has been developed for theoretical physics. Each $4000 node is a FORTRAN or C programmable pipelined 20 MFlops (peak), 10 MByte single board computer. These are plugged into a 16 port crossbar switch crate which handles both inter and intra crate communication. The crates are connected in a hypercube. Site oriented applications like lattice gauge theory are supported by system software called CANOPY, which makes the hardware virtually transparent to users. A 256 node, 5 GFlop, system is under construction. 10 refs., 7 figs

Simple, parallel, high-performance virtual machines for extreme computations

International Nuclear Information System (INIS)

Chokoufe Nejad, Bijan; Ohl, Thorsten; Reuter, Jurgen

2014-11-01

We introduce a high-performance virtual machine (VM) written in a numerically fast language like Fortran or C to evaluate very large expressions. We discuss the general concept of how to perform computations in terms of a VM and present specifically a VM that is able to compute tree-level cross sections for any number of external legs, given the corresponding byte code from the optimal matrix element generator, O'Mega. Furthermore, this approach allows to formulate the parallel computation of a single phase space point in a simple and obvious way. We analyze hereby the scaling behaviour with multiple threads as well as the benefits and drawbacks that are introduced with this method. Our implementation of a VM can run faster than the corresponding native, compiled code for certain processes and compilers, especially for very high multiplicities, and has in general runtimes in the same order of magnitude. By avoiding the tedious compile and link steps, which may fail for source code files of gigabyte sizes, new processes or complex higher order corrections that are currently out of reach could be evaluated with a VM given enough computing power.

Heterogeneous High Throughput Scientific Computing with APM X-Gene and Intel Xeon Phi

CERN Document Server

Abdurachmanov, David; Elmer, Peter; Eulisse, Giulio; Knight, Robert; Muzaffar, Shahzad

2014-01-01

Electrical power requirements will be a constraint on the future growth of Distributed High Throughput Computing (DHTC) as used by High Energy Physics. Performance-per-watt is a critical metric for the evaluation of computer architectures for cost- efficient computing. Additionally, future performance growth will come from heterogeneous, many-core, and high computing density platforms with specialized processors. In this paper, we examine the Intel Xeon Phi Many Integrated Cores (MIC) co-processor and Applied Micro X-Gene ARMv8 64-bit low-power server system-on-a-chip (SoC) solutions for scientific computing applications. We report our experience on software porting, performance and energy efficiency and evaluate the potential for use of such technologies in the context of distributed computing systems such as the Worldwide LHC Computing Grid (WLCG).

Heterogeneous High Throughput Scientific Computing with APM X-Gene and Intel Xeon Phi

Science.gov (United States)

Abdurachmanov, David; Bockelman, Brian; Elmer, Peter; Eulisse, Giulio; Knight, Robert; Muzaffar, Shahzad

2015-05-01

Electrical power requirements will be a constraint on the future growth of Distributed High Throughput Computing (DHTC) as used by High Energy Physics. Performance-per-watt is a critical metric for the evaluation of computer architectures for cost- efficient computing. Additionally, future performance growth will come from heterogeneous, many-core, and high computing density platforms with specialized processors. In this paper, we examine the Intel Xeon Phi Many Integrated Cores (MIC) co-processor and Applied Micro X-Gene ARMv8 64-bit low-power server system-on-a-chip (SoC) solutions for scientific computing applications. We report our experience on software porting, performance and energy efficiency and evaluate the potential for use of such technologies in the context of distributed computing systems such as the Worldwide LHC Computing Grid (WLCG).

Heterogeneous High Throughput Scientific Computing with APM X-Gene and Intel Xeon Phi

International Nuclear Information System (INIS)

Abdurachmanov, David; Bockelman, Brian; Elmer, Peter; Eulisse, Giulio; Muzaffar, Shahzad; Knight, Robert

2015-01-01

Electrical power requirements will be a constraint on the future growth of Distributed High Throughput Computing (DHTC) as used by High Energy Physics. Performance-per-watt is a critical metric for the evaluation of computer architectures for cost- efficient computing. Additionally, future performance growth will come from heterogeneous, many-core, and high computing density platforms with specialized processors. In this paper, we examine the Intel Xeon Phi Many Integrated Cores (MIC) co-processor and Applied Micro X-Gene ARMv8 64-bit low-power server system-on-a-chip (SoC) solutions for scientific computing applications. We report our experience on software porting, performance and energy efficiency and evaluate the potential for use of such technologies in the context of distributed computing systems such as the Worldwide LHC Computing Grid (WLCG). (paper)

A High Performance VLSI Computer Architecture For Computer Graphics

Science.gov (United States)

Chin, Chi-Yuan; Lin, Wen-Tai

1988-10-01

A VLSI computer architecture, consisting of multiple processors, is presented in this paper to satisfy the modern computer graphics demands, e.g. high resolution, realistic animation, real-time display etc.. All processors share a global memory which are partitioned into multiple banks. Through a crossbar network, data from one memory bank can be broadcasted to many processors. Processors are physically interconnected through a hyper-crossbar network (a crossbar-like network). By programming the network, the topology of communication links among processors can be reconfigurated to satisfy specific dataflows of different applications. Each processor consists of a controller, arithmetic operators, local memory, a local crossbar network, and I/O ports to communicate with other processors, memory banks, and a system controller. Operations in each processor are characterized into two modes, i.e. object domain and space domain, to fully utilize the data-independency characteristics of graphics processing. Special graphics features such as 3D-to-2D conversion, shadow generation, texturing, and reflection, can be easily handled. With the current high density interconnection (MI) technology, it is feasible to implement a 64-processor system to achieve 2.5 billion operations per second, a performance needed in most advanced graphics applications.

High Performance Numerical Computing for High Energy Physics: A New Challenge for Big Data Science

International Nuclear Information System (INIS)

Pop, Florin

2014-01-01

Modern physics is based on both theoretical analysis and experimental validation. Complex scenarios like subatomic dimensions, high energy, and lower absolute temperature are frontiers for many theoretical models. Simulation with stable numerical methods represents an excellent instrument for high accuracy analysis, experimental validation, and visualization. High performance computing support offers possibility to make simulations at large scale, in parallel, but the volume of data generated by these experiments creates a new challenge for Big Data Science. This paper presents existing computational methods for high energy physics (HEP) analyzed from two perspectives: numerical methods and high performance computing. The computational methods presented are Monte Carlo methods and simulations of HEP processes, Markovian Monte Carlo, unfolding methods in particle physics, kernel estimation in HEP, and Random Matrix Theory used in analysis of particles spectrum. All of these methods produce data-intensive applications, which introduce new challenges and requirements for ICT systems architecture, programming paradigms, and storage capabilities.

FY 1992 Blue Book: Grand Challenges: High Performance Computing and Communications

Data.gov (United States)

Networking and Information Technology Research and Development, Executive Office of the President — High performance computing and computer communications networks are becoming increasingly important to scientific advancement, economic competition, and national...

High performance computing and communications: Advancing the frontiers of information technology

Energy Technology Data Exchange (ETDEWEB)

NONE

1997-12-31

This report, which supplements the President`s Fiscal Year 1997 Budget, describes the interagency High Performance Computing and Communications (HPCC) Program. The HPCC Program will celebrate its fifth anniversary in October 1996 with an impressive array of accomplishments to its credit. Over its five-year history, the HPCC Program has focused on developing high performance computing and communications technologies that can be applied to computation-intensive applications. Major highlights for FY 1996: (1) High performance computing systems enable practical solutions to complex problems with accuracies not possible five years ago; (2) HPCC-funded research in very large scale networking techniques has been instrumental in the evolution of the Internet, which continues exponential growth in size, speed, and availability of information; (3) The combination of hardware capability measured in gigaflop/s, networking technology measured in gigabit/s, and new computational science techniques for modeling phenomena has demonstrated that very large scale accurate scientific calculations can be executed across heterogeneous parallel processing systems located thousands of miles apart; (4) Federal investments in HPCC software R and D support researchers who pioneered the development of parallel languages and compilers, high performance mathematical, engineering, and scientific libraries, and software tools--technologies that allow scientists to use powerful parallel systems to focus on Federal agency mission applications; and (5) HPCC support for virtual environments has enabled the development of immersive technologies, where researchers can explore and manipulate multi-dimensional scientific and engineering problems. Educational programs fostered by the HPCC Program have brought into classrooms new science and engineering curricula designed to teach computational science. This document contains a small sample of the significant HPCC Program accomplishments in FY 1996.

High Performance Polar Decomposition on Distributed Memory Systems

KAUST Repository

Sukkari, Dalal E.

2016-08-08

The polar decomposition of a dense matrix is an important operation in linear algebra. It can be directly calculated through the singular value decomposition (SVD) or iteratively using the QR dynamically-weighted Halley algorithm (QDWH). The former is difficult to parallelize due to the preponderant number of memory-bound operations during the bidiagonal reduction. We investigate the latter scenario, which performs more floating-point operations but exposes at the same time more parallelism, and therefore, runs closer to the theoretical peak performance of the system, thanks to more compute-bound matrix operations. Profiling results show the performance scalability of QDWH for calculating the polar decomposition using around 9200 MPI processes on well and ill-conditioned matrices of 100K×100K problem size. We study then the performance impact of the QDWH-based polar decomposition as a pre-processing step toward calculating the SVD itself. The new distributed-memory implementation of the QDWH-SVD solver achieves up to five-fold speedup against current state-of-the-art vendor SVD implementations. © Springer International Publishing Switzerland 2016.

Component-based software for high-performance scientific computing

Energy Technology Data Exchange (ETDEWEB)

Alexeev, Yuri; Allan, Benjamin A; Armstrong, Robert C; Bernholdt, David E; Dahlgren, Tamara L; Gannon, Dennis; Janssen, Curtis L; Kenny, Joseph P; Krishnan, Manojkumar; Kohl, James A; Kumfert, Gary; McInnes, Lois Curfman; Nieplocha, Jarek; Parker, Steven G; Rasmussen, Craig; Windus, Theresa L

2005-01-01

Recent advances in both computational hardware and multidisciplinary science have given rise to an unprecedented level of complexity in scientific simulation software. This paper describes an ongoing grass roots effort aimed at addressing complexity in high-performance computing through the use of Component-Based Software Engineering (CBSE). Highlights of the benefits and accomplishments of the Common Component Architecture (CCA) Forum and SciDAC ISIC are given, followed by an illustrative example of how the CCA has been applied to drive scientific discovery in quantum chemistry. Thrusts for future research are also described briefly.

Component-based software for high-performance scientific computing

International Nuclear Information System (INIS)

Alexeev, Yuri; Allan, Benjamin A; Armstrong, Robert C; Bernholdt, David E; Dahlgren, Tamara L; Gannon, Dennis; Janssen, Curtis L; Kenny, Joseph P; Krishnan, Manojkumar; Kohl, James A; Kumfert, Gary; McInnes, Lois Curfman; Nieplocha, Jarek; Parker, Steven G; Rasmussen, Craig; Windus, Theresa L

2005-01-01

Recent advances in both computational hardware and multidisciplinary science have given rise to an unprecedented level of complexity in scientific simulation software. This paper describes an ongoing grass roots effort aimed at addressing complexity in high-performance computing through the use of Component-Based Software Engineering (CBSE). Highlights of the benefits and accomplishments of the Common Component Architecture (CCA) Forum and SciDAC ISIC are given, followed by an illustrative example of how the CCA has been applied to drive scientific discovery in quantum chemistry. Thrusts for future research are also described briefly

Distributed multiscale computing

NARCIS (Netherlands)

Borgdorff, J.

2014-01-01

Multiscale models combine knowledge, data, and hypotheses from different scales. Simulating a multiscale model often requires extensive computation. This thesis evaluates distributing these computations, an approach termed distributed multiscale computing (DMC). First, the process of multiscale

High-performance computing on GPUs for resistivity logging of oil and gas wells

Science.gov (United States)

Glinskikh, V.; Dudaev, A.; Nechaev, O.; Surodina, I.

2017-10-01

We developed and implemented into software an algorithm for high-performance simulation of electrical logs from oil and gas wells using high-performance heterogeneous computing. The numerical solution of the 2D forward problem is based on the finite-element method and the Cholesky decomposition for solving a system of linear algebraic equations (SLAE). Software implementations of the algorithm used the NVIDIA CUDA technology and computing libraries are made, allowing us to perform decomposition of SLAE and find its solution on central processor unit (CPU) and graphics processor unit (GPU). The calculation time is analyzed depending on the matrix size and number of its non-zero elements. We estimated the computing speed on CPU and GPU, including high-performance heterogeneous CPU-GPU computing. Using the developed algorithm, we simulated resistivity data in realistic models.

Organization of the secure distributed computing based on multi-agent system

Science.gov (United States)

Khovanskov, Sergey; Rumyantsev, Konstantin; Khovanskova, Vera

2018-04-01

Nowadays developing methods for distributed computing is received much attention. One of the methods of distributed computing is using of multi-agent systems. The organization of distributed computing based on the conventional network computers can experience security threats performed by computational processes. Authors have developed the unified agent algorithm of control system of computing network nodes operation. Network PCs is used as computing nodes. The proposed multi-agent control system for the implementation of distributed computing allows in a short time to organize using of the processing power of computers any existing network to solve large-task by creating a distributed computing. Agents based on a computer network can: configure a distributed computing system; to distribute the computational load among computers operated agents; perform optimization distributed computing system according to the computing power of computers on the network. The number of computers connected to the network can be increased by connecting computers to the new computer system, which leads to an increase in overall processing power. Adding multi-agent system in the central agent increases the security of distributed computing. This organization of the distributed computing system reduces the problem solving time and increase fault tolerance (vitality) of computing processes in a changing computing environment (dynamic change of the number of computers on the network). Developed a multi-agent system detects cases of falsification of the results of a distributed system, which may lead to wrong decisions. In addition, the system checks and corrects wrong results.

High performance computing and communications: FY 1995 implementation plan

Energy Technology Data Exchange (ETDEWEB)

NONE

1994-04-01

The High Performance Computing and Communications (HPCC) Program was formally established following passage of the High Performance Computing Act of 1991 signed on December 9, 1991. Ten federal agencies in collaboration with scientists and managers from US industry, universities, and laboratories have developed the HPCC Program to meet the challenges of advancing computing and associated communications technologies and practices. This plan provides a detailed description of the agencies` HPCC implementation plans for FY 1994 and FY 1995. This Implementation Plan contains three additional sections. Section 3 provides an overview of the HPCC Program definition and organization. Section 4 contains a breakdown of the five major components of the HPCC Program, with an emphasis on the overall directions and milestones planned for each one. Section 5 provides a detailed look at HPCC Program activities within each agency. Although the Department of Education is an official HPCC agency, its current funding and reporting of crosscut activities goes through the Committee on Education and Health Resources, not the HPCC Program. For this reason the Implementation Plan covers nine HPCC agencies.

Computational Environments and Analysis methods available on the NCI High Performance Computing (HPC) and High Performance Data (HPD) Platform

Science.gov (United States)

Evans, B. J. K.; Foster, C.; Minchin, S. A.; Pugh, T.; Lewis, A.; Wyborn, L. A.; Evans, B. J.; Uhlherr, A.

2014-12-01

The National Computational Infrastructure (NCI) has established a powerful in-situ computational environment to enable both high performance computing and data-intensive science across a wide spectrum of national environmental data collections - in particular climate, observational data and geoscientific assets. This paper examines 1) the computational environments that supports the modelling and data processing pipelines, 2) the analysis environments and methods to support data analysis, and 3) the progress in addressing harmonisation of the underlying data collections for future transdisciplinary research that enable accurate climate projections. NCI makes available 10+ PB major data collections from both the government and research sectors based on six themes: 1) weather, climate, and earth system science model simulations, 2) marine and earth observations, 3) geosciences, 4) terrestrial ecosystems, 5) water and hydrology, and 6) astronomy, social and biosciences. Collectively they span the lithosphere, crust, biosphere, hydrosphere, troposphere, and stratosphere. The data is largely sourced from NCI's partners (which include the custodians of many of the national scientific records), major research communities, and collaborating overseas organisations. The data is accessible within an integrated HPC-HPD environment - a 1.2 PFlop supercomputer (Raijin), a HPC class 3000 core OpenStack cloud system and several highly connected large scale and high-bandwidth Lustre filesystems. This computational environment supports a catalogue of integrated reusable software and workflows from earth system and ecosystem modelling, weather research, satellite and other observed data processing and analysis. To enable transdisciplinary research on this scale, data needs to be harmonised so that researchers can readily apply techniques and software across the corpus of data available and not be constrained to work within artificial disciplinary boundaries. Future challenges will

Open source acceleration of wave optics simulations on energy efficient high-performance computing platforms

Science.gov (United States)

Beck, Jeffrey; Bos, Jeremy P.

2017-05-01

We compare several modifications to the open-source wave optics package, WavePy, intended to improve execution time. Specifically, we compare the relative performance of the Intel MKL, a CPU based OpenCV distribution, and GPU-based version. Performance is compared between distributions both on the same compute platform and between a fully-featured computing workstation and the NVIDIA Jetson TX1 platform. Comparisons are drawn in terms of both execution time and power consumption. We have found that substituting the Fast Fourier Transform operation from OpenCV provides a marked improvement on all platforms. In addition, we show that embedded platforms offer some possibility for extensive improvement in terms of efficiency compared to a fully featured workstation.

Unravelling the structure of matter on high-performance computers

International Nuclear Information System (INIS)

Kieu, T.D.; McKellar, B.H.J.

1992-11-01

The various phenomena and the different forms of matter in nature are believed to be the manifestation of only a handful set of fundamental building blocks-the elementary particles-which interact through the four fundamental forces. In the study of the structure of matter at this level one has to consider forces which are not sufficiently weak to be treated as small perturbations to the system, an example of which is the strong force that binds the nucleons together. High-performance computers, both vector and parallel machines, have facilitated the necessary non-perturbative treatments. The principles and the techniques of computer simulations applied to Quantum Chromodynamics are explained examples include the strong interactions, the calculation of the mass of nucleons and their decay rates. Some commercial and special-purpose high-performance machines for such calculations are also mentioned. 3 refs., 2 tabs

Usage of super high speed computer for clarification of complex phenomena

International Nuclear Information System (INIS)

Sekiguchi, Tomotsugu; Sato, Mitsuhisa; Nakata, Hideki; Tatebe, Osami; Takagi, Hiromitsu

1999-01-01

This study aims at construction of an efficient super high speed computer system application environment in response to parallel distributed system with easy transplantation to different computer system and different number by conducting research and development on super high speed computer application technology required for elucidation of complicated phenomenon in elucidation of complicated phenomenon of nuclear power field due to computed scientific method. In order to realize such environment, the Electrotechnical Laboratory has conducted development on Ninf, a network numerical information library. This Ninf system can supply a global network infrastructure for worldwide computing with high performance on further wide range distributed network (G.K.)

Parameters that affect parallel processing for computational electromagnetic simulation codes on high performance computing clusters

Science.gov (United States)

Moon, Hongsik

What is the impact of multicore and associated advanced technologies on computational software for science? Most researchers and students have multicore laptops or desktops for their research and they need computing power to run computational software packages. Computing power was initially derived from Central Processing Unit (CPU) clock speed. That changed when increases in clock speed became constrained by power requirements. Chip manufacturers turned to multicore CPU architectures and associated technological advancements to create the CPUs for the future. Most software applications benefited by the increased computing power the same way that increases in clock speed helped applications run faster. However, for Computational ElectroMagnetics (CEM) software developers, this change was not an obvious benefit - it appeared to be a detriment. Developers were challenged to find a way to correctly utilize the advancements in hardware so that their codes could benefit. The solution was parallelization and this dissertation details the investigation to address these challenges. Prior to multicore CPUs, advanced computer technologies were compared with the performance using benchmark software and the metric was FLoting-point Operations Per Seconds (FLOPS) which indicates system performance for scientific applications that make heavy use of floating-point calculations. Is FLOPS an effective metric for parallelized CEM simulation tools on new multicore system? Parallel CEM software needs to be benchmarked not only by FLOPS but also by the performance of other parameters related to type and utilization of the hardware, such as CPU, Random Access Memory (RAM), hard disk, network, etc. The codes need to be optimized for more than just FLOPs and new parameters must be included in benchmarking. In this dissertation, the parallel CEM software named High Order Basis Based Integral Equation Solver (HOBBIES) is introduced. This code was developed to address the needs of the

Performance of particle in cell methods on highly concurrent computational architectures

International Nuclear Information System (INIS)

Adams, M.F.; Ethier, S.; Wichmann, N.

2009-01-01

Particle in cell (PIC) methods are effective in computing Vlasov-Poisson system of equations used in simulations of magnetic fusion plasmas. PIC methods use grid based computations, for solving Poisson's equation or more generally Maxwell's equations, as well as Monte-Carlo type methods to sample the Vlasov equation. The presence of two types of discretizations, deterministic field solves and Monte-Carlo methods for the Vlasov equation, pose challenges in understanding and optimizing performance on today large scale computers which require high levels of concurrency. These challenges arises from the need to optimize two very different types of processes and the interactions between them. Modern cache based high-end computers have very deep memory hierarchies and high degrees of concurrency which must be utilized effectively to achieve good performance. The effective use of these machines requires maximizing concurrency by eliminating serial or redundant work and minimizing global communication. A related issue is minimizing the memory traffic between levels of the memory hierarchy because performance is often limited by the bandwidths and latencies of the memory system. This paper discusses some of the performance issues, particularly in regard to parallelism, of PIC methods. The gyrokinetic toroidal code (GTC) is used for these studies and a new radial grid decomposition is presented and evaluated. Scaling of the code is demonstrated on ITER sized plasmas with up to 16K Cray XT3/4 cores.

Performance of particle in cell methods on highly concurrent computational architectures

International Nuclear Information System (INIS)

Adams, M F; Ethier, S; Wichmann, N

2007-01-01

Particle in cell (PIC) methods are effective in computing Vlasov-Poisson system of equations used in simulations of magnetic fusion plasmas. PIC methods use grid based computations, for solving Poisson's equation or more generally Maxwell's equations, as well as Monte-Carlo type methods to sample the Vlasov equation. The presence of two types of discretizations, deterministic field solves and Monte-Carlo methods for the Vlasov equation, pose challenges in understanding and optimizing performance on today large scale computers which require high levels of concurrency. These challenges arises from the need to optimize two very different types of processes and the interactions between them. Modern cache based high-end computers have very deep memory hierarchies and high degrees of concurrency which must be utilized effectively to achieve good performance. The effective use of these machines requires maximizing concurrency by eliminating serial or redundant work and minimizing global communication. A related issue is minimizing the memory traffic between levels of the memory hierarchy because performance is often limited by the bandwidths and latencies of the memory system. This paper discusses some of the performance issues, particularly in regard to parallelism, of PIC methods. The gyrokinetic toroidal code (GTC) is used for these studies and a new radial grid decomposition is presented and evaluated. Scaling of the code is demonstrated on ITER sized plasmas with up to 16K Cray XT3/4 cores

5th International Conference on High Performance Scientific Computing

CERN Document Server

Hoang, Xuan; Rannacher, Rolf; Schlöder, Johannes

2014-01-01

This proceedings volume gathers a selection of papers presented at the Fifth International Conference on High Performance Scientific Computing, which took place in Hanoi on March 5-9, 2012. The conference was organized by the Institute of Mathematics of the Vietnam Academy of Science and Technology (VAST), the Interdisciplinary Center for Scientific Computing (IWR) of Heidelberg University, Ho Chi Minh City University of Technology, and the Vietnam Institute for Advanced Study in Mathematics. The contributions cover the broad interdisciplinary spectrum of scientific computing and present recent advances in theory, development of methods, and practical applications. Subjects covered include mathematical modeling; numerical simulation; methods for optimization and control; parallel computing; software development; and applications of scientific computing in physics, mechanics and biomechanics, material science, hydrology, chemistry, biology, biotechnology, medicine, sports, psychology, transport, logistics, com...

3rd International Conference on High Performance Scientific Computing

CERN Document Server

Kostina, Ekaterina; Phu, Hoang; Rannacher, Rolf

2008-01-01

This proceedings volume contains a selection of papers presented at the Third International Conference on High Performance Scientific Computing held at the Hanoi Institute of Mathematics, Vietnamese Academy of Science and Technology (VAST), March 6-10, 2006. The conference has been organized by the Hanoi Institute of Mathematics, Interdisciplinary Center for Scientific Computing (IWR), Heidelberg, and its International PhD Program ``Complex Processes: Modeling, Simulation and Optimization'', and Ho Chi Minh City University of Technology. The contributions cover the broad interdisciplinary spectrum of scientific computing and present recent advances in theory, development of methods, and applications in practice. Subjects covered are mathematical modelling, numerical simulation, methods for optimization and control, parallel computing, software development, applications of scientific computing in physics, chemistry, biology and mechanics, environmental and hydrology problems, transport, logistics and site loca...

6th International Conference on High Performance Scientific Computing

CERN Document Server

Phu, Hoang; Rannacher, Rolf; Schlöder, Johannes

2017-01-01

This proceedings volume highlights a selection of papers presented at the Sixth International Conference on High Performance Scientific Computing, which took place in Hanoi, Vietnam on March 16-20, 2015. The conference was jointly organized by the Heidelberg Institute of Theoretical Studies (HITS), the Institute of Mathematics of the Vietnam Academy of Science and Technology (VAST), the Interdisciplinary Center for Scientific Computing (IWR) at Heidelberg University, and the Vietnam Institute for Advanced Study in Mathematics, Ministry of Education The contributions cover a broad, interdisciplinary spectrum of scientific computing and showcase recent advances in theory, methods, and practical applications. Subjects covered numerical simulation, methods for optimization and control, parallel computing, and software development, as well as the applications of scientific computing in physics, mechanics, biomechanics and robotics, material science, hydrology, biotechnology, medicine, transport, scheduling, and in...

Distributed computer systems theory and practice

CERN Document Server

Zedan, H S M

2014-01-01

Distributed Computer Systems: Theory and Practice is a collection of papers dealing with the design and implementation of operating systems, including distributed systems, such as the amoeba system, argus, Andrew, and grapevine. One paper discusses the concepts and notations for concurrent programming, particularly language notation used in computer programming, synchronization methods, and also compares three classes of languages. Another paper explains load balancing or load redistribution to improve system performance, namely, static balancing and adaptive load balancing. For program effici

8th International Workshop on Parallel Tools for High Performance Computing

CERN Document Server

Gracia, José; Knüpfer, Andreas; Resch, Michael; Nagel, Wolfgang

2015-01-01

Numerical simulation and modelling using High Performance Computing has evolved into an established technique in academic and industrial research. At the same time, the High Performance Computing infrastructure is becoming ever more complex. For instance, most of the current top systems around the world use thousands of nodes in which classical CPUs are combined with accelerator cards in order to enhance their compute power and energy efficiency. This complexity can only be mastered with adequate development and optimization tools. Key topics addressed by these tools include parallelization on heterogeneous systems, performance optimization for CPUs and accelerators, debugging of increasingly complex scientific applications, and optimization of energy usage in the spirit of green IT. This book represents the proceedings of the 8th International Parallel Tools Workshop, held October 1-2, 2014 in Stuttgart, Germany – which is a forum to discuss the latest advancements in the parallel tools.

A High Performance COTS Based Computer Architecture

Science.gov (United States)

Patte, Mathieu; Grimoldi, Raoul; Trautner, Roland

2014-08-01

Using Commercial Off The Shelf (COTS) electronic components for space applications is a long standing idea. Indeed the difference in processing performance and energy efficiency between radiation hardened components and COTS components is so important that COTS components are very attractive for use in mass and power constrained systems. However using COTS components in space is not straightforward as one must account with the effects of the space environment on the COTS components behavior. In the frame of the ESA funded activity called High Performance COTS Based Computer, Airbus Defense and Space and its subcontractor OHB CGS have developed and prototyped a versatile COTS based architecture for high performance processing. The rest of the paper is organized as follows: in a first section we will start by recapitulating the interests and constraints of using COTS components for space applications; then we will briefly describe existing fault mitigation architectures and present our solution for fault mitigation based on a component called the SmartIO; in the last part of the paper we will describe the prototyping activities executed during the HiP CBC project.

High-performance computational fluid dynamics: a custom-code approach

International Nuclear Information System (INIS)

Fannon, James; Náraigh, Lennon Ó; Loiseau, Jean-Christophe; Valluri, Prashant; Bethune, Iain

2016-01-01

We introduce a modified and simplified version of the pre-existing fully parallelized three-dimensional Navier–Stokes flow solver known as TPLS. We demonstrate how the simplified version can be used as a pedagogical tool for the study of computational fluid dynamics (CFDs) and parallel computing. TPLS is at its heart a two-phase flow solver, and uses calls to a range of external libraries to accelerate its performance. However, in the present context we narrow the focus of the study to basic hydrodynamics and parallel computing techniques, and the code is therefore simplified and modified to simulate pressure-driven single-phase flow in a channel, using only relatively simple Fortran 90 code with MPI parallelization, but no calls to any other external libraries. The modified code is analysed in order to both validate its accuracy and investigate its scalability up to 1000 CPU cores. Simulations are performed for several benchmark cases in pressure-driven channel flow, including a turbulent simulation, wherein the turbulence is incorporated via the large-eddy simulation technique. The work may be of use to advanced undergraduate and graduate students as an introductory study in CFDs, while also providing insight for those interested in more general aspects of high-performance computing. (paper)

High-performance computational fluid dynamics: a custom-code approach

Science.gov (United States)

Fannon, James; Loiseau, Jean-Christophe; Valluri, Prashant; Bethune, Iain; Náraigh, Lennon Ó.

2016-07-01

We introduce a modified and simplified version of the pre-existing fully parallelized three-dimensional Navier-Stokes flow solver known as TPLS. We demonstrate how the simplified version can be used as a pedagogical tool for the study of computational fluid dynamics (CFDs) and parallel computing. TPLS is at its heart a two-phase flow solver, and uses calls to a range of external libraries to accelerate its performance. However, in the present context we narrow the focus of the study to basic hydrodynamics and parallel computing techniques, and the code is therefore simplified and modified to simulate pressure-driven single-phase flow in a channel, using only relatively simple Fortran 90 code with MPI parallelization, but no calls to any other external libraries. The modified code is analysed in order to both validate its accuracy and investigate its scalability up to 1000 CPU cores. Simulations are performed for several benchmark cases in pressure-driven channel flow, including a turbulent simulation, wherein the turbulence is incorporated via the large-eddy simulation technique. The work may be of use to advanced undergraduate and graduate students as an introductory study in CFDs, while also providing insight for those interested in more general aspects of high-performance computing.

Mixed-Language High-Performance Computing for Plasma Simulations

Directory of Open Access Journals (Sweden)

Quanming Lu

2003-01-01

Full Text Available Java is receiving increasing attention as the most popular platform for distributed computing. However, programmers are still reluctant to embrace Java as a tool for writing scientific and engineering applications due to its still noticeable performance drawbacks compared with other programming languages such as Fortran or C. In this paper, we present a hybrid Java/Fortran implementation of a parallel particle-in-cell (PIC algorithm for plasma simulations. In our approach, the time-consuming components of this application are designed and implemented as Fortran subroutines, while less calculation-intensive components usually involved in building the user interface are written in Java. The two types of software modules have been glued together using the Java native interface (JNI. Our mixed-language PIC code was tested and its performance compared with pure Java and Fortran versions of the same algorithm on a Sun E6500 SMP system and a Linux cluster of Pentium~III machines.

SCEAPI: A unified Restful Web API for High-Performance Computing

Science.gov (United States)

Rongqiang, Cao; Haili, Xiao; Shasha, Lu; Yining, Zhao; Xiaoning, Wang; Xuebin, Chi

2017-10-01

The development of scientific computing is increasingly moving to collaborative web and mobile applications. All these applications need high-quality programming interface for accessing heterogeneous computing resources consisting of clusters, grid computing or cloud computing. In this paper, we introduce our high-performance computing environment that integrates computing resources from 16 HPC centers across China. Then we present a bundle of web services called SCEAPI and describe how it can be used to access HPC resources with HTTP or HTTPs protocols. We discuss SCEAPI from several aspects including architecture, implementation and security, and address specific challenges in designing compatible interfaces and protecting sensitive data. We describe the functions of SCEAPI including authentication, file transfer and job management for creating, submitting and monitoring, and how to use SCEAPI in an easy-to-use way. Finally, we discuss how to exploit more HPC resources quickly for the ATLAS experiment by implementing the custom ARC compute element based on SCEAPI, and our work shows that SCEAPI is an easy-to-use and effective solution to extend opportunistic HPC resources.

Study of Solid State Drives performance in PROOF distributed analysis system

Science.gov (United States)

Panitkin, S. Y.; Ernst, M.; Petkus, R.; Rind, O.; Wenaus, T.

2010-04-01

Solid State Drives (SSD) is a promising storage technology for High Energy Physics parallel analysis farms. Its combination of low random access time and relatively high read speed is very well suited for situations where multiple jobs concurrently access data located on the same drive. It also has lower energy consumption and higher vibration tolerance than Hard Disk Drive (HDD) which makes it an attractive choice in many applications raging from personal laptops to large analysis farms. The Parallel ROOT Facility - PROOF is a distributed analysis system which allows to exploit inherent event level parallelism of high energy physics data. PROOF is especially efficient together with distributed local storage systems like Xrootd, when data are distributed over computing nodes. In such an architecture the local disk subsystem I/O performance becomes a critical factor, especially when computing nodes use multi-core CPUs. We will discuss our experience with SSDs in PROOF environment. We will compare performance of HDD with SSD in I/O intensive analysis scenarios. In particular we will discuss PROOF system performance scaling with a number of simultaneously running analysis jobs.

Multi-Language Programming Environments for High Performance Java Computing

OpenAIRE

Vladimir Getov; Paul Gray; Sava Mintchev; Vaidy Sunderam

1999-01-01

Recent developments in processor capabilities, software tools, programming languages and programming paradigms have brought about new approaches to high performance computing. A steadfast component of this dynamic evolution has been the scientific community’s reliance on established scientific packages. As a consequence, programmers of high‐performance applications are reluctant to embrace evolving languages such as Java. This paper describes the Java‐to‐C Interface (JCI) tool which provides ...

ATLAS Distributed Computing experience and performance during the LHC Run-2

CERN Document Server

AUTHOR|(INSPIRE)INSPIRE-00081160; The ATLAS collaboration

2017-01-01

ATLAS Distributed Computing during LHC Run-1 was challenged by steadily increasing computing, storage and network requirements. In addition, the complexity of processing task workflows and their associated data management requirements led to a new paradigm in the ATLAS computing model for Run-2, accompanied by extensive evolution and redesign of the workflow and data management systems. The new systems were put into production at the end of 2014, and gained robustness and maturity during 2015 data taking. ProdSys2, the new request and task interface; JEDI, the dynamic job execution engine developed as an extension to PanDA; and Rucio, the new data management system, form the core of Run-2 ATLAS distributed computing engine. One of the big changes for Run-2 was the adoption of the Derivation Framework, which moves the chaotic CPU and data intensive part of the user analysis into the centrally organized train production, delivering derived AOD datasets to user groups for final analysis. The effectiveness of the...

ATLAS Distributed Computing experience and performance during the LHC Run-2

CERN Document Server

AUTHOR|(INSPIRE)INSPIRE-00081160; The ATLAS collaboration

2016-01-01

ATLAS Distributed Computing during LHC Run-1 was challenged by steadily increasing computing, storage and network requirements. In addition, the complexity of processing task workflows and their associated data management requirements led to a new paradigm in the ATLAS computing model for Run-2, accompanied by extensive evolution and redesign of the workflow and data management systems. The new systems were put into production at the end of 2014, and gained robustness and maturity during 2015 data taking. ProdSys2, the new request and task interface; JEDI, the dynamic job execution engine developed as an extension to PanDA; and Rucio, the new data management system, form the core of the Run-2 ATLAS distributed computing engine. One of the big changes for Run-2 was the adoption of the Derivation Framework, which moves the chaotic CPU and data intensive part of the user analysis into the centrally organized train production, delivering derived AOD datasets to user groups for final analysis. The effectiveness of...

Analysis and Modeling of Social In uence in High Performance Computing Workloads

KAUST Repository

Zheng, Shuai

2011-06-01

High Performance Computing (HPC) is becoming a common tool in many research areas. Social influence (e.g., project collaboration) among increasing users of HPC systems creates bursty behavior in underlying workloads. This bursty behavior is increasingly common with the advent of grid computing and cloud computing. Mining the user bursty behavior is important for HPC workloads prediction and scheduling, which has direct impact on overall HPC computing performance. A representative work in this area is the Mixed User Group Model (MUGM), which clusters users according to the resource demand features of their submissions, such as duration time and parallelism. However, MUGM has some difficulties when implemented in real-world system. First, representing user behaviors by the features of their resource demand is usually difficult. Second, these features are not always available. Third, measuring the similarities among users is not a well-defined problem. In this work, we propose a Social Influence Model (SIM) to identify, analyze, and quantify the level of social influence across HPC users. The advantage of the SIM model is that it finds HPC communities by analyzing user job submission time, thereby avoiding the difficulties of MUGM. An offline algorithm and a fast-converging, computationally-efficient online learning algorithm for identifying social groups are proposed. Both offline and online algorithms are applied on several HPC and grid workloads, including Grid 5000, EGEE 2005 and 2007, and KAUST Supercomputing Lab (KSL) BGP data. From the experimental results, we show the existence of a social graph, which is characterized by a pattern of dominant users and followers. In order to evaluate the effectiveness of identified user groups, we show the pattern discovered by the offline algorithm follows a power-law distribution, which is consistent with those observed in mainstream social networks. We finally conclude the thesis and discuss future directions of our work.

Parallel computation for distributed parameter system-from vector processors to Adena computer

Energy Technology Data Exchange (ETDEWEB)

Nogi, T

1983-04-01

Research on advanced parallel hardware and software architectures for very high-speed computation deserves and needs more support and attention to fulfil its promise. Novel architectures for parallel processing are being made ready. Architectures for parallel processing can be roughly divided into two groups. One is a vector processor in which a single central processing unit involves multiple vector-arithmetic registers. The other is a processor array in which slave processors are connected to a host processor to perform parallel computation. In this review, the concept and data structure of the Adena (alternating-direction edition nexus array) architecture, which is conformable to distributed-parameter simulation algorithms, are described. 5 references.

FY 1993 Blue Book: Grand Challenges 1993: High Performance Computing and Communications

Data.gov (United States)

Networking and Information Technology Research and Development, Executive Office of the President — High performance computing and computer communications networks are becoming increasingly important to scientific advancement, economic competition, and national...

Use of the Web by a Distributed Research group Performing Distributed Computing

Science.gov (United States)

Burke, David A.; Peterkin, Robert E.

2001-06-01

A distributed research group that uses distributed computers faces a spectrum of challenges--some of which can be met by using various electronic means of communication. The particular challenge of our group involves three physically separated research entities. We have had to link two collaborating groups at AFRL and NRL together for software development, and the same AFRL group with a LANL group for software applications. We are developing and using a pair of general-purpose, portable, parallel, unsteady, plasma physics simulation codes. The first collaboration is centered around a formal weekly video teleconference on relatively inexpensive equipment that we have set up in convenient locations in our respective laboratories. The formal virtual meetings are augmented with informal virtual meetings as the need arises. Both collaborations share research data in a variety of forms on a secure URL that is set up behind the firewall at the AFRL. Of course, a computer-generated animation is a particularly efficient way of displaying results from time-dependent numerical simulations, so we generally like to post such animations (along with proper documentation) on our web page. In this presentation, we will discuss some of our accomplishments and disappointments.

A parallel calibration utility for WRF-Hydro on high performance computers

Science.gov (United States)

Wang, J.; Wang, C.; Kotamarthi, V. R.

2017-12-01

A successful modeling of complex hydrological processes comprises establishing an integrated hydrological model which simulates the hydrological processes in each water regime, calibrates and validates the model performance based on observation data, and estimates the uncertainties from different sources especially those associated with parameters. Such a model system requires large computing resources and often have to be run on High Performance Computers (HPC). The recently developed WRF-Hydro modeling system provides a significant advancement in the capability to simulate regional water cycles more completely. The WRF-Hydro model has a large range of parameters such as those in the input table files — GENPARM.TBL, SOILPARM.TBL and CHANPARM.TBL — and several distributed scaling factors such as OVROUGHRTFAC. These parameters affect the behavior and outputs of the model and thus may need to be calibrated against the observations in order to obtain a good modeling performance. Having a parameter calibration tool specifically for automate calibration and uncertainty estimates of WRF-Hydro model can provide significant convenience for the modeling community. In this study, we developed a customized tool using the parallel version of the model-independent parameter estimation and uncertainty analysis tool, PEST, to enabled it to run on HPC with PBS and SLURM workload manager and job scheduler. We also developed a series of PEST input file templates that are specifically for WRF-Hydro model calibration and uncertainty analysis. Here we will present a flood case study occurred in April 2013 over Midwest. The sensitivity and uncertainties are analyzed using the customized PEST tool we developed.

Distributed computing environments for future space control systems

Science.gov (United States)

Viallefont, Pierre

1993-01-01

The aim of this paper is to present the results of a CNES research project on distributed computing systems. The purpose of this research was to study the impact of the use of new computer technologies in the design and development of future space applications. The first part of this study was a state-of-the-art review of distributed computing systems. One of the interesting ideas arising from this review is the concept of a 'virtual computer' allowing the distributed hardware architecture to be hidden from a software application. The 'virtual computer' can improve system performance by adapting the best architecture (addition of computers) to the software application without having to modify its source code. This concept can also decrease the cost and obsolescence of the hardware architecture. In order to verify the feasibility of the 'virtual computer' concept, a prototype representative of a distributed space application is being developed independently of the hardware architecture.

Intelligent distributed computing

CERN Document Server

Thampi, Sabu

2015-01-01

This book contains a selection of refereed and revised papers of the Intelligent Distributed Computing Track originally presented at the third International Symposium on Intelligent Informatics (ISI-2014), September 24-27, 2014, Delhi, India.  The papers selected for this Track cover several Distributed Computing and related topics including Peer-to-Peer Networks, Cloud Computing, Mobile Clouds, Wireless Sensor Networks, and their applications.

Molecular simulation workflows as parallel algorithms: the execution engine of Copernicus, a distributed high-performance computing platform.

Science.gov (United States)

Pronk, Sander; Pouya, Iman; Lundborg, Magnus; Rotskoff, Grant; Wesén, Björn; Kasson, Peter M; Lindahl, Erik

2015-06-09

Computational chemistry and other simulation fields are critically dependent on computing resources, but few problems scale efficiently to the hundreds of thousands of processors available in current supercomputers-particularly for molecular dynamics. This has turned into a bottleneck as new hardware generations primarily provide more processing units rather than making individual units much faster, which simulation applications are addressing by increasingly focusing on sampling with algorithms such as free-energy perturbation, Markov state modeling, metadynamics, or milestoning. All these rely on combining results from multiple simulations into a single observation. They are potentially powerful approaches that aim to predict experimental observables directly, but this comes at the expense of added complexity in selecting sampling strategies and keeping track of dozens to thousands of simulations and their dependencies. Here, we describe how the distributed execution framework Copernicus allows the expression of such algorithms in generic workflows: dataflow programs. Because dataflow algorithms explicitly state dependencies of each constituent part, algorithms only need to be described on conceptual level, after which the execution is maximally parallel. The fully automated execution facilitates the optimization of these algorithms with adaptive sampling, where undersampled regions are automatically detected and targeted without user intervention. We show how several such algorithms can be formulated for computational chemistry problems, and how they are executed efficiently with many loosely coupled simulations using either distributed or parallel resources with Copernicus.

Homemade Buckeye-Pi: A Learning Many-Node Platform for High-Performance Parallel Computing

Science.gov (United States)

Amooie, M. A.; Moortgat, J.

2017-12-01

We report on the "Buckeye-Pi" cluster, the supercomputer developed in The Ohio State University School of Earth Sciences from 128 inexpensive Raspberry Pi (RPi) 3 Model B single-board computers. Each RPi is equipped with fast Quad Core 1.2GHz ARMv8 64bit processor, 1GB of RAM, and 32GB microSD card for local storage. Therefore, the cluster has a total RAM of 128GB that is distributed on the individual nodes and a flash capacity of 4TB with 512 processors, while it benefits from low power consumption, easy portability, and low total cost. The cluster uses the Message Passing Interface protocol to manage the communications between each node. These features render our platform the most powerful RPi supercomputer to date and suitable for educational applications in high-performance-computing (HPC) and handling of large datasets. In particular, we use the Buckeye-Pi to implement optimized parallel codes in our in-house simulator for subsurface media flows with the goal of achieving a massively-parallelized scalable code. We present benchmarking results for the computational performance across various number of RPi nodes. We believe our project could inspire scientists and students to consider the proposed unconventional cluster architecture as a mainstream and a feasible learning platform for challenging engineering and scientific problems.

Connecting Performance Analysis and Visualization to Advance Extreme Scale Computing

Energy Technology Data Exchange (ETDEWEB)

Bremer, Peer-Timo [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Mohr, Bernd [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Schulz, Martin [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Pasccci, Valerio [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Gamblin, Todd [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Brunst, Holger [Dresden Univ. of Technology (Germany)

2015-07-29

The characterization, modeling, analysis, and tuning of software performance has been a central topic in High Performance Computing (HPC) since its early beginnings. The overall goal is to make HPC software run faster on particular hardware, either through better scheduling, on-node resource utilization, or more efficient distributed communication.

High Performance Computing - Power Application Programming Interface Specification.

Energy Technology Data Exchange (ETDEWEB)

Laros, James H.,; Kelly, Suzanne M.; Pedretti, Kevin; Grant, Ryan; Olivier, Stephen Lecler; Levenhagen, Michael J.; DeBonis, David

2014-08-01

Measuring and controlling the power and energy consumption of high performance computing systems by various components in the software stack is an active research area [13, 3, 5, 10, 4, 21, 19, 16, 7, 17, 20, 18, 11, 1, 6, 14, 12]. Implementations in lower level software layers are beginning to emerge in some production systems, which is very welcome. To be most effective, a portable interface to measurement and control features would significantly facilitate participation by all levels of the software stack. We present a proposal for a standard power Application Programming Interface (API) that endeavors to cover the entire software space, from generic hardware interfaces to the input from the computer facility manager.

Nuclear forces and high-performance computing: The perfect match

International Nuclear Information System (INIS)

Luu, T; Walker-Loud, A

2009-01-01

High-performance computing is now enabling the calculation of certain hadronic interaction parameters directly from Quantum Chromodynamics, the quantum field theory that governs the behavior of quarks and gluons and is ultimately responsible for the nuclear strong force. In this paper we briefly describe the state of the field and show how other aspects of hadronic interactions will be ascertained in the near future. We give estimates of computational requirements needed to obtain these goals, and outline a procedure for incorporating these results into the broader nuclear physics community.

Final Technical Report: Integrated Distribution-Transmission Analysis for Very High Penetration Solar PV

Energy Technology Data Exchange (ETDEWEB)

Palmintier, Bryan [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Hale, Elaine [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Hansen, Timothy M. [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Jones, Wesley [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Biagioni, David [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Baker, Kyri [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Wu, Hongyu [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Giraldez, Julieta [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Sorensen, Harry [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Lunacek, Monte [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Merket, Noel [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Jorgenson, Jennie [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States)); Hodge, Bri-Mathias [NREL (National Renewable Energy Laboratory (NREL), Golden, CO (United States))

2016-01-29

Transmission and distribution simulations have historically been conducted separately, echoing their division in grid operations and planning while avoiding inherent computational challenges. Today, however, rapid growth in distributed energy resources (DERs)--including distributed generation from solar photovoltaics (DGPV)--requires understanding the unprecedented interactions between distribution and transmission. To capture these interactions, especially for high-penetration DGPV scenarios, this research project developed a first-of-its-kind, high performance computer (HPC) based, integrated transmission-distribution tool, the Integrated Grid Modeling System (IGMS). The tool was then used in initial explorations of system-wide operational interactions of high-penetration DGPV.

NINJA: Java for High Performance Numerical Computing

Directory of Open Access Journals (Sweden)

José E. Moreira

2002-01-01

Full Text Available When Java was first introduced, there was a perception that its many benefits came at a significant performance cost. In the particularly performance-sensitive field of numerical computing, initial measurements indicated a hundred-fold performance disadvantage between Java and more established languages such as Fortran and C. Although much progress has been made, and Java now can be competitive with C/C++ in many important situations, significant performance challenges remain. Existing Java virtual machines are not yet capable of performing the advanced loop transformations and automatic parallelization that are now common in state-of-the-art Fortran compilers. Java also has difficulties in implementing complex arithmetic efficiently. These performance deficiencies can be attacked with a combination of class libraries (packages, in Java that implement truly multidimensional arrays and complex numbers, and new compiler techniques that exploit the properties of these class libraries to enable other, more conventional, optimizations. Two compiler techniques, versioning and semantic expansion, can be leveraged to allow fully automatic optimization and parallelization of Java code. Our measurements with the NINJA prototype Java environment show that Java can be competitive in performance with highly optimized and tuned Fortran code.

High performance parallel computing of flows in complex geometries: II. Applications

International Nuclear Information System (INIS)

Gourdain, N; Gicquel, L; Staffelbach, G; Vermorel, O; Duchaine, F; Boussuge, J-F; Poinsot, T

2009-01-01

Present regulations in terms of pollutant emissions, noise and economical constraints, require new approaches and designs in the fields of energy supply and transportation. It is now well established that the next breakthrough will come from a better understanding of unsteady flow effects and by considering the entire system and not only isolated components. However, these aspects are still not well taken into account by the numerical approaches or understood whatever the design stage considered. The main challenge is essentially due to the computational requirements inferred by such complex systems if it is to be simulated by use of supercomputers. This paper shows how new challenges can be addressed by using parallel computing platforms for distinct elements of a more complex systems as encountered in aeronautical applications. Based on numerical simulations performed with modern aerodynamic and reactive flow solvers, this work underlines the interest of high-performance computing for solving flow in complex industrial configurations such as aircrafts, combustion chambers and turbomachines. Performance indicators related to parallel computing efficiency are presented, showing that establishing fair criterions is a difficult task for complex industrial applications. Examples of numerical simulations performed in industrial systems are also described with a particular interest for the computational time and the potential design improvements obtained with high-fidelity and multi-physics computing methods. These simulations use either unsteady Reynolds-averaged Navier-Stokes methods or large eddy simulation and deal with turbulent unsteady flows, such as coupled flow phenomena (thermo-acoustic instabilities, buffet, etc). Some examples of the difficulties with grid generation and data analysis are also presented when dealing with these complex industrial applications.

Prototyping and Simulating Parallel, Distributed Computations with VISA

National Research Council Canada - National Science Library

Demeure, Isabelle M; Nutt, Gary J

1989-01-01

...] to support the design, prototyping, and simulation of parallel, distributed computations. In particular, VISA is meant to guide the choice of partitioning and communication strategies for such computations, based on their performance...

RAPPORT: running scientific high-performance computing applications on the cloud.

Science.gov (United States)

Cohen, Jeremy; Filippis, Ioannis; Woodbridge, Mark; Bauer, Daniela; Hong, Neil Chue; Jackson, Mike; Butcher, Sarah; Colling, David; Darlington, John; Fuchs, Brian; Harvey, Matt

2013-01-28

Cloud computing infrastructure is now widely used in many domains, but one area where there has been more limited adoption is research computing, in particular for running scientific high-performance computing (HPC) software. The Robust Application Porting for HPC in the Cloud (RAPPORT) project took advantage of existing links between computing researchers and application scientists in the fields of bioinformatics, high-energy physics (HEP) and digital humanities, to investigate running a set of scientific HPC applications from these domains on cloud infrastructure. In this paper, we focus on the bioinformatics and HEP domains, describing the applications and target cloud platforms. We conclude that, while there are many factors that need consideration, there is no fundamental impediment to the use of cloud infrastructure for running many types of HPC applications and, in some cases, there is potential for researchers to benefit significantly from the flexibility offered by cloud platforms.

Computation of the efficiency distribution of a multichannel focusing collimator

International Nuclear Information System (INIS)

Balasubramanian, A.; Venkateswaran, T.V.

1977-01-01

This article describes two computer methods of calculating the point source efficiency distribution functions of a focusing collimator with round tapered holes. The first method which computes only the geometric efficiency distribution is adequate for low energy collimators while the second method which computes both geometric and penetration efficiencies can be made use of for medium and high energy collimators. The scatter contribution to the efficiency is not taken into account. In the first method the efficiency distribution of a single cone of the collimator is obtained and the data are used for computing the distribution of the whole collimator. For high energy collimator the entire detector region is imagined to be divided into elemental areas. Efficiency of the elemental area is computed after suitably weighting for the penetration within the collimator septa, which is determined by three dimensional geometric techniques. The method of computing the line source efficiency distribution from point source distribution is also explained. The formulations have been tested by computing the efficiency distribution of several commercial collimators and collimators fabricated by us. (Auth.)

FY 1995 Blue Book: High Performance Computing and Communications: Technology for the National Information Infrastructure

Data.gov (United States)

Networking and Information Technology Research and Development, Executive Office of the President — The Federal High Performance Computing and Communications HPCC Program was created to accelerate the development of future generations of high performance computers...

High performance distributed objects in large hadron collider experiments

International Nuclear Information System (INIS)

Gutleber, J.

1999-11-01

This dissertation demonstrates how object-oriented technology can support the development of software that has to meet the requirements of high performance distributed data acquisition systems. The environment for this work is a system under planning for the Compact Muon Solenoid experiment at CERN that shall start its operation in the year 2005. The long operational phase of the experiment together with a tight and puzzling interaction with custom devices make the quest for an evolvable architecture that exhibits a high level of abstraction the driving issue. The question arises if an existing approach already fits our needs. The presented work casts light on these problems and as a result comprises the following novel contributions: - Application of object technology at hardware/software boundary. Software components at this level must be characterised by high efficiency and extensibility at the same time. - Identification of limitations when deploying commercial-off-the-shelf middleware for distributed object-oriented computing. - Capturing of software component properties in an efficiency model for ease of comparison and improvement. - Proof of feasibility that the encountered deficiencies in middleware can be avoided and that with the use of software components the imposed requirements can be met. - Design and implementation of an on-line software control system that allows to take into account the ever evolving requirements by avoiding hardwired policies. We conclude that state-of-the-art middleware cannot meet the required efficiency of the planned data acquisition system. Although new tool generations already provide a certain degree of configurability, the obligation to follow standards specifications does not allow the necessary optimisations. We identified the major limiting factors and argue that a custom solution following a component model with narrow interfaces can satisfy our requirements. This approach has been adopted for the current design

Distributed control software of high-performance control-loop algorithm

CERN Document Server

Blanc, D

1999-01-01

The majority of industrial cooling and ventilation plants require the control of complex processes. All these processes are highly important for the operation of the machines. The stability and reliability of these processes are leading factors identifying the quality of the service provided. The control system architecture and software structure, as well, are required to have high dynamical performance and robust behaviour. The intelligent systems based on PID or RST controllers are used for their high level of stability and accuracy. The design and tuning of these complex controllers require the dynamic model of the plant to be known (generally obtained by identification) and the desired performance of the various control loops to be specified for achieving good performances. The concept of having a distributed control algorithm software provides full automation facilities with well-adapted functionality and good performances, giving methodology, means and tools to master the dynamic process optimization an...

Human Computer Music Performance

OpenAIRE

Dannenberg, Roger B.

2012-01-01

Human Computer Music Performance (HCMP) is the study of music performance by live human performers and real-time computer-based performers. One goal of HCMP is to create a highly autonomous artificial performer that can fill the role of a human, especially in a popular music setting. This will require advances in automated music listening and understanding, new representations for music, techniques for music synchronization, real-time human-computer communication, music generation, sound synt...

The high performance cluster computing system for BES offline data analysis

International Nuclear Information System (INIS)

Sun Yongzhao; Xu Dong; Zhang Shaoqiang; Yang Ting

2004-01-01

A high performance cluster computing system (EPCfarm) is introduced, which used for BES offline data analysis. The setup and the characteristics of the hardware and software of EPCfarm are described. The PBS, a queue management package, and the performance of EPCfarm is presented also. (authors)

HIGH-PERFORMANCE COMPUTING FOR THE STUDY OF EARTH AND ENVIRONMENTAL SCIENCE MATERIALS USING SYNCHROTRON X-RAY COMPUTED MICROTOMOGRAPHY

International Nuclear Information System (INIS)

FENG, H.; JONES, K.W.; MCGUIGAN, M.; SMITH, G.J.; SPILETIC, J.

2001-01-01

Synchrotron x-ray computed microtomography (CMT) is a non-destructive method for examination of rock, soil, and other types of samples studied in the earth and environmental sciences. The high x-ray intensities of the synchrotron source make possible the acquisition of tomographic volumes at a high rate that requires the application of high-performance computing techniques for data reconstruction to produce the three-dimensional volumes, for their visualization, and for data analysis. These problems are exacerbated by the need to share information between collaborators at widely separated locations over both local and tide-area networks. A summary of the CMT technique and examples of applications are given here together with a discussion of the applications of high-performance computing methods to improve the experimental techniques and analysis of the data

HIGH-PERFORMANCE COMPUTING FOR THE STUDY OF EARTH AND ENVIRONMENTAL SCIENCE MATERIALS USING SYNCHROTRON X-RAY COMPUTED MICROTOMOGRAPHY.

Energy Technology Data Exchange (ETDEWEB)

FENG,H.; JONES,K.W.; MCGUIGAN,M.; SMITH,G.J.; SPILETIC,J.

2001-10-12

Synchrotron x-ray computed microtomography (CMT) is a non-destructive method for examination of rock, soil, and other types of samples studied in the earth and environmental sciences. The high x-ray intensities of the synchrotron source make possible the acquisition of tomographic volumes at a high rate that requires the application of high-performance computing techniques for data reconstruction to produce the three-dimensional volumes, for their visualization, and for data analysis. These problems are exacerbated by the need to share information between collaborators at widely separated locations over both local and tide-area networks. A summary of the CMT technique and examples of applications are given here together with a discussion of the applications of high-performance computing methods to improve the experimental techniques and analysis of the data.

Cloud Computing as Evolution of Distributed Computing – A Case Study for SlapOS Distributed Cloud Computing Platform

Directory of Open Access Journals (Sweden)

George SUCIU

2013-01-01

Full Text Available The cloud computing paradigm has been defined from several points of view, the main two directions being either as an evolution of the grid and distributed computing paradigm, or, on the contrary, as a disruptive revolution in the classical paradigms of operating systems, network layers and web applications. This paper presents a distributed cloud computing platform called SlapOS, which unifies technologies and communication protocols into a new technology model for offering any application as a service. Both cloud and distributed computing can be efficient methods for optimizing resources that are aggregated from a grid of standard PCs hosted in homes, offices and small data centers. The paper fills a gap in the existing distributed computing literature by providing a distributed cloud computing model which can be applied for deploying various applications.

Thinking processes used by high-performing students in a computer programming task

Directory of Open Access Journals (Sweden)

Marietjie Havenga

2011-07-01

Full Text Available Computer programmers must be able to understand programming source code and write programs that execute complex tasks to solve real-world problems. This article is a trans- disciplinary study at the intersection of computer programming, education and psychology. It outlines the role of mental processes in the process of programming and indicates how successful thinking processes can support computer science students in writing correct and well-defined programs. A mixed methods approach was used to better understand the thinking activities and programming processes of participating students. Data collection involved both computer programs and students’ reflective thinking processes recorded in their journals. This enabled analysis of psychological dimensions of participants’ thinking processes and their problem-solving activities as they considered a programming problem. Findings indicate that the cognitive, reflective and psychological processes used by high-performing programmers contributed to their success in solving a complex programming problem. Based on the thinking processes of high performers, we propose a model of integrated thinking processes, which can support computer programming students. Keywords: Computer programming, education, mixed methods research, thinking processes.  Disciplines: Computer programming, education, psychology

ATLAS Distributed Computing: Experience and Evolution

CERN Document Server

Nairz, A; The ATLAS collaboration

2013-01-01

The ATLAS experiment has just concluded its first running period which commenced in 2010. After two years of remarkable performance from the LHC and ATLAS, the experiment has accumulated more than 25 fb-1 of data. The total volume of beam and simulated data products exceeds 100 PB distributed across more than 150 computing centers around the world, managed by the experiment's distributed data management system. These sites have provided up to 150,000 computing cores to ATLAS's global production and analysis processing system, enabling a rich physics program including the discovery of the Higgs-like boson in 2012. The wealth of accumulated experience in global data-intensive computing at this massive scale, and the considerably more challenging requirements of LHC computing from 2014 when the LHC resumes operation, are driving a comprehensive design and development cycle to prepare a revised computing model together with data processing and management systems able to meet the demands of higher trigger rates, e...

ATLAS distributed computing: experience and evolution

CERN Document Server

Nairz, A; The ATLAS collaboration

2014-01-01

The ATLAS experiment has just concluded its first running period which commenced in 2010. After two years of remarkable performance from the LHC and ATLAS, the experiment has accumulated more than 25/fb of data. The total volume of beam and simulated data products exceeds 100~PB distributed across more than 150 computing centres around the world, managed by the experiment's distributed data management system. These sites have provided up to 150,000 computing cores to ATLAS's global production and analysis processing system, enabling a rich physics programme including the discovery of the Higgs-like boson in 2012. The wealth of accumulated experience in global data-intensive computing at this massive scale, and the considerably more challenging requirements of LHC computing from 2015 when the LHC resumes operation, are driving a comprehensive design and development cycle to prepare a revised computing model together with data processing and management systems able to meet the demands of higher trigger rates, e...

Spatial Processing of Urban Acoustic Wave Fields from High-Performance Computations

National Research Council Canada - National Science Library

Ketcham, Stephen A; Wilson, D. K; Cudney, Harley H; Parker, Michael W

2007-01-01

.... The objective of this work is to develop spatial processing techniques for acoustic wave propagation data from three-dimensional high-performance computations to quantify scattering due to urban...

Proceedings of workshop on distributed computing and network

International Nuclear Information System (INIS)

Abe, F.; Yuasa, F.

1993-02-01

'Distributed Computing and Network' is one of hot topics in the field of computing. Recent progress in the computer technology is providing new paradigm for computing even in High Energy Physics. Particularly the workstation based computer system is opening new active field of computer application to sciences. The major topics discussed in this symposium are distributed computing and wide area research network for domestic and international link. The two days symposium provided so enough topics to foresee the next direction of our computing environment. 70 people have got together to discuss on these interesting thema as well as information exchange on the computer technologies. (J.P.N.)

High performance simulation for the Silva project using the tera computer

International Nuclear Information System (INIS)

Bergeaud, V.; La Hargue, J.P.; Mougery, F.; Boulet, M.; Scheurer, B.; Le Fur, J.F.; Comte, M.; Benisti, D.; Lamare, J. de; Petit, A.

2003-01-01

In the context of the SILVA Project (Atomic Vapor Laser Isotope Separation), numerical simulation of the plant scale propagation of laser beams through uranium vapour was a great challenge. The PRODIGE code has been developed to achieve this goal. Here we focus on the task of achieving high performance simulation on the TERA computer. We describe the main issues for optimizing the parallelization of the PRODIGE code on TERA. Thus, we discuss advantages and drawbacks of the implemented diagonal parallelization scheme. As a consequence, it has been found fruitful to fit out the code in three aspects: memory allocation, MPI communications and interconnection network bandwidth usage. We stress out the interest of MPI/IO in this context and the benefit obtained for production computations on TERA. Finally, we shall illustrate our developments. We indicate some performance measurements reflecting the good parallelization properties of PRODIGE on the TERA computer. The code is currently used for demonstrating the feasibility of the laser propagation at a plant enrichment level and for preparing the 2003 Menphis experiment. We conclude by emphasizing the contribution of high performance TERA simulation to the project. (authors)

High performance simulation for the Silva project using the tera computer

Energy Technology Data Exchange (ETDEWEB)

Bergeaud, V.; La Hargue, J.P.; Mougery, F. [CS Communication and Systemes, 92 - Clamart (France); Boulet, M.; Scheurer, B. [CEA Bruyeres-le-Chatel, 91 - Bruyeres-le-Chatel (France); Le Fur, J.F.; Comte, M.; Benisti, D.; Lamare, J. de; Petit, A. [CEA Saclay, 91 - Gif sur Yvette (France)

2003-07-01

In the context of the SILVA Project (Atomic Vapor Laser Isotope Separation), numerical simulation of the plant scale propagation of laser beams through uranium vapour was a great challenge. The PRODIGE code has been developed to achieve this goal. Here we focus on the task of achieving high performance simulation on the TERA computer. We describe the main issues for optimizing the parallelization of the PRODIGE code on TERA. Thus, we discuss advantages and drawbacks of the implemented diagonal parallelization scheme. As a consequence, it has been found fruitful to fit out the code in three aspects: memory allocation, MPI communications and interconnection network bandwidth usage. We stress out the interest of MPI/IO in this context and the benefit obtained for production computations on TERA. Finally, we shall illustrate our developments. We indicate some performance measurements reflecting the good parallelization properties of PRODIGE on the TERA computer. The code is currently used for demonstrating the feasibility of the laser propagation at a plant enrichment level and for preparing the 2003 Menphis experiment. We conclude by emphasizing the contribution of high performance TERA simulation to the project. (authors)

Continuous Distributed Top-k Monitoring over High-Speed Rail Data Stream in Cloud Computing Environment

Directory of Open Access Journals (Sweden)

Hanning Wang

2013-01-01

Full Text Available In the environment of cloud computing, real-time mass data about high-speed rail which is based on the intense monitoring of large scale perceived equipment provides strong support for the safety and maintenance of high-speed rail. In this paper, we focus on the Top-k algorithm of continuous distribution based on Multisource distributed data stream for high-speed rail monitoring. Specifically, we formalized Top-k monitoring model of high-speed rail and proposed DTMR that is the Top-k monitoring algorithm with random, continuous, or strictly monotone aggregation functions. The DTMR was proved to be valid by lots of experiments.

Scalability of DL_POLY on High Performance Computing Platform

Directory of Open Access Journals (Sweden)

Mabule Samuel Mabakane

2017-12-01

Full Text Available This paper presents a case study on the scalability of several versions of the molecular dynamics code (DL_POLY performed on South Africa‘s Centre for High Performance Computing e1350 IBM Linux cluster, Sun system and Lengau supercomputers. Within this study different problem sizes were designed and the same chosen systems were employed in order to test the performance of DL_POLY using weak and strong scalability. It was found that the speed-up results for the small systems were better than large systems on both Ethernet and Infiniband network. However, simulations of large systems in DL_POLY performed well using Infiniband network on Lengau cluster as compared to e1350 and Sun supercomputer.

Towards a Scalable and Adaptive Application Support Platform for Large-Scale Distributed E-Sciences in High-Performance Network Environments

Energy Technology Data Exchange (ETDEWEB)

Wu, Chase Qishi [New Jersey Inst. of Technology, Newark, NJ (United States); Univ. of Memphis, TN (United States); Zhu, Michelle Mengxia [Southern Illinois Univ., Carbondale, IL (United States)

2016-06-06

The advent of large-scale collaborative scientific applications has demonstrated the potential for broad scientific communities to pool globally distributed resources to produce unprecedented data acquisition, movement, and analysis. System resources including supercomputers, data repositories, computing facilities, network infrastructures, storage systems, and display devices have been increasingly deployed at national laboratories and academic institutes. These resources are typically shared by large communities of users over Internet or dedicated networks and hence exhibit an inherent dynamic nature in their availability, accessibility, capacity, and stability. Scientific applications using either experimental facilities or computation-based simulations with various physical, chemical, climatic, and biological models feature diverse scientific workflows as simple as linear pipelines or as complex as a directed acyclic graphs, which must be executed and supported over wide-area networks with massively distributed resources. Application users oftentimes need to manually configure their computing tasks over networks in an ad hoc manner, hence significantly limiting the productivity of scientists and constraining the utilization of resources. The success of these large-scale distributed applications requires a highly adaptive and massively scalable workflow platform that provides automated and optimized computing and networking services. This project is to design and develop a generic Scientific Workflow Automation and Management Platform (SWAMP), which contains a web-based user interface specially tailored for a target application, a set of user libraries, and several easy-to-use computing and networking toolkits for application scientists to conveniently assemble, execute, monitor, and control complex computing workflows in heterogeneous high-performance network environments. SWAMP will enable the automation and management of the entire process of scientific

Can We Build a Truly High Performance Computer Which is Flexible and Transparent?

KAUST Repository

Rojas, Jhonathan Prieto

2013-09-10

State-of-the art computers need high performance transistors, which consume ultra-low power resulting in longer battery lifetime. Billions of transistors are integrated neatly using matured silicon fabrication process to maintain the performance per cost advantage. In that context, low-cost mono-crystalline bulk silicon (100) based high performance transistors are considered as the heart of today\\'s computers. One limitation is silicon\\'s rigidity and brittleness. Here we show a generic batch process to convert high performance silicon electronics into flexible and semi-transparent one while retaining its performance, process compatibility, integration density and cost. We demonstrate high-k/metal gate stack based p-type metal oxide semiconductor field effect transistors on 4 inch silicon fabric released from bulk silicon (100) wafers with sub-threshold swing of 80 mV dec(-1) and on/off ratio of near 10(4) within 10% device uniformity with a minimum bending radius of 5 mm and an average transmittance of similar to 7% in the visible spectrum.

Analysis and modeling of social influence in high performance computing workloads

KAUST Repository

Zheng, Shuai; Shae, Zon Yin; Zhang, Xiangliang; Jamjoom, Hani T.; Fong, Liana

2011-01-01

Social influence among users (e.g., collaboration on a project) creates bursty behavior in the underlying high performance computing (HPC) workloads. Using representative HPC and cluster workload logs, this paper identifies, analyzes, and quantifies

Topic 14+16: High-performance and scientific applications and extreme-scale computing (Introduction)

KAUST Repository

Downes, Turlough P.

2013-01-01

As our understanding of the world around us increases it becomes more challenging to make use of what we already know, and to increase our understanding still further. Computational modeling and simulation have become critical tools in addressing this challenge. The requirements of high-resolution, accurate modeling have outstripped the ability of desktop computers and even small clusters to provide the necessary compute power. Many applications in the scientific and engineering domains now need very large amounts of compute time, while other applications, particularly in the life sciences, frequently have large data I/O requirements. There is thus a growing need for a range of high performance applications which can utilize parallel compute systems effectively, which have efficient data handling strategies and which have the capacity to utilise current and future systems. The High Performance and Scientific Applications topic aims to highlight recent progress in the use of advanced computing and algorithms to address the varied, complex and increasing challenges of modern research throughout both the "hard" and "soft" sciences. This necessitates being able to use large numbers of compute nodes, many of which are equipped with accelerators, and to deal with difficult I/O requirements. © 2013 Springer-Verlag.

Bringing high-performance computing to the biologist's workbench: approaches, applications, and challenges

International Nuclear Information System (INIS)

Oehmen, C S; Cannon, W R

2008-01-01

Data-intensive and high-performance computing are poised to significantly impact the future of biological research which is increasingly driven by the prevalence of high-throughput experimental methodologies for genome sequencing, transcriptomics, proteomics, and other areas. Large centers such as NIH's National Center for Biotechnology Information, The Institute for Genomic Research, and the DOE's Joint Genome Institute) have made extensive use of multiprocessor architectures to deal with some of the challenges of processing, storing and curating exponentially growing genomic and proteomic datasets, thus enabling users to rapidly access a growing public data source, as well as use analysis tools transparently on high-performance computing resources. Applying this computational power to single-investigator analysis, however, often relies on users to provide their own computational resources, forcing them to endure the learning curve of porting, building, and running software on multiprocessor architectures. Solving the next generation of large-scale biology challenges using multiprocessor machines-from small clusters to emerging petascale machines-can most practically be realized if this learning curve can be minimized through a combination of workflow management, data management and resource allocation as well as intuitive interfaces and compatibility with existing common data formats

A performance model for the communication in fast multipole methods on high-performance computing platforms

KAUST Repository

Ibeid, Huda; Yokota, Rio; Keyes, David E.

2016-01-01

model and the actual communication time on four high-performance computing (HPC) systems, when latency, bandwidth, network topology, and multicore penalties are all taken into account. To our knowledge, this is the first formal characterization

User-Defined Data Distributions in High-Level Programming Languages

Science.gov (United States)

Diaconescu, Roxana E.; Zima, Hans P.

2006-01-01

One of the characteristic features of today s high performance computing systems is a physically distributed memory. Efficient management of locality is essential for meeting key performance requirements for these architectures. The standard technique for dealing with this issue has involved the extension of traditional sequential programming languages with explicit message passing, in the context of a processor-centric view of parallel computation. This has resulted in complex and error-prone assembly-style codes in which algorithms and communication are inextricably interwoven. This paper presents a high-level approach to the design and implementation of data distributions. Our work is motivated by the need to improve the current parallel programming methodology by introducing a paradigm supporting the development of efficient and reusable parallel code. This approach is currently being implemented in the context of a new programming language called Chapel, which is designed in the HPCS project Cascade.

Overview of Parallel Platforms for Common High Performance Computing

Directory of Open Access Journals (Sweden)

T. Fryza

2012-04-01

Full Text Available The paper deals with various parallel platforms used for high performance computing in the signal processing domain. More precisely, the methods exploiting the multicores central processing units such as message passing interface and OpenMP are taken into account. The properties of the programming methods are experimentally proved in the application of a fast Fourier transform and a discrete cosine transform and they are compared with the possibilities of MATLAB's built-in functions and Texas Instruments digital signal processors with very long instruction word architectures. New FFT and DCT implementations were proposed and tested. The implementation phase was compared with CPU based computing methods and with possibilities of the Texas Instruments digital signal processing library on C6747 floating-point DSPs. The optimal combination of computing methods in the signal processing domain and new, fast routines' implementation is proposed as well.

Distributed computing for real-time petroleum reservoir monitoring

Energy Technology Data Exchange (ETDEWEB)

Ayodele, O. R. [University of Alberta, Edmonton, AB (Canada)

2004-05-01

Computer software architecture is presented to illustrate how the concept of distributed computing can be applied to real-time reservoir monitoring processes, permitting the continuous monitoring of the dynamic behaviour of petroleum reservoirs at much shorter intervals. The paper describes the fundamental technologies driving distributed computing, namely Java 2 Platform Enterprise edition (J2EE) by Sun Microsystems, and the Microsoft Dot-Net (Microsoft.Net) initiative, and explains the challenges involved in distributed computing. These are: (1) availability of permanently placed downhole equipment to acquire and transmit seismic data; (2) availability of high bandwidth to transmit the data; (3) security considerations; (4) adaptation of existing legacy codes to run on networks as downloads on demand; and (5) credibility issues concerning data security over the Internet. Other applications of distributed computing in the petroleum industry are also considered, specifically MWD, LWD and SWD (measurement-while-drilling, logging-while-drilling, and simulation-while-drilling), and drill-string vibration monitoring. 23 refs., 1 fig.

10th International Workshop on Parallel Tools for High Performance Computing

CERN Document Server

Gracia, José; Hilbrich, Tobias; Knüpfer, Andreas; Resch, Michael; Nagel, Wolfgang

2017-01-01

This book presents the proceedings of the 10th International Parallel Tools Workshop, held October 4-5, 2016 in Stuttgart, Germany – a forum to discuss the latest advances in parallel tools. High-performance computing plays an increasingly important role for numerical simulation and modelling in academic and industrial research. At the same time, using large-scale parallel systems efficiently is becoming more difficult. A number of tools addressing parallel program development and analysis have emerged from the high-performance computing community over the last decade, and what may have started as collection of small helper script has now matured to production-grade frameworks. Powerful user interfaces and an extensive body of documentation allow easy usage by non-specialists.

ATLAS distributed computing: experience and evolution

International Nuclear Information System (INIS)

Nairz, A

2014-01-01

The ATLAS experiment has just concluded its first running period which commenced in 2010. After two years of remarkable performance from the LHC and ATLAS, the experiment has accumulated more than 25 fb −1 of data. The total volume of beam and simulated data products exceeds 100 PB distributed across more than 150 computing centres around the world, managed by the experiment's distributed data management system. These sites have provided up to 150,000 computing cores to ATLAS's global production and analysis processing system, enabling a rich physics programme including the discovery of the Higgs-like boson in 2012. The wealth of accumulated experience in global data-intensive computing at this massive scale, and the considerably more challenging requirements of LHC computing from 2015 when the LHC resumes operation, are driving a comprehensive design and development cycle to prepare a revised computing model together with data processing and management systems able to meet the demands of higher trigger rates, energies and event complexities. An essential requirement will be the efficient utilisation of current and future processor technologies as well as a broad range of computing platforms, including supercomputing and cloud resources. We will report on experience gained thus far and our progress in preparing ATLAS computing for the future

Intelligent Distributed Computing VI : Proceedings of the 6th International Symposium on Intelligent Distributed Computing

CERN Document Server

Badica, Costin; Malgeri, Michele; Unland, Rainer

2013-01-01

This book represents the combined peer-reviewed proceedings of the Sixth International Symposium on Intelligent Distributed Computing -- IDC~2012, of the International Workshop on Agents for Cloud -- A4C~2012 and of the Fourth International Workshop on Multi-Agent Systems Technology and Semantics -- MASTS~2012. All the events were held in Calabria, Italy during September 24-26, 2012. The 37 contributions published in this book address many topics related to theory and applications of intelligent distributed computing and multi-agent systems, including: adaptive and autonomous distributed systems, agent programming, ambient assisted living systems, business process modeling and verification, cloud computing, coalition formation, decision support systems, distributed optimization and constraint satisfaction, gesture recognition, intelligent energy management in WSNs, intelligent logistics, machine learning, mobile agents, parallel and distributed computational intelligence, parallel evolutionary computing, trus...

High Performance Computing Facility Operational Assessment 2015: Oak Ridge Leadership Computing Facility

Energy Technology Data Exchange (ETDEWEB)

Barker, Ashley D. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Bernholdt, David E. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Bland, Arthur S. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Gary, Jeff D. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Hack, James J. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; McNally, Stephen T. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Rogers, James H. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Smith, Brian E. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Straatsma, T. P. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Sukumar, Sreenivas Rangan [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Thach, Kevin G. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Tichenor, Suzy [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Vazhkudai, Sudharshan S. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility; Wells, Jack C. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility

2016-03-01

Oak Ridge National Laboratory’s (ORNL’s) Leadership Computing Facility (OLCF) continues to surpass its operational target goals: supporting users; delivering fast, reliable systems; creating innovative solutions for high-performance computing (HPC) needs; and managing risks, safety, and security aspects associated with operating one of the most powerful computers in the world. The results can be seen in the cutting-edge science delivered by users and the praise from the research community. Calendar year (CY) 2015 was filled with outstanding operational results and accomplishments: a very high rating from users on overall satisfaction that ties the highest-ever mark set in CY 2014; the greatest number of core-hours delivered to research projects; the largest percentage of capability usage since the OLCF began tracking the metric in 2009; and success in delivering on the allocation of 60, 30, and 10% of core hours offered for the INCITE (Innovative and Novel Computational Impact on Theory and Experiment), ALCC (Advanced Scientific Computing Research Leadership Computing Challenge), and Director’s Discretionary programs, respectively. These accomplishments, coupled with the extremely high utilization rate, represent the fulfillment of the promise of Titan: maximum use by maximum-size simulations. The impact of all of these successes and more is reflected in the accomplishments of OLCF users, with publications this year in notable journals Nature, Nature Materials, Nature Chemistry, Nature Physics, Nature Climate Change, ACS Nano, Journal of the American Chemical Society, and Physical Review Letters, as well as many others. The achievements included in the 2015 OLCF Operational Assessment Report reflect first-ever or largest simulations in their communities; for example Titan enabled engineers in Los Angeles and the surrounding region to design and begin building improved critical infrastructure by enabling the highest-resolution Cybershake map for Southern

FPGA-based distributed computing microarchitecture for complex physical dynamics investigation.

Science.gov (United States)

Borgese, Gianluca; Pace, Calogero; Pantano, Pietro; Bilotta, Eleonora

2013-09-01

In this paper, we present a distributed computing system, called DCMARK, aimed at solving partial differential equations at the basis of many investigation fields, such as solid state physics, nuclear physics, and plasma physics. This distributed architecture is based on the cellular neural network paradigm, which allows us to divide the differential equation system solving into many parallel integration operations to be executed by a custom multiprocessor system. We push the number of processors to the limit of one processor for each equation. In order to test the present idea, we choose to implement DCMARK on a single FPGA, designing the single processor in order to minimize its hardware requirements and to obtain a large number of easily interconnected processors. This approach is particularly suited to study the properties of 1-, 2- and 3-D locally interconnected dynamical systems. In order to test the computing platform, we implement a 200 cells, Korteweg-de Vries (KdV) equation solver and perform a comparison between simulations conducted on a high performance PC and on our system. Since our distributed architecture takes a constant computing time to solve the equation system, independently of the number of dynamical elements (cells) of the CNN array, it allows us to reduce the elaboration time more than other similar systems in the literature. To ensure a high level of reconfigurability, we design a compact system on programmable chip managed by a softcore processor, which controls the fast data/control communication between our system and a PC Host. An intuitively graphical user interface allows us to change the calculation parameters and plot the results.

Export Controls: Implementation of the 1998 Legislative Mandate for High Performance Computers

National Research Council Canada - National Science Library

1999-01-01

We found that most of the 938 proposed exports of high performance computers to civilian end users in countries of concern from February 3, 1998, when procedures implementing the 1998 authorization...

File and metadata management for BESIII distributed computing

International Nuclear Information System (INIS)

Nicholson, C; Zheng, Y H; Lin, L; Deng, Z Y; Li, W D; Zhang, X M

2012-01-01

The BESIII experiment at the Institute of High Energy Physics (IHEP), Beijing, uses the high-luminosity BEPCII e + e − collider to study physics in the π-charm energy region around 3.7 GeV; BEPCII has produced the worlds largest samples of J/φ and φ’ events to date. An order of magnitude increase in the data sample size over the 2011-2012 data-taking period demanded a move from a very centralized to a distributed computing environment, as well as the development of an efficient file and metadata management system. While BESIII is on a smaller scale than some other HEP experiments, this poses particular challenges for its distributed computing and data management system. These constraints include limited resources and manpower, and low quality of network connections to IHEP. Drawing on the rich experience of the HEP community, a system has been developed which meets these constraints. The design and development of the BESIII distributed data management system, including its integration with other BESIII distributed computing components, such as job management, are presented here.

An Introduction to High Performance Fortran

Directory of Open Access Journals (Sweden)

John Merlin

1995-01-01

Full Text Available High Performance Fortran (HPF is an informal standard for extensions to Fortran 90 to assist its implementation on parallel architectures, particularly for data-parallel computation. Among other things, it includes directives for specifying data distribution across multiple memories, and concurrent execution features. This article provides a tutorial introduction to the main features of HPF.

SU-E-T-531: Performance Evaluation of Multithreaded Geant4 for Proton Therapy Dose Calculations in a High Performance Computing Facility

International Nuclear Information System (INIS)

Shin, J; Coss, D; McMurry, J; Farr, J; Faddegon, B

2014-01-01

Purpose: To evaluate the efficiency of multithreaded Geant4 (Geant4-MT, version 10.0) for proton Monte Carlo dose calculations using a high performance computing facility. Methods: Geant4-MT was used to calculate 3D dose distributions in 1×1×1 mm3 voxels in a water phantom and patient's head with a 150 MeV proton beam covering approximately 5×5 cm2 in the water phantom. Three timestamps were measured on the fly to separately analyze the required time for initialization (which cannot be parallelized), processing time of individual threads, and completion time. Scalability of averaged processing time per thread was calculated as a function of thread number (1, 100, 150, and 200) for both 1M and 50 M histories. The total memory usage was recorded. Results: Simulations with 50 M histories were fastest with 100 threads, taking approximately 1.3 hours and 6 hours for the water phantom and the CT data, respectively with better than 1.0 % statistical uncertainty. The calculations show 1/N scalability in the event loops for both cases. The gains from parallel calculations started to decrease with 150 threads. The memory usage increases linearly with number of threads. No critical failures were observed during the simulations. Conclusion: Multithreading in Geant4-MT decreased simulation time in proton dose distribution calculations by a factor of 64 and 54 at a near optimal 100 threads for water phantom and patient's data respectively. Further simulations will be done to determine the efficiency at the optimal thread number. Considering the trend of computer architecture development, utilizing Geant4-MT for radiotherapy simulations is an excellent cost-effective alternative for a distributed batch queuing system. However, because the scalability depends highly on simulation details, i.e., the ratio of the processing time of one event versus waiting time to access for the shared event queue, a performance evaluation as described is recommended

Computer science of the high performance; Informatica del alto rendimiento

Energy Technology Data Exchange (ETDEWEB)

Moraleda, A.

2008-07-01

The high performance computing is taking shape as a powerful accelerator of the process of innovation, to drastically reduce the waiting times for access to the results and the findings in a growing number of processes and activities as complex and important as medicine, genetics, pharmacology, environment, natural resources management or the simulation of complex processes in a wide variety of industries. (Author)

Kemari: A Portable High Performance Fortran System for Distributed Memory Parallel Processors

Directory of Open Access Journals (Sweden)

T. Kamachi

1997-01-01

Full Text Available We have developed a compilation system which extends High Performance Fortran (HPF in various aspects. We support the parallelization of well-structured problems with loop distribution and alignment directives similar to HPF's data distribution directives. Such directives give both additional control to the user and simplify the compilation process. For the support of unstructured problems, we provide directives for dynamic data distribution through user-defined mappings. The compiler also allows integration of message-passing interface (MPI primitives. The system is part of a complete programming environment which also comprises a parallel debugger and a performance monitor and analyzer. After an overview of the compiler, we describe the language extensions and related compilation mechanisms in detail. Performance measurements demonstrate the compiler's applicability to a variety of application classes.

Business Models of High Performance Computing Centres in Higher Education in Europe

Science.gov (United States)

Eurich, Markus; Calleja, Paul; Boutellier, Roman

2013-01-01

High performance computing (HPC) service centres are a vital part of the academic infrastructure of higher education organisations. However, despite their importance for research and the necessary high capital expenditures, business research on HPC service centres is mostly missing. From a business perspective, it is important to find an answer to…

Big Data and High-Performance Computing in Global Seismology

Science.gov (United States)

Bozdag, Ebru; Lefebvre, Matthieu; Lei, Wenjie; Peter, Daniel; Smith, James; Komatitsch, Dimitri; Tromp, Jeroen

2014-05-01

Much of our knowledge of Earth's interior is based on seismic observations and measurements. Adjoint methods provide an efficient way of incorporating 3D full wave propagation in iterative seismic inversions to enhance tomographic images and thus our understanding of processes taking place inside the Earth. Our aim is to take adjoint tomography, which has been successfully applied to regional and continental scale problems, further to image the entire planet. This is one of the extreme imaging challenges in seismology, mainly due to the intense computational requirements and vast amount of high-quality seismic data that can potentially be assimilated. We have started low-resolution inversions (T > 30 s and T > 60 s for body and surface waves, respectively) with a limited data set (253 carefully selected earthquakes and seismic data from permanent and temporary networks) on Oak Ridge National Laboratory's Cray XK7 "Titan" system. Recent improvements in our 3D global wave propagation solvers, such as a GPU version of the SPECFEM3D_GLOBE package, will enable us perform higher-resolution (T > 9 s) and longer duration (~180 m) simulations to take the advantage of high-frequency body waves and major-arc surface waves, thereby improving imbalanced ray coverage as a result of the uneven global distribution of sources and receivers. Our ultimate goal is to use all earthquakes in the global CMT catalogue within the magnitude range of our interest and data from all available seismic networks. To take the full advantage of computational resources, we need a solid framework to manage big data sets during numerical simulations, pre-processing (i.e., data requests and quality checks, processing data, window selection, etc.) and post-processing (i.e., pre-conditioning and smoothing kernels, etc.). We address the bottlenecks in our global seismic workflow, which are mainly coming from heavy I/O traffic during simulations and the pre- and post-processing stages, by defining new data

Distributed computer controls for accelerator systems

Science.gov (United States)

Moore, T. L.

1989-04-01

A distributed control system has been designed and installed at the Lawrence Livermore National Laboratory Multiuser Tandem Facility using an extremely modular approach in hardware and software. The two tiered, geographically organized design allowed total system implantation within four months with a computer and instrumentation cost of approximately $100k. Since the system structure is modular, application to a variety of facilities is possible. Such a system allows rethinking of operational style of the facilities, making possible highly reproducible and unattended operation. The impact of industry standards, i.e., UNIX, CAMAC, and IEEE-802.3, and the use of a graphics-oriented controls software suite allowed the effective implementation of the system. The definition, design, implementation, operation and total system performance will be discussed.

Distributed computer controls for accelerator systems

International Nuclear Information System (INIS)

Moore, T.L.

1989-01-01

A distributed control system has been designed and installed at the Lawrence Livermore National Laboratory Multiuser Tandem Facility using an extremely modular approach in hardware and software. The two tiered, geographically organized design allowed total system implantation within four months with a computer and instrumentation cost of approximately $100k. Since the system structure is modular, application to a variety of facilities is possible. Such a system allows rethinking of operational style of the facilities, making possible highly reproducible and unattended operation. The impact of industry standards, i.e., UNIX, CAMAC, and IEEE-802.3, and the use of a graphics-oriented controls software suite allowed the effective implementation of the system. The definition, design, implementation, operation and total system performance will be discussed. (orig.)

Distributed computer controls for accelerator systems

International Nuclear Information System (INIS)

Moore, T.L.

1988-09-01

A distributed control system has been designed and installed at the Lawrence Livermore National Laboratory Multi-user Tandem Facility using an extremely modular approach in hardware and software. The two tiered, geographically organized design allowed total system implementation with four months with a computer and instrumentation cost of approximately $100K. Since the system structure is modular, application to a variety of facilities is possible. Such a system allows rethinking and operational style of the facilities, making possible highly reproducible and unattended operation. The impact of industry standards, i.e., UNIX, CAMAC, and IEEE-802.3, and the use of a graphics-oriented controls software suite allowed the efficient implementation of the system. The definition, design, implementation, operation and total system performance will be discussed. 3 refs

Visualization of Distributed Data Structures for High Performance Fortran-Like Languages

Directory of Open Access Journals (Sweden)

Rainer Koppler

1997-01-01

Full Text Available This article motivates the usage of graphics and visualization for efficient utilization of High Performance Fortran's (HPF's data distribution facilities. It proposes a graphical toolkit consisting of exploratory and estimation tools which allow the programmer to navigate through complex distributions and to obtain graphical ratings with respect to load distribution and communication. The toolkit has been implemented in a mapping design and visualization tool which is coupled with a compilation system for the HPF predecessor Vienna Fortran. Since this language covers a superset of HPF's facilities, the tool may also be used for visualization of HPF data structures.

Confabulation Based Real-time Anomaly Detection for Wide-area Surveillance Using Heterogeneous High Performance Computing Architecture

Science.gov (United States)

2015-06-01

CONFABULATION BASED REAL-TIME ANOMALY DETECTION FOR WIDE-AREA SURVEILLANCE USING HETEROGENEOUS HIGH PERFORMANCE COMPUTING ARCHITECTURE SYRACUSE...DETECTION FOR WIDE-AREA SURVEILLANCE USING HETEROGENEOUS HIGH PERFORMANCE COMPUTING ARCHITECTURE 5a. CONTRACT NUMBER FA8750-12-1-0251 5b. GRANT...processors including graphic processor units (GPUs) and Intel Xeon Phi processors. Experimental results showed significant speedups, which can enable

High Performance Computing Facility Operational Assessment, FY 2010 Oak Ridge Leadership Computing Facility

Energy Technology Data Exchange (ETDEWEB)

Bland, Arthur S Buddy [ORNL; Hack, James J [ORNL; Baker, Ann E [ORNL; Barker, Ashley D [ORNL; Boudwin, Kathlyn J. [ORNL; Kendall, Ricky A [ORNL; Messer, Bronson [ORNL; Rogers, James H [ORNL; Shipman, Galen M [ORNL; White, Julia C [ORNL

2010-08-01

Oak Ridge National Laboratory's (ORNL's) Cray XT5 supercomputer, Jaguar, kicked off the era of petascale scientific computing in 2008 with applications that sustained more than a thousand trillion floating point calculations per second - or 1 petaflop. Jaguar continues to grow even more powerful as it helps researchers broaden the boundaries of knowledge in virtually every domain of computational science, including weather and climate, nuclear energy, geosciences, combustion, bioenergy, fusion, and materials science. Their insights promise to broaden our knowledge in areas that are vitally important to the Department of Energy (DOE) and the nation as a whole, particularly energy assurance and climate change. The science of the 21st century, however, will demand further revolutions in computing, supercomputers capable of a million trillion calculations a second - 1 exaflop - and beyond. These systems will allow investigators to continue attacking global challenges through modeling and simulation and to unravel longstanding scientific questions. Creating such systems will also require new approaches to daunting challenges. High-performance systems of the future will need to be codesigned for scientific and engineering applications with best-in-class communications networks and data-management infrastructures and teams of skilled researchers able to take full advantage of these new resources. The Oak Ridge Leadership Computing Facility (OLCF) provides the nation's most powerful open resource for capability computing, with a sustainable path that will maintain and extend national leadership for DOE's Office of Science (SC). The OLCF has engaged a world-class team to support petascale science and to take a dramatic step forward, fielding new capabilities for high-end science. This report highlights the successful delivery and operation of a petascale system and shows how the OLCF fosters application development teams, developing cutting-edge tools

Management issues for high performance storage systems

Energy Technology Data Exchange (ETDEWEB)

Louis, S. [Lawrence Livermore National Lab., CA (United States); Burris, R. [Oak Ridge National Lab., TN (United States)

1995-03-01

Managing distributed high-performance storage systems is complex and, although sharing common ground with traditional network and systems management, presents unique storage-related issues. Integration technologies and frameworks exist to help manage distributed network and system environments. Industry-driven consortia provide open forums where vendors and users cooperate to leverage solutions. But these new approaches to open management fall short addressing the needs of scalable, distributed storage. We discuss the motivation and requirements for storage system management (SSM) capabilities and describe how SSM manages distributed servers and storage resource objects in the High Performance Storage System (HPSS), a new storage facility for data-intensive applications and large-scale computing. Modem storage systems, such as HPSS, require many SSM capabilities, including server and resource configuration control, performance monitoring, quality of service, flexible policies, file migration, file repacking, accounting, and quotas. We present results of initial HPSS SSM development including design decisions and implementation trade-offs. We conclude with plans for follow-on work and provide storage-related recommendations for vendors and standards groups seeking enterprise-wide management solutions.

A compositional reservoir simulator on distributed memory parallel computers

International Nuclear Information System (INIS)

Rame, M.; Delshad, M.

1995-01-01

This paper presents the application of distributed memory parallel computes to field scale reservoir simulations using a parallel version of UTCHEM, The University of Texas Chemical Flooding Simulator. The model is a general purpose highly vectorized chemical compositional simulator that can simulate a wide range of displacement processes at both field and laboratory scales. The original simulator was modified to run on both distributed memory parallel machines (Intel iPSC/960 and Delta, Connection Machine 5, Kendall Square 1 and 2, and CRAY T3D) and a cluster of workstations. A domain decomposition approach has been taken towards parallelization of the code. A portion of the discrete reservoir model is assigned to each processor by a set-up routine that attempts a data layout as even as possible from the load-balance standpoint. Each of these subdomains is extended so that data can be shared between adjacent processors for stencil computation. The added routines that make parallel execution possible are written in a modular fashion that makes the porting to new parallel platforms straight forward. Results of the distributed memory computing performance of Parallel simulator are presented for field scale applications such as tracer flood and polymer flood. A comparison of the wall-clock times for same problems on a vector supercomputer is also presented

Parallel Backprojection: A Case Study in High-Performance Reconfigurable Computing

Directory of Open Access Journals (Sweden)

Cordes Ben

2009-01-01

Full Text Available High-performance reconfigurable computing (HPRC is a novel approach to provide large-scale computing power to modern scientific applications. Using both general-purpose processors and FPGAs allows application designers to exploit fine-grained and coarse-grained parallelism, achieving high degrees of speedup. One scientific application that benefits from this technique is backprojection, an image formation algorithm that can be used as part of a synthetic aperture radar (SAR processing system. We present an implementation of backprojection for SAR on an HPRC system. Using simulated data taken at a variety of ranges, our implementation runs over 200 times faster than a similar software program, with an overall application speedup better than 50x. The backprojection application is easily parallelizable, achieving near-linear speedup when run on multiple nodes of a clustered HPRC system. The results presented can be applied to other systems and other algorithms with similar characteristics.

Parallel Backprojection: A Case Study in High-Performance Reconfigurable Computing

Directory of Open Access Journals (Sweden)

2009-03-01

Full Text Available High-performance reconfigurable computing (HPRC is a novel approach to provide large-scale computing power to modern scientific applications. Using both general-purpose processors and FPGAs allows application designers to exploit fine-grained and coarse-grained parallelism, achieving high degrees of speedup. One scientific application that benefits from this technique is backprojection, an image formation algorithm that can be used as part of a synthetic aperture radar (SAR processing system. We present an implementation of backprojection for SAR on an HPRC system. Using simulated data taken at a variety of ranges, our implementation runs over 200 times faster than a similar software program, with an overall application speedup better than 50x. The backprojection application is easily parallelizable, achieving near-linear speedup when run on multiple nodes of a clustered HPRC system. The results presented can be applied to other systems and other algorithms with similar characteristics.

High performance computing environment for multidimensional image analysis.

Science.gov (United States)

Rao, A Ravishankar; Cecchi, Guillermo A; Magnasco, Marcelo

2007-07-10

The processing of images acquired through microscopy is a challenging task due to the large size of datasets (several gigabytes) and the fast turnaround time required. If the throughput of the image processing stage is significantly increased, it can have a major impact in microscopy applications. We present a high performance computing (HPC) solution to this problem. This involves decomposing the spatial 3D image into segments that are assigned to unique processors, and matched to the 3D torus architecture of the IBM Blue Gene/L machine. Communication between segments is restricted to the nearest neighbors. When running on a 2 Ghz Intel CPU, the task of 3D median filtering on a typical 256 megabyte dataset takes two and a half hours, whereas by using 1024 nodes of Blue Gene, this task can be performed in 18.8 seconds, a 478x speedup. Our parallel solution dramatically improves the performance of image processing, feature extraction and 3D reconstruction tasks. This increased throughput permits biologists to conduct unprecedented large scale experiments with massive datasets.

A checkpoint compression study for high-performance computing systems

Energy Technology Data Exchange (ETDEWEB)

Ibtesham, Dewan [Univ. of New Mexico, Albuquerque, NM (United States). Dept. of Computer Science; Ferreira, Kurt B. [Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States). Scalable System Software Dept.; Arnold, Dorian [Univ. of New Mexico, Albuquerque, NM (United States). Dept. of Computer Science

2015-02-17

As high-performance computing systems continue to increase in size and complexity, higher failure rates and increased overheads for checkpoint/restart (CR) protocols have raised concerns about the practical viability of CR protocols for future systems. Previously, compression has proven to be a viable approach for reducing checkpoint data volumes and, thereby, reducing CR protocol overhead leading to improved application performance. In this article, we further explore compression-based CR optimization by exploring its baseline performance and scaling properties, evaluating whether improved compression algorithms might lead to even better application performance and comparing checkpoint compression against and alongside other software- and hardware-based optimizations. Our results highlights are: (1) compression is a very viable CR optimization; (2) generic, text-based compression algorithms appear to perform near optimally for checkpoint data compression and faster compression algorithms will not lead to better application performance; (3) compression-based optimizations fare well against and alongside other software-based optimizations; and (4) while hardware-based optimizations outperform software-based ones, they are not as cost effective.

14th annual Results and Review Workshop on High Performance Computing in Science and Engineering

CERN Document Server

Nagel, Wolfgang E; Resch, Michael M; Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2011; High Performance Computing in Science and Engineering '11

2012-01-01

This book presents the state-of-the-art in simulation on supercomputers. Leading researchers present results achieved on systems of the High Performance Computing Center Stuttgart (HLRS) for the year 2011. The reports cover all fields of computational science and engineering, ranging from CFD to computational physics and chemistry, to computer science, with a special emphasis on industrially relevant applications. Presenting results for both vector systems and microprocessor-based systems, the book allows readers to compare the performance levels and usability of various architectures. As HLRS

Acceleration of FDTD mode solver by high-performance computing techniques.

Science.gov (United States)

Han, Lin; Xi, Yanping; Huang, Wei-Ping

2010-06-21

A two-dimensional (2D) compact finite-difference time-domain (FDTD) mode solver is developed based on wave equation formalism in combination with the matrix pencil method (MPM). The method is validated for calculation of both real guided and complex leaky modes of typical optical waveguides against the bench-mark finite-difference (FD) eigen mode solver. By taking advantage of the inherent parallel nature of the FDTD algorithm, the mode solver is implemented on graphics processing units (GPUs) using the compute unified device architecture (CUDA). It is demonstrated that the high-performance computing technique leads to significant acceleration of the FDTD mode solver with more than 30 times improvement in computational efficiency in comparison with the conventional FDTD mode solver running on CPU of a standard desktop computer. The computational efficiency of the accelerated FDTD method is in the same order of magnitude of the standard finite-difference eigen mode solver and yet require much less memory (e.g., less than 10%). Therefore, the new method may serve as an efficient, accurate and robust tool for mode calculation of optical waveguides even when the conventional eigen value mode solvers are no longer applicable due to memory limitation.

Using spatial principles to optimize distributed computing for enabling the physical science discoveries.

Science.gov (United States)

Yang, Chaowei; Wu, Huayi; Huang, Qunying; Li, Zhenlong; Li, Jing

2011-04-05

Contemporary physical science studies rely on the effective analyses of geographically dispersed spatial data and simulations of physical phenomena. Single computers and generic high-end computing are not sufficient to process the data for complex physical science analysis and simulations, which can be successfully supported only through distributed computing, best optimized through the application of spatial principles. Spatial computing, the computing aspect of a spatial cyberinfrastructure, refers to a computing paradigm that utilizes spatial principles to optimize distributed computers to catalyze advancements in the physical sciences. Spatial principles govern the interactions between scientific parameters across space and time by providing the spatial connections and constraints to drive the progression of the phenomena. Therefore, spatial computing studies could better position us to leverage spatial principles in simulating physical phenomena and, by extension, advance the physical sciences. Using geospatial science as an example, this paper illustrates through three research examples how spatial computing could (i) enable data intensive science with efficient data/services search, access, and utilization, (ii) facilitate physical science studies with enabling high-performance computing capabilities, and (iii) empower scientists with multidimensional visualization tools to understand observations and simulations. The research examples demonstrate that spatial computing is of critical importance to design computing methods to catalyze physical science studies with better data access, phenomena simulation, and analytical visualization. We envision that spatial computing will become a core technology that drives fundamental physical science advancements in the 21st century.

Multi-Language Programming Environments for High Performance Java Computing

Directory of Open Access Journals (Sweden)

Vladimir Getov

1999-01-01

Full Text Available Recent developments in processor capabilities, software tools, programming languages and programming paradigms have brought about new approaches to high performance computing. A steadfast component of this dynamic evolution has been the scientific community’s reliance on established scientific packages. As a consequence, programmers of high‐performance applications are reluctant to embrace evolving languages such as Java. This paper describes the Java‐to‐C Interface (JCI tool which provides application programmers wishing to use Java with immediate accessibility to existing scientific packages. The JCI tool also facilitates rapid development and reuse of existing code. These benefits are provided at minimal cost to the programmer. While beneficial to the programmer, the additional advantages of mixed‐language programming in terms of application performance and portability are addressed in detail within the context of this paper. In addition, we discuss how the JCI tool is complementing other ongoing projects such as IBM’s High‐Performance Compiler for Java (HPCJ and IceT’s metacomputing environment.

A Distributed Computing Network for Real-Time Systems.

Science.gov (United States)

1980-11-03

7 ) AU2 o NAVA TUNDEWATER SY$TEMS CENTER NEWPORT RI F/G 9/2 UIS RIBUT E 0 COMPUTIN G N LTWORK FOR REAL - TIME SYSTEMS .(U) UASSIFIED NOV Al 6 1...MORAIS - UT 92 dLEVEL c A Distributed Computing Network for Real - Time Systems . 11 𔃺-1 Gordon E/Morson I7 y tm- ,r - t "en t As J 2 -p .. - 7 I’ cNaval...NUMBER TD 5932 / N 4. TITLE mand SubotI. S. TYPE OF REPORT & PERIOD COVERED A DISTRIBUTED COMPUTING NETWORK FOR REAL - TIME SYSTEMS 6. PERFORMING ORG

What Physicists Should Know About High Performance Computing - Circa 2002

Science.gov (United States)

Frederick, Donald

2002-08-01

High Performance Computing (HPC) is a dynamic, cross-disciplinary field that traditionally has involved applied mathematicians, computer scientists, and others primarily from the various disciplines that have been major users of HPC resources - physics, chemistry, engineering, with increasing use by those in the life sciences. There is a technological dynamic that is powered by economic as well as by technical innovations and developments. This talk will discuss practical ideas to be considered when developing numerical applications for research purposes. Even with the rapid pace of development in the field, the author believes that these concepts will not become obsolete for a while, and will be of use to scientists who either are considering, or who have already started down the HPC path. These principles will be applied in particular to current parallel HPC systems, but there will also be references of value to desktop users. The talk will cover such topics as: computing hardware basics, single-cpu optimization, compilers, timing, numerical libraries, debugging and profiling tools and the emergence of Computational Grids.

RISC Processors and High Performance Computing

Science.gov (United States)

Bailey, David H.; Saini, Subhash; Craw, James M. (Technical Monitor)

1995-01-01

This tutorial will discuss the top five RISC microprocessors and the parallel systems in which they are used. It will provide a unique cross-machine comparison not available elsewhere. The effective performance of these processors will be compared by citing standard benchmarks in the context of real applications. The latest NAS Parallel Benchmarks, both absolute performance and performance per dollar, will be listed. The next generation of the NPB will be described. The tutorial will conclude with a discussion of future directions in the field. Technology Transfer Considerations: All of these computer systems are commercially available internationally. Information about these processors is available in the public domain, mostly from the vendors themselves. The NAS Parallel Benchmarks and their results have been previously approved numerous times for public release, beginning back in 1991.

Comprehensive Simulation Lifecycle Management for High Performance Computing Modeling and Simulation, Phase I

Data.gov (United States)

National Aeronautics and Space Administration — There are significant logistical barriers to entry-level high performance computing (HPC) modeling and simulation (M IllinoisRocstar) sets up the infrastructure for...

A Methodology to Reduce the Computational Effort in the Evaluation of the Lightning Performance of Distribution Networks

Directory of Open Access Journals (Sweden)

Ilaria Bendato

2016-11-01

Full Text Available The estimation of the lightning performance of a power distribution network is of great importance to design its protection system against lightning. An accurate evaluation of the number of lightning events that can create dangerous overvoltages requires a huge computational effort, as it implies the adoption of a Monte Carlo procedure. Such a procedure consists of generating many different random lightning events and calculating the corresponding overvoltages. The paper proposes a methodology to deal with the problem in two computationally efficient ways: (i finding out the minimum number of Monte Carlo runs that lead to reliable results; and (ii setting up a procedure that bypasses the lightning field-to-line coupling problem for each Monte Carlo run. The proposed approach is shown to provide results consistent with existing approaches while exhibiting superior Central Processing Unit (CPU time performances.

High-Performance Computing in Neuroscience for Data-Driven Discovery, Integration, and Dissemination

International Nuclear Information System (INIS)

Bouchard, Kristofer E.

2016-01-01

A lack of coherent plans to analyze, manage, and understand data threatens the various opportunities offered by new neuro-technologies. High-performance computing will allow exploratory analysis of massive datasets stored in standardized formats, hosted in open repositories, and integrated with simulations.

High Performance Computing - Power Application Programming Interface Specification Version 2.0.

Energy Technology Data Exchange (ETDEWEB)

Laros, James H. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Grant, Ryan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Levenhagen, Michael J. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Olivier, Stephen Lecler [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Pedretti, Kevin [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Ward, H. Lee [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Younge, Andrew J. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

2017-03-01

Measuring and controlling the power and energy consumption of high performance computing systems by various components in the software stack is an active research area. Implementations in lower level software layers are beginning to emerge in some production systems, which is very welcome. To be most effective, a portable interface to measurement and control features would significantly facilitate participation by all levels of the software stack. We present a proposal for a standard power Application Programming Interface (API) that endeavors to cover the entire software space, from generic hardware interfaces to the input from the computer facility manager.

Electromagnetic Modeling of Human Body Using High Performance Computing

Science.gov (United States)

Ng, Cho-Kuen; Beall, Mark; Ge, Lixin; Kim, Sanghoek; Klaas, Ottmar; Poon, Ada

Realistic simulation of electromagnetic wave propagation in the actual human body can expedite the investigation of the phenomenon of harvesting implanted devices using wireless powering coupled from external sources. The parallel electromagnetics code suite ACE3P developed at SLAC National Accelerator Laboratory is based on the finite element method for high fidelity accelerator simulation, which can be enhanced to model electromagnetic wave propagation in the human body. Starting with a CAD model of a human phantom that is characterized by a number of tissues, a finite element mesh representing the complex geometries of the individual tissues is built for simulation. Employing an optimal power source with a specific pattern of field distribution, the propagation and focusing of electromagnetic waves in the phantom has been demonstrated. Substantial speedup of the simulation is achieved by using multiple compute cores on supercomputers.

BEAGLE: an application programming interface and high-performance computing library for statistical phylogenetics.

Science.gov (United States)

Ayres, Daniel L; Darling, Aaron; Zwickl, Derrick J; Beerli, Peter; Holder, Mark T; Lewis, Paul O; Huelsenbeck, John P; Ronquist, Fredrik; Swofford, David L; Cummings, Michael P; Rambaut, Andrew; Suchard, Marc A

2012-01-01

Phylogenetic inference is fundamental to our understanding of most aspects of the origin and evolution of life, and in recent years, there has been a concentration of interest in statistical approaches such as Bayesian inference and maximum likelihood estimation. Yet, for large data sets and realistic or interesting models of evolution, these approaches remain computationally demanding. High-throughput sequencing can yield data for thousands of taxa, but scaling to such problems using serial computing often necessitates the use of nonstatistical or approximate approaches. The recent emergence of graphics processing units (GPUs) provides an opportunity to leverage their excellent floating-point computational performance to accelerate statistical phylogenetic inference. A specialized library for phylogenetic calculation would allow existing software packages to make more effective use of available computer hardware, including GPUs. Adoption of a common library would also make it easier for other emerging computing architectures, such as field programmable gate arrays, to be used in the future. We present BEAGLE, an application programming interface (API) and library for high-performance statistical phylogenetic inference. The API provides a uniform interface for performing phylogenetic likelihood calculations on a variety of compute hardware platforms. The library includes a set of efficient implementations and can currently exploit hardware including GPUs using NVIDIA CUDA, central processing units (CPUs) with Streaming SIMD Extensions and related processor supplementary instruction sets, and multicore CPUs via OpenMP. To demonstrate the advantages of a common API, we have incorporated the library into several popular phylogenetic software packages. The BEAGLE library is free open source software licensed under the Lesser GPL and available from http://beagle-lib.googlecode.com. An example client program is available as public domain software.

Computational Analysis of a Wing Designed for the X-57 Distributed Electric Propulsion Aircraft

Science.gov (United States)

Deere, Karen A.; Viken, Jeffrey K.; Viken, Sally A.; Carter, Melissa B.; Wiese, Michael R.; Farr, Norma L.

2017-01-01

A computational study of the wing for the distributed electric propulsion X-57 Maxwell airplane configuration at cruise and takeoff/landing conditions was completed. Two unstructured-mesh, Navier-Stokes computational fluid dynamics methods, FUN3D and USM3D, were used to predict the wing performance. The goal of the X-57 wing and distributed electric propulsion system design was to meet or exceed the required lift coefficient 3.95 for a stall speed of 58 knots, with a cruise speed of 150 knots at an altitude of 8,000 ft. The X-57 Maxwell airplane was designed with a small, high aspect ratio cruise wing that was designed for a high cruise lift coefficient (0.75) at angle of attack of 0deg. The cruise propulsors at the wingtip rotate counter to the wingtip vortex and reduce induced drag by 7.5 percent at an angle of attack of 0.6deg. The unblown maximum lift coefficient of the high-lift wing (with the 30deg flap setting) is 2.439. The stall speed goal performance metric was confirmed with a blown wing computed effective lift coefficient of 4.202. The lift augmentation from the high-lift, distributed electric propulsion system is 1.7. The predicted cruise wing drag coefficient of 0.02191 is 0.00076 above the drag allotted for the wing in the original estimate. However, the predicted drag overage for the wing would only use 10.1 percent of the original estimated drag margin, which is 0.00749.

Integrated State Estimation and Contingency Analysis Software Implementation using High Performance Computing Techniques

Energy Technology Data Exchange (ETDEWEB)

Chen, Yousu; Glaesemann, Kurt R.; Rice, Mark J.; Huang, Zhenyu

2015-12-31

Power system simulation tools are traditionally developed in sequential mode and codes are optimized for single core computing only. However, the increasing complexity in the power grid models requires more intensive computation. The traditional simulation tools will soon not be able to meet the grid operation requirements. Therefore, power system simulation tools need to evolve accordingly to provide faster and better results for grid operations. This paper presents an integrated state estimation and contingency analysis software implementation using high performance computing techniques. The software is able to solve large size state estimation problems within one second and achieve a near-linear speedup of 9,800 with 10,000 cores for contingency analysis application. The performance evaluation is presented to show its effectiveness.

Trends in high-performance computing for engineering calculations.

Science.gov (United States)

Giles, M B; Reguly, I

2014-08-13

High-performance computing has evolved remarkably over the past 20 years, and that progress is likely to continue. However, in recent years, this progress has been achieved through greatly increased hardware complexity with the rise of multicore and manycore processors, and this is affecting the ability of application developers to achieve the full potential of these systems. This article outlines the key developments on the hardware side, both in the recent past and in the near future, with a focus on two key issues: energy efficiency and the cost of moving data. It then discusses the much slower evolution of system software, and the implications of all of this for application developers. © 2014 The Author(s) Published by the Royal Society. All rights reserved.

Distributed computing and nuclear reactor analysis

International Nuclear Information System (INIS)

Brown, F.B.; Derstine, K.L.; Blomquist, R.N.

1994-01-01

Large-scale scientific and engineering calculations for nuclear reactor analysis can now be carried out effectively in a distributed computing environment, at costs far lower than for traditional mainframes. The distributed computing environment must include support for traditional system services, such as a queuing system for batch work, reliable filesystem backups, and parallel processing capabilities for large jobs. All ANL computer codes for reactor analysis have been adapted successfully to a distributed system based on workstations and X-terminals. Distributed parallel processing has been demonstrated to be effective for long-running Monte Carlo calculations

Cryptographically Secure Multiparty Computation and Distributed Auctions Using Homomorphic Encryption

Directory of Open Access Journals (Sweden)

Anunay Kulshrestha

2017-12-01

Full Text Available We introduce a robust framework that allows for cryptographically secure multiparty computations, such as distributed private value auctions. The security is guaranteed by two-sided authentication of all network connections, homomorphically encrypted bids, and the publication of zero-knowledge proofs of every computation. This also allows a non-participant verifier to verify the result of any such computation using only the information broadcasted on the network by each individual bidder. Building on previous work on such systems, we design and implement an extensible framework that puts the described ideas to practice. Apart from the actual implementation of the framework, our biggest contribution is the level of protection we are able to guarantee from attacks described in previous work. In order to provide guidance to users of the library, we analyze the use of zero knowledge proofs in ensuring the correct behavior of each node in a computation. We also describe the usage of the library to perform a private-value distributed auction, as well as the other challenges in implementing the protocol, such as auction registration and certificate distribution. Finally, we provide performance statistics on our implementation of the auction.

High-performance mass storage system for workstations

Science.gov (United States)

Chiang, T.; Tang, Y.; Gupta, L.; Cooperman, S.

1993-01-01

Reduced Instruction Set Computer (RISC) workstations and Personnel Computers (PC) are very popular tools for office automation, command and control, scientific analysis, database management, and many other applications. However, when using Input/Output (I/O) intensive applications, the RISC workstations and PC's are often overburdened with the tasks of collecting, staging, storing, and distributing data. Also, by using standard high-performance peripherals and storage devices, the I/O function can still be a common bottleneck process. Therefore, the high-performance mass storage system, developed by Loral AeroSys' Independent Research and Development (IR&D) engineers, can offload a RISC workstation of I/O related functions and provide high-performance I/O functions and external interfaces. The high-performance mass storage system has the capabilities to ingest high-speed real-time data, perform signal or image processing, and stage, archive, and distribute the data. This mass storage system uses a hierarchical storage structure, thus reducing the total data storage cost, while maintaining high-I/O performance. The high-performance mass storage system is a network of low-cost parallel processors and storage devices. The nodes in the network have special I/O functions such as: SCSI controller, Ethernet controller, gateway controller, RS232 controller, IEEE488 controller, and digital/analog converter. The nodes are interconnected through high-speed direct memory access links to form a network. The topology of the network is easily reconfigurable to maximize system throughput for various applications. This high-performance mass storage system takes advantage of a 'busless' architecture for maximum expandability. The mass storage system consists of magnetic disks, a WORM optical disk jukebox, and an 8mm helical scan tape to form a hierarchical storage structure. Commonly used files are kept in the magnetic disk for fast retrieval. The optical disks are used as archive

Distributed computing and artificial intelligence : 10th International Conference

CERN Document Server

Neves, José; Rodriguez, Juan; Santana, Juan; Gonzalez, Sara

2013-01-01

The International Symposium on Distributed Computing and Artificial Intelligence 2013 (DCAI 2013) is a forum in which applications of innovative techniques for solving complex problems are presented. Artificial intelligence is changing our society. Its application in distributed environments, such as the internet, electronic commerce, environment monitoring, mobile communications, wireless devices, distributed computing, to mention only a few, is continuously increasing, becoming an element of high added value with social and economic potential, in industry, quality of life, and research. This conference is a stimulating and productive forum where the scientific community can work towards future cooperation in Distributed Computing and Artificial Intelligence areas. These technologies are changing constantly as a result of the large research and technical effort being undertaken in both universities and businesses. The exchange of ideas between scientists and technicians from both the academic and industry se...

Optical high-performance computing: introduction to the JOSA A and Applied Optics feature.

Science.gov (United States)

Caulfield, H John; Dolev, Shlomi; Green, William M J

2009-08-01

The feature issues in both Applied Optics and the Journal of the Optical Society of America A focus on topics of immediate relevance to the community working in the area of optical high-performance computing.

Performance Analysis of Ivshmem for High-Performance Computing in Virtual Machines

Science.gov (United States)

Ivanovic, Pavle; Richter, Harald

2018-01-01

High-Performance computing (HPC) is rarely accomplished via virtual machines (VMs). In this paper, we present a remake of ivshmem which can change this. Ivshmem was a shared memory (SHM) between virtual machines on the same server, with SHM-access synchronization included, until about 5 years ago when newer versions of Linux and its virtualization library libvirt evolved. We restored that SHM-access synchronization feature because it is indispensable for HPC and made ivshmem runnable with contemporary versions of Linux, libvirt, KVM, QEMU and especially MPICH, which is an implementation of MPI - the standard HPC communication library. Additionally, MPICH was transparently modified by us to get ivshmem included, resulting in a three to ten times performance improvement compared to TCP/IP. Furthermore, we have transparently replaced MPI_PUT, a single-side MPICH communication mechanism, by an own MPI_PUT wrapper. As a result, our ivshmem even surpasses non-virtualized SHM data transfers for block lengths greater than 512 KBytes, showing the benefits of virtualization. All improvements were possible without using SR-IOV.

ATLAS Distributed Computing in LHC Run2

CERN Document Server

Campana, Simone; The ATLAS collaboration

2015-01-01

The ATLAS Distributed Computing infrastructure has evolved after the first period of LHC data taking in order to cope with the challenges of the upcoming LHC Run2. An increased data rate and computing demands of the Monte-Carlo simulation, as well as new approaches to ATLAS analysis, dictated a more dynamic workload management system (ProdSys2) and data management system (Rucio), overcoming the boundaries imposed by the design of the old computing model. In particular, the commissioning of new central computing system components was the core part of the migration toward the flexible computing model. The flexible computing utilization exploring the opportunistic resources such as HPC, cloud, and volunteer computing is embedded in the new computing model, the data access mechanisms have been enhanced with the remote access, and the network topology and performance is deeply integrated into the core of the system. Moreover a new data management strategy, based on defined lifetime for each dataset, has been defin...

Analysis of scalability of high-performance 3D image processing platform for virtual colonoscopy.

Science.gov (United States)

Yoshida, Hiroyuki; Wu, Yin; Cai, Wenli

2014-03-19

One of the key challenges in three-dimensional (3D) medical imaging is to enable the fast turn-around time, which is often required for interactive or real-time response. This inevitably requires not only high computational power but also high memory bandwidth due to the massive amount of data that need to be processed. For this purpose, we previously developed a software platform for high-performance 3D medical image processing, called HPC 3D-MIP platform, which employs increasingly available and affordable commodity computing systems such as the multicore, cluster, and cloud computing systems. To achieve scalable high-performance computing, the platform employed size-adaptive, distributable block volumes as a core data structure for efficient parallelization of a wide range of 3D-MIP algorithms, supported task scheduling for efficient load distribution and balancing, and consisted of a layered parallel software libraries that allow image processing applications to share the common functionalities. We evaluated the performance of the HPC 3D-MIP platform by applying it to computationally intensive processes in virtual colonoscopy. Experimental results showed a 12-fold performance improvement on a workstation with 12-core CPUs over the original sequential implementation of the processes, indicating the efficiency of the platform. Analysis of performance scalability based on the Amdahl's law for symmetric multicore chips showed the potential of a high performance scalability of the HPC 3D-MIP platform when a larger number of cores is available.

Improving the Eco-Efficiency of High Performance Computing Clusters Using EECluster

Directory of Open Access Journals (Sweden)

Alberto Cocaña-Fernández

2016-03-01

Full Text Available As data and supercomputing centres increase their performance to improve service quality and target more ambitious challenges every day, their carbon footprint also continues to grow, and has already reached the magnitude of the aviation industry. Also, high power consumptions are building up to a remarkable bottleneck for the expansion of these infrastructures in economic terms due to the unavailability of sufficient energy sources. A substantial part of the problem is caused by current energy consumptions of High Performance Computing (HPC clusters. To alleviate this situation, we present in this work EECluster, a tool that integrates with multiple open-source Resource Management Systems to significantly reduce the carbon footprint of clusters by improving their energy efficiency. EECluster implements a dynamic power management mechanism based on Computational Intelligence techniques by learning a set of rules through multi-criteria evolutionary algorithms. This approach enables cluster operators to find the optimal balance between a reduction in the cluster energy consumptions, service quality, and number of reconfigurations. Experimental studies using both synthetic and actual workloads from a real world cluster support the adoption of this tool to reduce the carbon footprint of HPC clusters.

7th International Workshop on Parallel Tools for High Performance Computing

CERN Document Server

Gracia, José; Nagel, Wolfgang; Resch, Michael

2014-01-01

Current advances in High Performance Computing (HPC) increasingly impact efficient software development workflows. Programmers for HPC applications need to consider trends such as increased core counts, multiple levels of parallelism, reduced memory per core, and I/O system challenges in order to derive well performing and highly scalable codes. At the same time, the increasing complexity adds further sources of program defects. While novel programming paradigms and advanced system libraries provide solutions for some of these challenges, appropriate supporting tools are indispensable. Such tools aid application developers in debugging, performance analysis, or code optimization and therefore make a major contribution to the development of robust and efficient parallel software. This book introduces a selection of the tools presented and discussed at the 7th International Parallel Tools Workshop, held in Dresden, Germany, September 3-4, 2013.  

Low-cost, high-performance and efficiency computational photometer design

Science.gov (United States)

Siewert, Sam B.; Shihadeh, Jeries; Myers, Randall; Khandhar, Jay; Ivanov, Vitaly

2014-05-01

Researchers at the University of Alaska Anchorage and University of Colorado Boulder have built a low cost high performance and efficiency drop-in-place Computational Photometer (CP) to test in field applications ranging from port security and safety monitoring to environmental compliance monitoring and surveying. The CP integrates off-the-shelf visible spectrum cameras with near to long wavelength infrared detectors and high resolution digital snapshots in a single device. The proof of concept combines three or more detectors into a single multichannel imaging system that can time correlate read-out, capture, and image process all of the channels concurrently with high performance and energy efficiency. The dual-channel continuous read-out is combined with a third high definition digital snapshot capability and has been designed using an FPGA (Field Programmable Gate Array) to capture, decimate, down-convert, re-encode, and transform images from two standard definition CCD (Charge Coupled Device) cameras at 30Hz. The continuous stereo vision can be time correlated to megapixel high definition snapshots. This proof of concept has been fabricated as a fourlayer PCB (Printed Circuit Board) suitable for use in education and research for low cost high efficiency field monitoring applications that need multispectral and three dimensional imaging capabilities. Initial testing is in progress and includes field testing in ports, potential test flights in un-manned aerial systems, and future planned missions to image harsh environments in the arctic including volcanic plumes, ice formation, and arctic marine life.

Overview of the ATLAS distributed computing system

CERN Document Server

Elmsheuser, Johannes; The ATLAS collaboration

2018-01-01

The CERN ATLAS experiment successfully uses a worldwide computing infrastructure to support the physics program during LHC Run 2. The grid workflow system PanDA routinely manages 250 to 500 thousand concurrently running production and analysis jobs to process simulation and detector data. In total more than 300 PB of data is distributed over more than 150 sites in the WLCG and handled by the ATLAS data management system Rucio. To prepare for the ever growing LHC luminosity in future runs new developments are underway to even more efficiently use opportunistic resources such as HPCs and utilize new technologies. This presentation will review and explain the outline and the performance of the ATLAS distributed computing system and give an outlook to new workflow and data management ideas for the beginning of the LHC Run 3.

Grid computing in high energy physics

CERN Document Server

Avery, P

2004-01-01

Over the next two decades, major high energy physics (HEP) experiments, particularly at the Large Hadron Collider, will face unprecedented challenges to achieving their scientific potential. These challenges arise primarily from the rapidly increasing size and complexity of HEP datasets that will be collected and the enormous computational, storage and networking resources that will be deployed by global collaborations in order to process, distribute and analyze them. Coupling such vast information technology resources to globally distributed collaborations of several thousand physicists requires extremely capable computing infrastructures supporting several key areas: (1) computing (providing sufficient computational and storage resources for all processing, simulation and analysis tasks undertaken by the collaborations); (2) networking (deploying high speed networks to transport data quickly between institutions around the world); (3) software (supporting simple and transparent access to data and software r...

The Convergence of High Performance Computing and Large Scale Data Analytics

Science.gov (United States)

Duffy, D.; Bowen, M. K.; Thompson, J. H.; Yang, C. P.; Hu, F.; Wills, B.

2015-12-01

As the combinations of remote sensing observations and model outputs have grown, scientists are increasingly burdened with both the necessity and complexity of large-scale data analysis. Scientists are increasingly applying traditional high performance computing (HPC) solutions to solve their "Big Data" problems. While this approach has the benefit of limiting data movement, the HPC system is not optimized to run analytics, which can create problems that permeate throughout the HPC environment. To solve these issues and to alleviate some of the strain on the HPC environment, the NASA Center for Climate Simulation (NCCS) has created the Advanced Data Analytics Platform (ADAPT), which combines both HPC and cloud technologies to create an agile system designed for analytics. Large, commonly used data sets are stored in this system in a write once/read many file system, such as Landsat, MODIS, MERRA, and NGA. High performance virtual machines are deployed and scaled according to the individual scientist's requirements specifically for data analysis. On the software side, the NCCS and GMU are working with emerging commercial technologies and applying them to structured, binary scientific data in order to expose the data in new ways. Native NetCDF data is being stored within a Hadoop Distributed File System (HDFS) enabling storage-proximal processing through MapReduce while continuing to provide accessibility of the data to traditional applications. Once the data is stored within HDFS, an additional indexing scheme is built on top of the data and placed into a relational database. This spatiotemporal index enables extremely fast mappings of queries to data locations to dramatically speed up analytics. These are some of the first steps toward a single unified platform that optimizes for both HPC and large-scale data analysis, and this presentation will elucidate the resulting and necessary exascale architectures required for future systems.

Computational Fluid Dynamics and Building Energy Performance Simulation

DEFF Research Database (Denmark)

Nielsen, Peter V.; Tryggvason, Tryggvi

An interconnection between a building energy performance simulation program and a Computational Fluid Dynamics program (CFD) for room air distribution will be introduced for improvement of the predictions of both the energy consumption and the indoor environment. The building energy performance...

Real-time Tsunami Inundation Prediction Using High Performance Computers

Science.gov (United States)

Oishi, Y.; Imamura, F.; Sugawara, D.

2014-12-01

Recently off-shore tsunami observation stations based on cabled ocean bottom pressure gauges are actively being deployed especially in Japan. These cabled systems are designed to provide real-time tsunami data before tsunamis reach coastlines for disaster mitigation purposes. To receive real benefits of these observations, real-time analysis techniques to make an effective use of these data are necessary. A representative study was made by Tsushima et al. (2009) that proposed a method to provide instant tsunami source prediction based on achieving tsunami waveform data. As time passes, the prediction is improved by using updated waveform data. After a tsunami source is predicted, tsunami waveforms are synthesized from pre-computed tsunami Green functions of linear long wave equations. Tsushima et al. (2014) updated the method by combining the tsunami waveform inversion with an instant inversion of coseismic crustal deformation and improved the prediction accuracy and speed in the early stages. For disaster mitigation purposes, real-time predictions of tsunami inundation are also important. In this study, we discuss the possibility of real-time tsunami inundation predictions, which require faster-than-real-time tsunami inundation simulation in addition to instant tsunami source analysis. Although the computational amount is large to solve non-linear shallow water equations for inundation predictions, it has become executable through the recent developments of high performance computing technologies. We conducted parallel computations of tsunami inundation and achieved 6.0 TFLOPS by using 19,000 CPU cores. We employed a leap-frog finite difference method with nested staggered grids of which resolution range from 405 m to 5 m. The resolution ratio of each nested domain was 1/3. Total number of grid points were 13 million, and the time step was 0.1 seconds. Tsunami sources of 2011 Tohoku-oki earthquake were tested. The inundation prediction up to 2 hours after the

ClustalXeed: a GUI-based grid computation version for high performance and terabyte size multiple sequence alignment

Directory of Open Access Journals (Sweden)

Kim Taeho

2010-09-01

Full Text Available Abstract Background There is an increasing demand to assemble and align large-scale biological sequence data sets. The commonly used multiple sequence alignment programs are still limited in their ability to handle very large amounts of sequences because the system lacks a scalable high-performance computing (HPC environment with a greatly extended data storage capacity. Results We designed ClustalXeed, a software system for multiple sequence alignment with incremental improvements over previous versions of the ClustalX and ClustalW-MPI software. The primary advantage of ClustalXeed over other multiple sequence alignment software is its ability to align a large family of protein or nucleic acid sequences. To solve the conventional memory-dependency problem, ClustalXeed uses both physical random access memory (RAM and a distributed file-allocation system for distance matrix construction and pair-align computation. The computation efficiency of disk-storage system was markedly improved by implementing an efficient load-balancing algorithm, called "idle node-seeking task algorithm" (INSTA. The new editing option and the graphical user interface (GUI provide ready access to a parallel-computing environment for users who seek fast and easy alignment of large DNA and protein sequence sets. Conclusions ClustalXeed can now compute a large volume of biological sequence data sets, which were not tractable in any other parallel or single MSA program. The main developments include: 1 the ability to tackle larger sequence alignment problems than possible with previous systems through markedly improved storage-handling capabilities. 2 Implementing an efficient task load-balancing algorithm, INSTA, which improves overall processing times for multiple sequence alignment with input sequences of non-uniform length. 3 Support for both single PC and distributed cluster systems.

Support system for ATLAS distributed computing operations

CERN Document Server

Kishimoto, Tomoe; The ATLAS collaboration

2018-01-01

The ATLAS distributed computing system has allowed the experiment to successfully meet the challenges of LHC Run 2. In order for distributed computing to operate smoothly and efficiently, several support teams are organized in the ATLAS experiment. The ADCoS (ATLAS Distributed Computing Operation Shifts) is a dedicated group of shifters who follow and report failing jobs, failing data transfers between sites, degradation of ATLAS central computing services, and more. The DAST (Distributed Analysis Support Team) provides user support to resolve issues related to running distributed analysis on the grid. The CRC (Computing Run Coordinator) maintains a global view of the day-to-day operations. In this presentation, the status and operational experience of the support system for ATLAS distributed computing in LHC Run 2 will be reported. This report also includes operations experience from the grid site point of view, and an analysis of the errors that create the biggest waste of wallclock time. The report of oper...

Using Java for distributed computing in the Gaia satellite data processing

Science.gov (United States)

O'Mullane, William; Luri, Xavier; Parsons, Paul; Lammers, Uwe; Hoar, John; Hernandez, Jose

2011-10-01

In recent years Java has matured to a stable easy-to-use language with the flexibility of an interpreter (for reflection etc.) but the performance and type checking of a compiled language. When we started using Java for astronomical applications around 1999 they were the first of their kind in astronomy. Now a great deal of astronomy software is written in Java as are many business applications. We discuss the current environment and trends concerning the language and present an actual example of scientific use of Java for high-performance distributed computing: ESA's mission Gaia. The Gaia scanning satellite will perform a galactic census of about 1,000 million objects in our galaxy. The Gaia community has chosen to write its processing software in Java. We explore the manifold reasons for choosing Java for this large science collaboration. Gaia processing is numerically complex but highly distributable, some parts being embarrassingly parallel. We describe the Gaia processing architecture and its realisation in Java. We delve into the astrometric solution which is the most advanced and most complex part of the processing. The Gaia simulator is also written in Java and is the most mature code in the system. This has been successfully running since about 2005 on the supercomputer "Marenostrum" in Barcelona. We relate experiences of using Java on a large shared machine. Finally we discuss Java, including some of its problems, for scientific computing.

High performance systems

Energy Technology Data Exchange (ETDEWEB)

Vigil, M.B. [comp.

1995-03-01

This document provides a written compilation of the presentations and viewgraphs from the 1994 Conference on High Speed Computing given at the High Speed Computing Conference, {open_quotes}High Performance Systems,{close_quotes} held at Gleneden Beach, Oregon, on April 18 through 21, 1994.

Can We Build a Truly High Performance Computer Which is Flexible and Transparent?

KAUST Repository

Rojas, Jhonathan Prieto; Sevilla, Galo T.; Hussain, Muhammad Mustafa

2013-01-01

cost advantage. In that context, low-cost mono-crystalline bulk silicon (100) based high performance transistors are considered as the heart of today's computers. One limitation is silicon's rigidity and brittleness. Here we show a generic batch process

Experiment Dashboard for Monitoring of the LHC Distributed Computing Systems

International Nuclear Information System (INIS)

Andreeva, J; Campos, M Devesas; Cros, J Tarragon; Gaidioz, B; Karavakis, E; Kokoszkiewicz, L; Lanciotti, E; Maier, G; Ollivier, W; Nowotka, M; Rocha, R; Sadykov, T; Saiz, P; Sargsyan, L; Sidorova, I; Tuckett, D

2011-01-01

LHC experiments are currently taking collisions data. A distributed computing model chosen by the four main LHC experiments allows physicists to benefit from resources spread all over the world. The distributed model and the scale of LHC computing activities increase the level of complexity of middleware, and also the chances of possible failures or inefficiencies in involved components. In order to ensure the required performance and functionality of the LHC computing system, monitoring the status of the distributed sites and services as well as monitoring LHC computing activities are among the key factors. Over the last years, the Experiment Dashboard team has been working on a number of applications that facilitate the monitoring of different activities: including following up jobs, transfers, and also site and service availabilities. This presentation describes Experiment Dashboard applications used by the LHC experiments and experience gained during the first months of data taking.

Department of Energy Mathematical, Information, and Computational Sciences Division: High Performance Computing and Communications Program

Energy Technology Data Exchange (ETDEWEB)

NONE

1996-11-01

This document is intended to serve two purposes. Its first purpose is that of a program status report of the considerable progress that the Department of Energy (DOE) has made since 1993, the time of the last such report (DOE/ER-0536, The DOE Program in HPCC), toward achieving the goals of the High Performance Computing and Communications (HPCC) Program. The second purpose is that of a summary report of the many research programs administered by the Mathematical, Information, and Computational Sciences (MICS) Division of the Office of Energy Research under the auspices of the HPCC Program and to provide, wherever relevant, easy access to pertinent information about MICS-Division activities via universal resource locators (URLs) on the World Wide Web (WWW).

Lightweight Provenance Service for High-Performance Computing

Energy Technology Data Exchange (ETDEWEB)

Dai, Dong; Chen, Yong; Carns, Philip; Jenkins, John; Ross, Robert

2017-09-09

Provenance describes detailed information about the history of a piece of data, containing the relationships among elements such as users, processes, jobs, and workflows that contribute to the existence of data. Provenance is key to supporting many data management functionalities that are increasingly important in operations such as identifying data sources, parameters, or assumptions behind a given result; auditing data usage; or understanding details about how inputs are transformed into outputs. Despite its importance, however, provenance support is largely underdeveloped in highly parallel architectures and systems. One major challenge is the demanding requirements of providing provenance service in situ. The need to remain lightweight and to be always on often conflicts with the need to be transparent and offer an accurate catalog of details regarding the applications and systems. To tackle this challenge, we introduce a lightweight provenance service, called LPS, for high-performance computing (HPC) systems. LPS leverages a kernel instrument mechanism to achieve transparency and introduces representative execution and flexible granularity to capture comprehensive provenance with controllable overhead. Extensive evaluations and use cases have confirmed its efficiency and usability. We believe that LPS can be integrated into current and future HPC systems to support a variety of data management needs.

Commercialization issues and funding opportunities for high-performance optoelectronic computing modules

Science.gov (United States)

Hessenbruch, John M.; Guilfoyle, Peter S.

1997-01-01

Low power, optoelectronic integrated circuits are being developed for high speed switching and data processing applications. These high performance optoelectronic computing modules consist of three primary components: vertical cavity surface emitting lasers, diffractive optical interconnect elements, and detector/amplifier/laser driver arrays. Following the design and fabrication of an HPOC module prototype, selected commercial funding sources will be evaluated to support a product development stage. These include the formation of a strategic alliance with one or more microprocessor or telecommunications vendors, and/or equity investment from one or more venture capital firms.

Distributed computing for global health

CERN Multimedia

CERN. Geneva; Schwede, Torsten; Moore, Celia; Smith, Thomas E; Williams, Brian; Grey, François

2005-01-01

Distributed computing harnesses the power of thousands of computers within organisations or over the Internet. In order to tackle global health problems, several groups of researchers have begun to use this approach to exceed by far the computing power of a single lab. This event illustrates how companies, research institutes and the general public are contributing their computing power to these efforts, and what impact this may have on a range of world health issues. Grids for neglected diseases Vincent Breton, CNRS/EGEE This talk introduces the topic of distributed computing, explaining the similarities and differences between Grid computing, volunteer computing and supercomputing, and outlines the potential of Grid computing for tackling neglected diseases where there is little economic incentive for private R&D efforts. Recent results on malaria drug design using the Grid infrastructure of the EU-funded EGEE project, which is coordinated by CERN and involves 70 partners in Europe, the US and Russi...

Quo vadis: Hydrologic inverse analyses using high-performance computing and a D-Wave quantum annealer

Science.gov (United States)

O'Malley, D.; Vesselinov, V. V.

2017-12-01

Classical microprocessors have had a dramatic impact on hydrology for decades, due largely to the exponential growth in computing power predicted by Moore's law. However, this growth is not expected to continue indefinitely and has already begun to slow. Quantum computing is an emerging alternative to classical microprocessors. Here, we demonstrated cutting edge inverse model analyses utilizing some of the best available resources in both worlds: high-performance classical computing and a D-Wave quantum annealer. The classical high-performance computing resources are utilized to build an advanced numerical model that assimilates data from O(10^5) observations, including water levels, drawdowns, and contaminant concentrations. The developed model accurately reproduces the hydrologic conditions at a Los Alamos National Laboratory contamination site, and can be leveraged to inform decision-making about site remediation. We demonstrate the use of a D-Wave 2X quantum annealer to solve hydrologic inverse problems. This work can be seen as an early step in quantum-computational hydrology. We compare and contrast our results with an early inverse approach in classical-computational hydrology that is comparable to the approach we use with quantum annealing. Our results show that quantum annealing can be useful for identifying regions of high and low permeability within an aquifer. While the problems we consider are small-scale compared to the problems that can be solved with modern classical computers, they are large compared to the problems that could be solved with early classical CPUs. Further, the binary nature of the high/low permeability problem makes it well-suited to quantum annealing, but challenging for classical computers.

Hydra: a scalable proteomic search engine which utilizes the Hadoop distributed computing framework.

Science.gov (United States)

Lewis, Steven; Csordas, Attila; Killcoyne, Sarah; Hermjakob, Henning; Hoopmann, Michael R; Moritz, Robert L; Deutsch, Eric W; Boyle, John

2012-12-05

For shotgun mass spectrometry based proteomics the most computationally expensive step is in matching the spectra against an increasingly large database of sequences and their post-translational modifications with known masses. Each mass spectrometer can generate data at an astonishingly high rate, and the scope of what is searched for is continually increasing. Therefore solutions for improving our ability to perform these searches are needed. We present a sequence database search engine that is specifically designed to run efficiently on the Hadoop MapReduce distributed computing framework. The search engine implements the K-score algorithm, generating comparable output for the same input files as the original implementation. The scalability of the system is shown, and the architecture required for the development of such distributed processing is discussed. The software is scalable in its ability to handle a large peptide database, numerous modifications and large numbers of spectra. Performance scales with the number of processors in the cluster, allowing throughput to expand with the available resources.

9th International Workshop on Parallel Tools for High Performance Computing

CERN Document Server

Hilbrich, Tobias; Niethammer, Christoph; Gracia, José; Nagel, Wolfgang; Resch, Michael

2016-01-01

High Performance Computing (HPC) remains a driver that offers huge potentials and benefits for science and society. However, a profound understanding of the computational matters and specialized software is needed to arrive at effective and efficient simulations. Dedicated software tools are important parts of the HPC software landscape, and support application developers. Even though a tool is by definition not a part of an application, but rather a supplemental piece of software, it can make a fundamental difference during the development of an application. Such tools aid application developers in the context of debugging, performance analysis, and code optimization, and therefore make a major contribution to the development of robust and efficient parallel software. This book introduces a selection of the tools presented and discussed at the 9th International Parallel Tools Workshop held in Dresden, Germany, September 2-3, 2015, which offered an established forum for discussing the latest advances in paral...

Monte Carlo in radiotherapy: experience in a distributed computational environment

Science.gov (United States)

Caccia, B.; Mattia, M.; Amati, G.; Andenna, C.; Benassi, M.; D'Angelo, A.; Frustagli, G.; Iaccarino, G.; Occhigrossi, A.; Valentini, S.

2007-06-01

New technologies in cancer radiotherapy need a more accurate computation of the dose delivered in the radiotherapeutical treatment plan, and it is important to integrate sophisticated mathematical models and advanced computing knowledge into the treatment planning (TP) process. We present some results about using Monte Carlo (MC) codes in dose calculation for treatment planning. A distributed computing resource located in the Technologies and Health Department of the Italian National Institute of Health (ISS) along with other computer facilities (CASPUR - Inter-University Consortium for the Application of Super-Computing for Universities and Research) has been used to perform a fully complete MC simulation to compute dose distribution on phantoms irradiated with a radiotherapy accelerator. Using BEAMnrc and GEANT4 MC based codes we calculated dose distributions on a plain water phantom and air/water phantom. Experimental and calculated dose values below ±2% (for depth between 5 mm and 130 mm) were in agreement both in PDD (Percentage Depth Dose) and transversal sections of the phantom. We consider these results a first step towards a system suitable for medical physics departments to simulate a complete treatment plan using remote computing facilities for MC simulations.

Guide to cloud computing for business and technology managers from distributed computing to cloudware applications

CERN Document Server

Kale, Vivek

2014-01-01

Guide to Cloud Computing for Business and Technology Managers: From Distributed Computing to Cloudware Applications unravels the mystery of cloud computing and explains how it can transform the operating contexts of business enterprises. It provides a clear understanding of what cloud computing really means, what it can do, and when it is practical to use. Addressing the primary management and operation concerns of cloudware, including performance, measurement, monitoring, and security, this pragmatic book:Introduces the enterprise applications integration (EAI) solutions that were a first ste

High Performance Computing - Power Application Programming Interface Specification Version 1.4

Energy Technology Data Exchange (ETDEWEB)

Laros III, James H. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); DeBonis, David [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Grant, Ryan [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Kelly, Suzanne M. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Levenhagen, Michael J. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Olivier, Stephen Lecler [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Pedretti, Kevin [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

2016-10-01

Measuring and controlling the power and energy consumption of high performance computing systems by various components in the software stack is an active research area [13, 3, 5, 10, 4, 21, 19, 16, 7, 17, 20, 18, 11, 1, 6, 14, 12]. Implementations in lower level software layers are beginning to emerge in some production systems, which is very welcome. To be most effective, a portable interface to measurement and control features would significantly facilitate participation by all levels of the software stack. We present a proposal for a standard power Application Programming Interface (API) that endeavors to cover the entire software space, from generic hardware interfaces to the input from the computer facility manager.

Distributed Large Data-Object Environments: End-to-End Performance Analysis of High Speed Distributed Storage Systems in Wide Area ATM Networks

Science.gov (United States)

Johnston, William; Tierney, Brian; Lee, Jason; Hoo, Gary; Thompson, Mary

1996-01-01

We have developed and deployed a distributed-parallel storage system (DPSS) in several high speed asynchronous transfer mode (ATM) wide area networks (WAN) testbeds to support several different types of data-intensive applications. Architecturally, the DPSS is a network striped disk array, but is fairly unique in that its implementation allows applications complete freedom to determine optimal data layout, replication and/or coding redundancy strategy, security policy, and dynamic reconfiguration. In conjunction with the DPSS, we have developed a 'top-to-bottom, end-to-end' performance monitoring and analysis methodology that has allowed us to characterize all aspects of the DPSS operating in high speed ATM networks. In particular, we have run a variety of performance monitoring experiments involving the DPSS in the MAGIC testbed, which is a large scale, high speed, ATM network and we describe our experience using the monitoring methodology to identify and correct problems that limit the performance of high speed distributed applications. Finally, the DPSS is part of an overall architecture for using high speed, WAN's for enabling the routine, location independent use of large data-objects. Since this is part of the motivation for a distributed storage system, we describe this architecture.

Distributed computing feasibility in a non-dedicated homogeneous distributed system

Science.gov (United States)

Leutenegger, Scott T.; Sun, Xian-He

1993-01-01

The low cost and availability of clusters of workstations have lead researchers to re-explore distributed computing using independent workstations. This approach may provide better cost/performance than tightly coupled multiprocessors. In practice, this approach often utilizes wasted cycles to run parallel jobs. The feasibility of such a non-dedicated parallel processing environment assuming workstation processes have preemptive priority over parallel tasks is addressed. An analytical model is developed to predict parallel job response times. Our model provides insight into how significantly workstation owner interference degrades parallel program performance. A new term task ratio, which relates the parallel task demand to the mean service demand of nonparallel workstation processes, is introduced. It was proposed that task ratio is a useful metric for determining how large the demand of a parallel applications must be in order to make efficient use of a non-dedicated distributed system.

A parallelization study of the general purpose Monte Carlo code MCNP4 on a distributed memory highly parallel computer

International Nuclear Information System (INIS)

Yamazaki, Takao; Fujisaki, Masahide; Okuda, Motoi; Takano, Makoto; Masukawa, Fumihiro; Naito, Yoshitaka

1993-01-01

The general purpose Monte Carlo code MCNP4 has been implemented on the Fujitsu AP1000 distributed memory highly parallel computer. Parallelization techniques developed and studied are reported. A shielding analysis function of the MCNP4 code is parallelized in this study. A technique to map a history to each processor dynamically and to map control process to a certain processor was applied. The efficiency of parallelized code is up to 80% for a typical practical problem with 512 processors. These results demonstrate the advantages of a highly parallel computer to the conventional computers in the field of shielding analysis by Monte Carlo method. (orig.)

HPDC ´12 : proceedings of the 21st ACM symposium on high-performance parallel and distributed computing, June 18-22, 2012, Delft, The Netherlands

NARCIS (Netherlands)

Epema, D.H.J.; Kielmann, T.; Ripeanu, M.

2012-01-01

Welcome to ACM HPDC 2012! This is the twenty-first year of HPDC and we are pleased to report that our community continues to grow in size, quality and reputation. The program consists of three days packed with presentations on the latest developments in high-performance parallel and distributed

Enabling the ATLAS Experiment at the LHC for High Performance Computing

CERN Document Server

AUTHOR|(CDS)2091107; Ereditato, Antonio

In this thesis, I studied the feasibility of running computer data analysis programs from the Worldwide LHC Computing Grid, in particular large-scale simulations of the ATLAS experiment at the CERN LHC, on current general purpose High Performance Computing (HPC) systems. An approach for integrating HPC systems into the Grid is proposed, which has been implemented and tested on the „Todi” HPC machine at the Swiss National Supercomputing Centre (CSCS). Over the course of the test, more than 500000 CPU-hours of processing time have been provided to ATLAS, which is roughly equivalent to the combined computing power of the two ATLAS clusters at the University of Bern. This showed that current HPC systems can be used to efficiently run large-scale simulations of the ATLAS detector and of the detected physics processes. As a first conclusion of my work, one can argue that, in perspective, running large-scale tasks on a few large machines might be more cost-effective than running on relatively small dedicated com...

A Web-based Distributed Voluntary Computing Platform for Large Scale Hydrological Computations

Science.gov (United States)

Demir, I.; Agliamzanov, R.

2014-12-01

Distributed volunteer computing can enable researchers and scientist to form large parallel computing environments to utilize the computing power of the millions of computers on the Internet, and use them towards running large scale environmental simulations and models to serve the common good of local communities and the world. Recent developments in web technologies and standards allow client-side scripting languages to run at speeds close to native application, and utilize the power of Graphics Processing Units (GPU). Using a client-side scripting language like JavaScript, we have developed an open distributed computing framework that makes it easy for researchers to write their own hydrologic models, and run them on volunteer computers. Users will easily enable their websites for visitors to volunteer sharing their computer resources to contribute running advanced hydrological models and simulations. Using a web-based system allows users to start volunteering their computational resources within seconds without installing any software. The framework distributes the model simulation to thousands of nodes in small spatial and computational sizes. A relational database system is utilized for managing data connections and queue management for the distributed computing nodes. In this paper, we present a web-based distributed volunteer computing platform to enable large scale hydrological simulations and model runs in an open and integrated environment.

Integration of Cloud resources in the LHCb Distributed Computing

CERN Document Server

Ubeda Garcia, Mario; Stagni, Federico; Cabarrou, Baptiste; Rauschmayr, Nathalie; Charpentier, Philippe; Closier, Joel

2014-01-01

This contribution describes how Cloud resources have been integrated in the LHCb Distributed Computing. LHCb is using its specific Dirac extension (LHCbDirac) as an interware for its Distributed Computing. So far, it was seamlessly integrating Grid resources and Computer clusters. The cloud extension of DIRAC (VMDIRAC) allows the integration of Cloud computing infrastructures. It is able to interact with multiple types of infrastructures in commercial and institutional clouds, supported by multiple interfaces (Amazon EC2, OpenNebula, OpenStack and CloudStack) – instantiates, monitors and manages Virtual Machines running on this aggregation of Cloud resources. Moreover, specifications for institutional Cloud resources proposed by Worldwide LHC Computing Grid (WLCG), mainly by the High Energy Physics Unix Information Exchange (HEPiX) group, have been taken into account. Several initiatives and computing resource providers in the eScience environment have already deployed IaaS in production during 2013. Keepin...

High performance parallel computing of flows in complex geometries: I. Methods

International Nuclear Information System (INIS)

Gourdain, N; Gicquel, L; Montagnac, M; Vermorel, O; Staffelbach, G; Garcia, M; Boussuge, J-F; Gazaix, M; Poinsot, T

2009-01-01

Efficient numerical tools coupled with high-performance computers, have become a key element of the design process in the fields of energy supply and transportation. However flow phenomena that occur in complex systems such as gas turbines and aircrafts are still not understood mainly because of the models that are needed. In fact, most computational fluid dynamics (CFD) predictions as found today in industry focus on a reduced or simplified version of the real system (such as a periodic sector) and are usually solved with a steady-state assumption. This paper shows how to overcome such barriers and how such a new challenge can be addressed by developing flow solvers running on high-end computing platforms, using thousands of computing cores. Parallel strategies used by modern flow solvers are discussed with particular emphases on mesh-partitioning, load balancing and communication. Two examples are used to illustrate these concepts: a multi-block structured code and an unstructured code. Parallel computing strategies used with both flow solvers are detailed and compared. This comparison indicates that mesh-partitioning and load balancing are more straightforward with unstructured grids than with multi-block structured meshes. However, the mesh-partitioning stage can be challenging for unstructured grids, mainly due to memory limitations of the newly developed massively parallel architectures. Finally, detailed investigations show that the impact of mesh-partitioning on the numerical CFD solutions, due to rounding errors and block splitting, may be of importance and should be accurately addressed before qualifying massively parallel CFD tools for a routine industrial use.

An Applet-based Anonymous Distributed Computing System.

Science.gov (United States)

Finkel, David; Wills, Craig E.; Ciaraldi, Michael J.; Amorin, Kevin; Covati, Adam; Lee, Michael

2001-01-01

Defines anonymous distributed computing systems and focuses on the specifics of a Java, applet-based approach for large-scale, anonymous, distributed computing on the Internet. Explains the possibility of a large number of computers participating in a single computation and describes a test of the functionality of the system. (Author/LRW)

Cloud object store for checkpoints of high performance computing applications using decoupling middleware

Science.gov (United States)

Bent, John M.; Faibish, Sorin; Grider, Gary

2016-04-19

Cloud object storage is enabled for checkpoints of high performance computing applications using a middleware process. A plurality of files, such as checkpoint files, generated by a plurality of processes in a parallel computing system are stored by obtaining said plurality of files from said parallel computing system; converting said plurality of files to objects using a log structured file system middleware process; and providing said objects for storage in a cloud object storage system. The plurality of processes may run, for example, on a plurality of compute nodes. The log structured file system middleware process may be embodied, for example, as a Parallel Log-Structured File System (PLFS). The log structured file system middleware process optionally executes on a burst buffer node.

Grid Computing in High Energy Physics

International Nuclear Information System (INIS)

Avery, Paul

2004-01-01

Over the next two decades, major high energy physics (HEP) experiments, particularly at the Large Hadron Collider, will face unprecedented challenges to achieving their scientific potential. These challenges arise primarily from the rapidly increasing size and complexity of HEP datasets that will be collected and the enormous computational, storage and networking resources that will be deployed by global collaborations in order to process, distribute and analyze them.Coupling such vast information technology resources to globally distributed collaborations of several thousand physicists requires extremely capable computing infrastructures supporting several key areas: (1) computing (providing sufficient computational and storage resources for all processing, simulation and analysis tasks undertaken by the collaborations); (2) networking (deploying high speed networks to transport data quickly between institutions around the world); (3) software (supporting simple and transparent access to data and software resources, regardless of location); (4) collaboration (providing tools that allow members full and fair access to all collaboration resources and enable distributed teams to work effectively, irrespective of location); and (5) education, training and outreach (providing resources and mechanisms for training students and for communicating important information to the public).It is believed that computing infrastructures based on Data Grids and optical networks can meet these challenges and can offer data intensive enterprises in high energy physics and elsewhere a comprehensive, scalable framework for collaboration and resource sharing. A number of Data Grid projects have been underway since 1999. Interestingly, the most exciting and far ranging of these projects are led by collaborations of high energy physicists, computer scientists and scientists from other disciplines in support of experiments with massive, near-term data needs. I review progress in this

High performance computer code for molecular dynamics simulations

International Nuclear Information System (INIS)

Levay, I.; Toekesi, K.

2007-01-01

Complete text of publication follows. Molecular Dynamics (MD) simulation is a widely used technique for modeling complicated physical phenomena. Since 2005 we are developing a MD simulations code for PC computers. The computer code is written in C++ object oriented programming language. The aim of our work is twofold: a) to develop a fast computer code for the study of random walk of guest atoms in Be crystal, b) 3 dimensional (3D) visualization of the particles motion. In this case we mimic the motion of the guest atoms in the crystal (diffusion-type motion), and the motion of atoms in the crystallattice (crystal deformation). Nowadays, it is common to use Graphics Devices in intensive computational problems. There are several ways to use this extreme processing performance, but never before was so easy to programming these devices as now. The CUDA (Compute Unified Device) Architecture introduced by nVidia Corporation in 2007 is a very useful for every processor hungry application. A Unified-architecture GPU include 96-128, or more stream processors, so the raw calculation performance is 576(!) GFLOPS. It is ten times faster, than the fastest dual Core CPU [Fig.1]. Our improved MD simulation software uses this new technology, which speed up our software and the code run 10 times faster in the critical calculation code segment. Although the GPU is a very powerful tool, it has a strongly paralleled structure. It means, that we have to create an algorithm, which works on several processors without deadlock. Our code currently uses 256 threads, shared and constant on-chip memory, instead of global memory, which is 100 times slower than others. It is possible to implement the total algorithm on GPU, therefore we do not need to download and upload the data in every iteration. On behalf of maximal throughput, every thread run with the same instructions

Protect Heterogeneous Environment Distributed Computing from Malicious Code Assignment

Directory of Open Access Journals (Sweden)

V. S. Gorbatov

2011-09-01

Full Text Available The paper describes the practical implementation of the protection system of heterogeneous environment distributed computing from malicious code for the assignment. A choice of technologies, development of data structures, performance evaluation of the implemented system security are conducted.

InfoMall: An Innovative Strategy for High-Performance Computing and Communications Applications Development.

Science.gov (United States)

Mills, Kim; Fox, Geoffrey

1994-01-01

Describes the InfoMall, a program led by the Northeast Parallel Architectures Center (NPAC) at Syracuse University (New York). The InfoMall features a partnership of approximately 24 organizations offering linked programs in High Performance Computing and Communications (HPCC) technology integration, software development, marketing, education and…

9th International conference on distributed computing and artificial intelligence

CERN Document Server

Santana, Juan; González, Sara; Molina, Jose; Bernardos, Ana; Rodríguez, Juan; DCAI 2012; International Symposium on Distributed Computing and Artificial Intelligence 2012

2012-01-01

The International Symposium on Distributed Computing and Artificial Intelligence 2012 (DCAI 2012) is a stimulating and productive forum where the scientific community can work towards future cooperation in Distributed Computing and Artificial Intelligence areas. This conference is a forum in which  applications of innovative techniques for solving complex problems will be presented. Artificial intelligence is changing our society. Its application in distributed environments, such as the internet, electronic commerce, environment monitoring, mobile communications, wireless devices, distributed computing, to mention only a few, is continuously increasing, becoming an element of high added value with social and economic potential, in industry, quality of life, and research. These technologies are changing constantly as a result of the large research and technical effort being undertaken in both universities and businesses. The exchange of ideas between scientists and technicians from both the academic and indus...

A C++11 implementation of arbitrary-rank tensors for high-performance computing

Science.gov (United States)

Aragón, Alejandro M.

2014-11-01

This article discusses an efficient implementation of tensors of arbitrary rank by using some of the idioms introduced by the recently published C++ ISO Standard (C++11). With the aims at providing a basic building block for high-performance computing, a single Array class template is carefully crafted, from which vectors, matrices, and even higher-order tensors can be created. An expression template facility is also built around the array class template to provide convenient mathematical syntax. As a result, by using templates, an extra high-level layer is added to the C++ language when dealing with algebraic objects and their operations, without compromising performance. The implementation is tested running on both CPU and GPU.

Human and Robotic Space Mission Use Cases for High-Performance Spaceflight Computing

Science.gov (United States)

Some, Raphael; Doyle, Richard; Bergman, Larry; Whitaker, William; Powell, Wesley; Johnson, Michael; Goforth, Montgomery; Lowry, Michael

2013-01-01

Spaceflight computing is a key resource in NASA space missions and a core determining factor of spacecraft capability, with ripple effects throughout the spacecraft, end-to-end system, and mission. Onboard computing can be aptly viewed as a "technology multiplier" in that advances provide direct dramatic improvements in flight functions and capabilities across the NASA mission classes, and enable new flight capabilities and mission scenarios, increasing science and exploration return. Space-qualified computing technology, however, has not advanced significantly in well over ten years and the current state of the practice fails to meet the near- to mid-term needs of NASA missions. Recognizing this gap, the NASA Game Changing Development Program (GCDP), under the auspices of the NASA Space Technology Mission Directorate, commissioned a study on space-based computing needs, looking out 15-20 years. The study resulted in a recommendation to pursue high-performance spaceflight computing (HPSC) for next-generation missions, and a decision to partner with the Air Force Research Lab (AFRL) in this development.

US QCD computational performance studies with PERI

International Nuclear Information System (INIS)

Zhang, Y; Fowler, R; Huck, K; Malony, A; Porterfield, A; Reed, D; Shende, S; Taylor, V; Wu, X

2007-01-01

We report on some of the interactions between two SciDAC projects: The National Computational Infrastructure for Lattice Gauge Theory (USQCD), and the Performance Engineering Research Institute (PERI). Many modern scientific programs consistently report the need for faster computational resources to maintain global competitiveness. However, as the size and complexity of emerging high end computing (HEC) systems continue to rise, achieving good performance on such systems is becoming ever more challenging. In order to take full advantage of the resources, it is crucial to understand the characteristics of relevant scientific applications and the systems these applications are running on. Using tools developed under PERI and by other performance measurement researchers, we studied the performance of two applications, MILC and Chroma, on several high performance computing systems at DOE laboratories. In the case of Chroma, we discuss how the use of C++ and modern software engineering and programming methods are driving the evolution of performance tools

Distributed interactive graphics applications in computational fluid dynamics

International Nuclear Information System (INIS)

Rogers, S.E.; Buning, P.G.; Merritt, F.J.

1987-01-01

Implementation of two distributed graphics programs used in computational fluid dynamics is discussed. Both programs are interactive in nature. They run on a CRAY-2 supercomputer and use a Silicon Graphics Iris workstation as the front-end machine. The hardware and supporting software are from the Numerical Aerodynamic Simulation project. The supercomputer does all numerically intensive work and the workstation, as the front-end machine, allows the user to perform real-time interactive transformations on the displayed data. The first program was written as a distributed program that computes particle traces for fluid flow solutions existing on the supercomputer. The second is an older post-processing and plotting program modified to run in a distributed mode. Both programs have realized a large increase in speed over that obtained using a single machine. By using these programs, one can learn quickly about complex features of a three-dimensional flow field. Some color results are presented

Studies on high performance Timeslice building on the CBM FLES

Energy Technology Data Exchange (ETDEWEB)

Hartmann, Helvi [Frankfurt Institute for Advanced Studies, Goethe University, Frankfurt (Germany); Collaboration: CBM-Collaboration

2015-07-01

In contrast to already existing high energy physics experiments the Compressed Baryonic Matter (CBM) experiment collects all data untriggered. The First-level Event Selector (FLES), which denotes a high performance computer cluster, processes the very high incoming data rate of 1 TByte/s and performs a full online event reconstruction. For this task it needs to access the raw detector data in time intervals referred to as Timeslices. In order to construct the Timeslices, the FLES Timeslice building has to combine data from all input links and distribute them via a high-performance network to the compute nodes. For fast data transfer the Infiniband network has proven to be appropriate. One option to address the network is using Infiniband (RDMA) Verbs directly and potentially making best use of Infiniband. However, it is a very low-level implementation relying on the hardware and neglecting other possible network technologies in the future. Another approach is to apply a high-level API like MPI which is independent of the underlying hardware and suitable for less error prone software development. I present the given possibilities and show the results of benchmarks ran on high-performance computing clusters. The solutions are evaluated regarding the Timeslice building in CBM.

High Performance Spaceflight Computing (HPSC)

Data.gov (United States)

National Aeronautics and Space Administration — Space-based computing has not kept up with the needs of current and future NASA missions. We are developing a next-generation flight computing system that addresses...

Towards the development of run times leveraging virtualization for high performance computing

International Nuclear Information System (INIS)

Diakhate, F.

2010-12-01

In recent years, there has been a growing interest in using virtualization to improve the efficiency of data centers. This success is rooted in virtualization's excellent fault tolerance and isolation properties, in the overall flexibility it brings, and in its ability to exploit multi-core architectures efficiently. These characteristics also make virtualization an ideal candidate to tackle issues found in new compute cluster architectures. However, in spite of recent improvements in virtualization technology, overheads in the execution of parallel applications remain, which prevent its use in the field of high performance computing. In this thesis, we propose a virtual device dedicated to message passing between virtual machines, so as to improve the performance of parallel applications executed in a cluster of virtual machines. We also introduce a set of techniques facilitating the deployment of virtualized parallel applications. These functionalities have been implemented as part of a runtime system which allows to benefit from virtualization's properties in a way that is as transparent as possible to the user while minimizing performance overheads. (author)

HEP@Home - A distributed computing system based on BOINC

CERN Document Server

Amorim, A; Andrade, P; Amorim, Antonio; Villate, Jaime; Andrade, Pedro

2005-01-01

Project SETI@HOME has proven to be one of the biggest successes of distributed computing during the last years. With a quite simple approach SETI manages to process large volumes of data using a vast amount of distributed computer power. To extend the generic usage of this kind of distributed computing tools, BOINC is being developed. In this paper we propose HEP@HOME, a BOINC version tailored to the specific requirements of the High Energy Physics (HEP) community. The HEP@HOME will be able to process large amounts of data using virtually unlimited computing power, as BOINC does, and it should be able to work according to HEP specifications. In HEP the amounts of data to be analyzed or reconstructed are of central importance. Therefore, one of the design principles of this tool is to avoid data transfer. This will allow scientists to run their analysis applications and taking advantage of a large number of CPUs. This tool also satisfies other important requirements in HEP, namely, security, fault-tolerance an...

Integration of Cloud resources in the LHCb Distributed Computing

Science.gov (United States)

Úbeda García, Mario; Méndez Muñoz, Víctor; Stagni, Federico; Cabarrou, Baptiste; Rauschmayr, Nathalie; Charpentier, Philippe; Closier, Joel

2014-06-01

This contribution describes how Cloud resources have been integrated in the LHCb Distributed Computing. LHCb is using its specific Dirac extension (LHCbDirac) as an interware for its Distributed Computing. So far, it was seamlessly integrating Grid resources and Computer clusters. The cloud extension of DIRAC (VMDIRAC) allows the integration of Cloud computing infrastructures. It is able to interact with multiple types of infrastructures in commercial and institutional clouds, supported by multiple interfaces (Amazon EC2, OpenNebula, OpenStack and CloudStack) - instantiates, monitors and manages Virtual Machines running on this aggregation of Cloud resources. Moreover, specifications for institutional Cloud resources proposed by Worldwide LHC Computing Grid (WLCG), mainly by the High Energy Physics Unix Information Exchange (HEPiX) group, have been taken into account. Several initiatives and computing resource providers in the eScience environment have already deployed IaaS in production during 2013. Keeping this on mind, pros and cons of a cloud based infrasctructure have been studied in contrast with the current setup. As a result, this work addresses four different use cases which represent a major improvement on several levels of our infrastructure. We describe the solution implemented by LHCb for the contextualisation of the VMs based on the idea of Cloud Site. We report on operational experience of using in production several institutional Cloud resources that are thus becoming integral part of the LHCb Distributed Computing resources. Furthermore, we describe as well the gradual migration of our Service Infrastructure towards a fully distributed architecture following the Service as a Service (SaaS) model.

Integration of cloud resources in the LHCb distributed computing

International Nuclear Information System (INIS)

García, Mario Úbeda; Stagni, Federico; Cabarrou, Baptiste; Rauschmayr, Nathalie; Charpentier, Philippe; Closier, Joel; Muñoz, Víctor Méndez

2014-01-01

This contribution describes how Cloud resources have been integrated in the LHCb Distributed Computing. LHCb is using its specific Dirac extension (LHCbDirac) as an interware for its Distributed Computing. So far, it was seamlessly integrating Grid resources and Computer clusters. The cloud extension of DIRAC (VMDIRAC) allows the integration of Cloud computing infrastructures. It is able to interact with multiple types of infrastructures in commercial and institutional clouds, supported by multiple interfaces (Amazon EC2, OpenNebula, OpenStack and CloudStack) – instantiates, monitors and manages Virtual Machines running on this aggregation of Cloud resources. Moreover, specifications for institutional Cloud resources proposed by Worldwide LHC Computing Grid (WLCG), mainly by the High Energy Physics Unix Information Exchange (HEPiX) group, have been taken into account. Several initiatives and computing resource providers in the eScience environment have already deployed IaaS in production during 2013. Keeping this on mind, pros and cons of a cloud based infrasctructure have been studied in contrast with the current setup. As a result, this work addresses four different use cases which represent a major improvement on several levels of our infrastructure. We describe the solution implemented by LHCb for the contextualisation of the VMs based on the idea of Cloud Site. We report on operational experience of using in production several institutional Cloud resources that are thus becoming integral part of the LHCb Distributed Computing resources. Furthermore, we describe as well the gradual migration of our Service Infrastructure towards a fully distributed architecture following the Service as a Service (SaaS) model.

Context-aware distributed cloud computing using CloudScheduler

Science.gov (United States)

Seuster, R.; Leavett-Brown, CR; Casteels, K.; Driemel, C.; Paterson, M.; Ring, D.; Sobie, RJ; Taylor, RP; Weldon, J.

2017-10-01

The distributed cloud using the CloudScheduler VM provisioning service is one of the longest running systems for HEP workloads. It has run millions of jobs for ATLAS and Belle II over the past few years using private and commercial clouds around the world. Our goal is to scale the distributed cloud to the 10,000-core level, with the ability to run any type of application (low I/O, high I/O and high memory) on any cloud. To achieve this goal, we have been implementing changes that utilize context-aware computing designs that are currently employed in the mobile communication industry. Context-awareness makes use of real-time and archived data to respond to user or system requirements. In our distributed cloud, we have many opportunistic clouds with no local HEP services, software or storage repositories. A context-aware design significantly improves the reliability and performance of our system by locating the nearest location of the required services. We describe how we are collecting and managing contextual information from our workload management systems, the clouds, the virtual machines and our services. This information is used not only to monitor the system but also to carry out automated corrective actions. We are incrementally adding new alerting and response services to our distributed cloud. This will enable us to scale the number of clouds and virtual machines. Further, a context-aware design will enable us to run analysis or high I/O application on opportunistic clouds. We envisage an open-source HTTP data federation (for example, the DynaFed system at CERN) as a service that would provide us access to existing storage elements used by the HEP experiments.

The design development and commissioning of two distributed computer based boiler control systems

International Nuclear Information System (INIS)

Collier, D.; Johnstone, L.R.; Pringle, S.T.; Walker, R.W.

1980-01-01

The CEBG N.E. Region has recently commissioned two major boiler control schemes using distributed computer control system. Both systems have considerable development potential to allow modifications to meet changing operational requirements. The distributed approach to control was chosen in both instances so as to achieve high control system availability and as a method of easing the commissioning programs. The experience gained with these two projects has reinforced the view that distributed computer systems show advantages over centralised single computers especially if software is designed for the distributed system. (auth)

International Conference on Modern Mathematical Methods and High Performance Computing in Science and Technology

CERN Document Server

Srivastava, HM; Venturino, Ezio; Resch, Michael; Gupta, Vijay

2016-01-01

The book discusses important results in modern mathematical models and high performance computing, such as applied operations research, simulation of operations, statistical modeling and applications, invisibility regions and regular meta-materials, unmanned vehicles, modern radar techniques/SAR imaging, satellite remote sensing, coding, and robotic systems. Furthermore, it is valuable as a reference work and as a basis for further study and research. All contributing authors are respected academicians, scientists and researchers from around the globe. All the papers were presented at the international conference on Modern Mathematical Methods and High Performance Computing in Science & Technology (M3HPCST 2015), held at Raj Kumar Goel Institute of Technology, Ghaziabad, India, from 27–29 December 2015, and peer-reviewed by international experts. The conference provided an exceptional platform for leading researchers, academicians, developers, engineers and technocrats from a broad range of disciplines ...

ATLAS Distributed Computing in LHC Run2

International Nuclear Information System (INIS)

Campana, Simone

2015-01-01

The ATLAS Distributed Computing infrastructure has evolved after the first period of LHC data taking in order to cope with the challenges of the upcoming LHC Run-2. An increase in both the data rate and the computing demands of the Monte-Carlo simulation, as well as new approaches to ATLAS analysis, dictated a more dynamic workload management system (Prodsys-2) and data management system (Rucio), overcoming the boundaries imposed by the design of the old computing model. In particular, the commissioning of new central computing system components was the core part of the migration toward a flexible computing model. A flexible computing utilization exploring the use of opportunistic resources such as HPC, cloud, and volunteer computing is embedded in the new computing model; the data access mechanisms have been enhanced with the remote access, and the network topology and performance is deeply integrated into the core of the system. Moreover, a new data management strategy, based on a defined lifetime for each dataset, has been defined to better manage the lifecycle of the data. In this note, an overview of an operational experience of the new system and its evolution is presented. (paper)

High-performance scalable Information Service for the ATLAS experiment

CERN Document Server

Kolos, S; The ATLAS collaboration; Hauser, R

2012-01-01

The ATLAS experiment is being operated by highly distributed computing system which is constantly producing a lot of status information which is used to monitor the experiment operational conditions as well as to access the quality of the physics data being taken. For example the ATLAS High Level Trigger(HLT) algorithms are executed on the online computing farm consisting from about 1500 nodes. Each HLT algorithm is producing few thousands histograms, which have to be integrated over the whole farm and carefully analyzed in order to properly tune the event rejection. In order to handle such non-physics data the Information Service (IS) facility has been developed in the scope of the ATLAS TDAQ project. The IS provides high-performance scalable solution for information exchange in distributed environment. In the course of an ATLAS data taking session the IS handles about hundred gigabytes of information which is being constantly updated with the update interval varying from a second to few tens of seconds. IS ...

Performance Measurements in a High Throughput Computing Environment

CERN Document Server

AUTHOR|(CDS)2145966; Gribaudo, Marco

The IT infrastructures of companies and research centres are implementing new technologies to satisfy the increasing need of computing resources for big data analysis. In this context, resource profiling plays a crucial role in identifying areas where the improvement of the utilisation efficiency is needed. In order to deal with the profiling and optimisation of computing resources, two complementary approaches can be adopted: the measurement-based approach and the model-based approach. The measurement-based approach gathers and analyses performance metrics executing benchmark applications on computing resources. Instead, the model-based approach implies the design and implementation of a model as an abstraction of the real system, selecting only those aspects relevant to the study. This Thesis originates from a project carried out by the author within the CERN IT department. CERN is an international scientific laboratory that conducts fundamental researches in the domain of elementary particle physics. The p...

10th International Symposium on Intelligent Distributed Computing

CERN Document Server

Seghrouchni, Amal; Beynier, Aurélie; Camacho, David; Herpson, Cédric; Hindriks, Koen; Novais, Paulo

2017-01-01

This book presents the combined peer-reviewed proceedings of the tenth International Symposium on Intelligent Distributed Computing (IDC’2016), which was held in Paris, France from October 10th to 12th, 2016. The 23 contributions address a range of topics related to theory and application of intelligent distributed computing, including: Intelligent Distributed Agent-Based Systems, Ambient Intelligence and Social Networks, Computational Sustainability, Intelligent Distributed Knowledge Representation and Processing, Smart Networks, Networked Intelligence and Intelligent Distributed Applications, amongst others.

Polymer waveguides for electro-optical integration in data centers and high-performance computers.

Science.gov (United States)

Dangel, Roger; Hofrichter, Jens; Horst, Folkert; Jubin, Daniel; La Porta, Antonio; Meier, Norbert; Soganci, Ibrahim Murat; Weiss, Jonas; Offrein, Bert Jan

2015-02-23

To satisfy the intra- and inter-system bandwidth requirements of future data centers and high-performance computers, low-cost low-power high-throughput optical interconnects will become a key enabling technology. To tightly integrate optics with the computing hardware, particularly in the context of CMOS-compatible silicon photonics, optical printed circuit boards using polymer waveguides are considered as a formidable platform. IBM Research has already demonstrated the essential silicon photonics and interconnection building blocks. A remaining challenge is electro-optical packaging, i.e., the connection of the silicon photonics chips with the system. In this paper, we present a new single-mode polymer waveguide technology and a scalable method for building the optical interface between silicon photonics chips and single-mode polymer waveguides.

Power/energy use cases for high performance computing

Energy Technology Data Exchange (ETDEWEB)

Laros, James H. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Kelly, Suzanne M. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Hammond, Steven [National Renewable Energy Lab. (NREL), Golden, CO (United States); Elmore, Ryan [National Renewable Energy Lab. (NREL), Golden, CO (United States); Munch, Kristin [National Renewable Energy Lab. (NREL), Golden, CO (United States)

2013-12-01

Power and Energy have been identified as a first order challenge for future extreme scale high performance computing (HPC) systems. In practice the breakthroughs will need to be provided by the hardware vendors. But to make the best use of the solutions in an HPC environment, it will likely require periodic tuning by facility operators and software components. This document describes the actions and interactions needed to maximize power resources. It strives to cover the entire operational space in which an HPC system occupies. The descriptions are presented as formal use cases, as documented in the Unified Modeling Language Specification [1]. The document is intended to provide a common understanding to the HPC community of the necessary management and control capabilities. Assuming a common understanding can be achieved, the next step will be to develop a set of Application Programing Interfaces (APIs) to which hardware vendors and software developers could utilize to steer power consumption.

High-performance implementation of Chebyshev filter diagonalization for interior eigenvalue computations

Energy Technology Data Exchange (ETDEWEB)

Pieper, Andreas [Ernst-Moritz-Arndt-Universität Greifswald (Germany); Kreutzer, Moritz [Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany); Alvermann, Andreas, E-mail: alvermann@physik.uni-greifswald.de [Ernst-Moritz-Arndt-Universität Greifswald (Germany); Galgon, Martin [Bergische Universität Wuppertal (Germany); Fehske, Holger [Ernst-Moritz-Arndt-Universität Greifswald (Germany); Hager, Georg [Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany); Lang, Bruno [Bergische Universität Wuppertal (Germany); Wellein, Gerhard [Friedrich-Alexander-Universität Erlangen-Nürnberg (Germany)

2016-11-15

We study Chebyshev filter diagonalization as a tool for the computation of many interior eigenvalues of very large sparse symmetric matrices. In this technique the subspace projection onto the target space of wanted eigenvectors is approximated with filter polynomials obtained from Chebyshev expansions of window functions. After the discussion of the conceptual foundations of Chebyshev filter diagonalization we analyze the impact of the choice of the damping kernel, search space size, and filter polynomial degree on the computational accuracy and effort, before we describe the necessary steps towards a parallel high-performance implementation. Because Chebyshev filter diagonalization avoids the need for matrix inversion it can deal with matrices and problem sizes that are presently not accessible with rational function methods based on direct or iterative linear solvers. To demonstrate the potential of Chebyshev filter diagonalization for large-scale problems of this kind we include as an example the computation of the 10{sup 2} innermost eigenpairs of a topological insulator matrix with dimension 10{sup 9} derived from quantum physics applications.

DIRAC distributed computing services

International Nuclear Information System (INIS)

Tsaregorodtsev, A

2014-01-01

DIRAC Project provides a general-purpose framework for building distributed computing systems. It is used now in several HEP and astrophysics experiments as well as for user communities in other scientific domains. There is a large interest from smaller user communities to have a simple tool like DIRAC for accessing grid and other types of distributed computing resources. However, small experiments cannot afford to install and maintain dedicated services. Therefore, several grid infrastructure projects are providing DIRAC services for their respective user communities. These services are used for user tutorials as well as to help porting the applications to the grid for a practical day-to-day work. The services are giving access typically to several grid infrastructures as well as to standalone computing clusters accessible by the target user communities. In the paper we will present the experience of running DIRAC services provided by the France-Grilles NGI and other national grid infrastructure projects.

A uniform approach for programming distributed heterogeneous computing systems.

Science.gov (United States)

Grasso, Ivan; Pellegrini, Simone; Cosenza, Biagio; Fahringer, Thomas

2014-12-01

Large-scale compute clusters of heterogeneous nodes equipped with multi-core CPUs and GPUs are getting increasingly popular in the scientific community. However, such systems require a combination of different programming paradigms making application development very challenging. In this article we introduce libWater, a library-based extension of the OpenCL programming model that simplifies the development of heterogeneous distributed applications. libWater consists of a simple interface, which is a transparent abstraction of the underlying distributed architecture, offering advanced features such as inter-context and inter-node device synchronization. It provides a runtime system which tracks dependency information enforced by event synchronization to dynamically build a DAG of commands, on which we automatically apply two optimizations: collective communication pattern detection and device-host-device copy removal. We assess libWater's performance in three compute clusters available from the Vienna Scientific Cluster, the Barcelona Supercomputing Center and the University of Innsbruck, demonstrating improved performance and scaling with different test applications and configurations.

Implementation of the Principal Component Analysis onto High-Performance Computer Facilities for Hyperspectral Dimensionality Reduction: Results and Comparisons

Directory of Open Access Journals (Sweden)

Ernestina Martel

2018-06-01

Full Text Available Dimensionality reduction represents a critical preprocessing step in order to increase the efficiency and the performance of many hyperspectral imaging algorithms. However, dimensionality reduction algorithms, such as the Principal Component Analysis (PCA, suffer from their computationally demanding nature, becoming advisable for their implementation onto high-performance computer architectures for applications under strict latency constraints. This work presents the implementation of the PCA algorithm onto two different high-performance devices, namely, an NVIDIA Graphics Processing Unit (GPU and a Kalray manycore, uncovering a highly valuable set of tips and tricks in order to take full advantage of the inherent parallelism of these high-performance computing platforms, and hence, reducing the time that is required to process a given hyperspectral image. Moreover, the achieved results obtained with different hyperspectral images have been compared with the ones that were obtained with a field programmable gate array (FPGA-based implementation of the PCA algorithm that has been recently published, providing, for the first time in the literature, a comprehensive analysis in order to highlight the pros and cons of each option.

Computer Graphics Simulations of Sampling Distributions.

Science.gov (United States)

Gordon, Florence S.; Gordon, Sheldon P.

1989-01-01

Describes the use of computer graphics simulations to enhance student understanding of sampling distributions that arise in introductory statistics. Highlights include the distribution of sample proportions, the distribution of the difference of sample means, the distribution of the difference of sample proportions, and the distribution of sample…

High Performance Computing and Storage Requirements for Nuclear Physics: Target 2017

Energy Technology Data Exchange (ETDEWEB)

Gerber, Richard [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Wasserman, Harvey [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

2014-04-30

In April 2014, NERSC, ASCR, and the DOE Office of Nuclear Physics (NP) held a review to characterize high performance computing (HPC) and storage requirements for NP research through 2017. This review is the 12th in a series of reviews held by NERSC and Office of Science program offices that began in 2009. It is the second for NP, and the final in the second round of reviews that covered the six Office of Science program offices. This report is the result of that review

Software Quality Measurement for Distributed Systems. Volume 3. Distributed Computing Systems: Impact on Software Quality.

Science.gov (United States)

1983-07-01

Distributed Computing Systems impact DrnwrR - aehR on Sotwar Quaity. PERFORMING 010. REPORT NUMBER 7. AUTNOW) S. CONTRACT OR GRANT "UMBER(*)IS ThomasY...C31 Application", "Space Systems Network", "Need for Distributed Database Management", and "Adaptive Routing". This is discussed in the last para ...data reduction, buffering, encryption, and error detection and correction functions. Examples of such data streams include imagery data, video

Peer-to-peer computing for secure high performance data copying

International Nuclear Information System (INIS)

Hanushevsky, A.; Trunov, A.; Cottrell, L.

2001-01-01

The BaBar Copy Program (bbcp) is an excellent representative of peer-to-peer (P2P) computing. It is also a pioneering application of its type in the P2P arena. Built upon the foundation of its predecessor, Secure Fast Copy (sfcp), bbcp incorporates significant improvements performance and usability. As with sfcp, bbcp uses ssh for authentication; providing an elegant and simple working model--if you can ssh to a location, you can copy files to or from that location. To fully support this notion, bbcp transparently supports 3rd party copy operations. The program also incorporates several mechanism to deal with firewall security; the bane of P2P computing. To achieve high performance in a wide area network, bbcp allows a user to independently specify, the number of parallel network streams, tcp window size, and the file I/O blocking factor. Using these parameters, data is pipelined from source to target to provide a uniform traffic pattern that maximizes router efficiency. For improved recoverability, bbcp also keeps track of copy operations so that an operation can be restarted from the point of failure at a later time; minimizing the amount of network traffic in the event of a copy failure. Here, the authors present the bbcp architecture, it's various features, and the reasons for their inclusion

Peer-to-Peer Computing for Secure High Performance Data Copying

International Nuclear Information System (INIS)

2002-01-01

The BaBar Copy Program (bbcp) is an excellent representative of peer-to-peer (P2P) computing. It is also a pioneering application of its type in the P2P arena. Built upon the foundation of its predecessor, Secure Fast Copy (sfcp), bbcp incorporates significant improvements performance and usability. As with sfcp, bbcp uses ssh for authentication; providing an elegant and simple working model -- if you can ssh to a location, you can copy files to or from that location. To fully support this notion, bbcp transparently supports 3rd party copy operations. The program also incorporates several mechanism to deal with firewall security; the bane of P2P computing. To achieve high performance in a wide area network, bbcp allows a user to independently specify, the number of parallel network streams, tcp window size, and the file I/O blocking factor. Using these parameters, data is pipelined from source to target to provide a uniform traffic pattern that maximizes router efficiency. For improved recoverability, bbcp also keeps track of copy operations so that an operation can be restarted from the point of failure at a later time; minimizing the amount of network traffic in the event of a copy failure. Here, we preset the bbcp architecture, it's various features, and the reasons for their inclusion

Using High Performance Computing to Examine the Processes of Neurogenesis Underlying Pattern Separation/Completion of Episodic Information.

Energy Technology Data Exchange (ETDEWEB)

Aimone, James Bradley [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Betty, Rita [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

2015-03-01

Using High Performance Computing to Examine the Processes of Neurogenesis Underlying Pattern Separation/Completion of Episodic Information - Sandia researchers developed novel methods and metrics for studying the computational function of neurogenesis, thus generating substantial impact to the neuroscience and neural computing communities. This work could benefit applications in machine learning and other analysis activities.

GISpark: A Geospatial Distributed Computing Platform for Spatiotemporal Big Data

Science.gov (United States)

Wang, S.; Zhong, E.; Wang, E.; Zhong, Y.; Cai, W.; Li, S.; Gao, S.

2016-12-01

Geospatial data are growing exponentially because of the proliferation of cost effective and ubiquitous positioning technologies such as global remote-sensing satellites and location-based devices. Analyzing large amounts of geospatial data can provide great value for both industrial and scientific applications. Data- and compute- intensive characteristics inherent in geospatial big data increasingly pose great challenges to technologies of data storing, computing and analyzing. Such challenges require a scalable and efficient architecture that can store, query, analyze, and visualize large-scale spatiotemporal data. Therefore, we developed GISpark - a geospatial distributed computing platform for processing large-scale vector, raster and stream data. GISpark is constructed based on the latest virtualized computing infrastructures and distributed computing architecture. OpenStack and Docker are used to build multi-user hosting cloud computing infrastructure for GISpark. The virtual storage systems such as HDFS, Ceph, MongoDB are combined and adopted for spatiotemporal data storage management. Spark-based algorithm framework is developed for efficient parallel computing. Within this framework, SuperMap GIScript and various open-source GIS libraries can be integrated into GISpark. GISpark can also integrated with scientific computing environment (e.g., Anaconda), interactive computing web applications (e.g., Jupyter notebook), and machine learning tools (e.g., TensorFlow/Orange). The associated geospatial facilities of GISpark in conjunction with the scientific computing environment, exploratory spatial data analysis tools, temporal data management and analysis systems make up a powerful geospatial computing tool. GISpark not only provides spatiotemporal big data processing capacity in the geospatial field, but also provides spatiotemporal computational model and advanced geospatial visualization tools that deals with other domains related with spatial property. We

Distributed computing for macromolecular crystallography.

Science.gov (United States)

Krissinel, Evgeny; Uski, Ville; Lebedev, Andrey; Winn, Martyn; Ballard, Charles

2018-02-01

Modern crystallographic computing is characterized by the growing role of automated structure-solution pipelines, which represent complex expert systems utilizing a number of program components, decision makers and databases. They also require considerable computational resources and regular database maintenance, which is increasingly more difficult to provide at the level of individual desktop-based CCP4 setups. On the other hand, there is a significant growth in data processed in the field, which brings up the issue of centralized facilities for keeping both the data collected and structure-solution projects. The paradigm of distributed computing and data management offers a convenient approach to tackling these problems, which has become more attractive in recent years owing to the popularity of mobile devices such as tablets and ultra-portable laptops. In this article, an overview is given of developments by CCP4 aimed at bringing distributed crystallographic computations to a wide crystallographic community.

Heterogeneous Gpu&Cpu Cluster For High Performance Computing In Cryptography

Directory of Open Access Journals (Sweden)

Michał Marks

2012-01-01

Full Text Available This paper addresses issues associated with distributed computing systems andthe application of mixed GPU&CPU technology to data encryption and decryptionalgorithms. We describe a heterogenous cluster HGCC formed by twotypes of nodes: Intel processor with NVIDIA graphics processing unit and AMDprocessor with AMD graphics processing unit (formerly ATI, and a novel softwareframework that hides the heterogeneity of our cluster and provides toolsfor solving complex scientific and engineering problems. Finally, we present theresults of numerical experiments. The considered case study is concerned withparallel implementations of selected cryptanalysis algorithms. The main goal ofthe paper is to show the wide applicability of the GPU&CPU technology tolarge scale computation and data processing.

Scalability of DL_POLY on High Performance Computing Platform

CSIR Research Space (South Africa)

Mabakane, Mabule S

2017-12-01

Full Text Available stream_source_info Mabakanea_19979_2017.pdf.txt stream_content_type text/plain stream_size 33716 Content-Encoding UTF-8 stream_name Mabakanea_19979_2017.pdf.txt Content-Type text/plain; charset=UTF-8 SACJ 29(3) December... when using many processors within the compute nodes of the supercomputer. The type of the processors of compute nodes and their memory also play an important role in the overall performance of the parallel application running on a supercomputer. DL...

Cost effective distributed computing for Monte Carlo radiation dosimetry

International Nuclear Information System (INIS)

Wise, K.N.; Webb, D.V.

2000-01-01

Full text: An inexpensive computing facility has been established for performing repetitive Monte Carlo simulations with the BEAM and EGS4/EGSnrc codes of linear accelerator beams, for calculating effective dose from diagnostic imaging procedures and of ion chambers and phantoms used for the Australian high energy absorbed dose standards. The facility currently consists of 3 dual-processor 450 MHz processor PCs linked by a high speed LAN. The 3 PCs can be accessed either locally from a single keyboard/monitor/mouse combination using a SwitchView controller or remotely via a computer network from PCs with suitable communications software (e.g. Telnet, Kermit etc). All 3 PCs are identically configured to have the Red Hat Linux 6.0 operating system. A Fortran compiler and the BEAM and EGS4/EGSnrc codes are available on the 3 PCs. The preparation of sequences of jobs utilising the Monte Carlo codes is simplified using load-distributing software (enFuzion 6.0 marketed by TurboLinux Inc, formerly Cluster from Active Tools) which efficiently distributes the computing load amongst all 6 processors. We describe 3 applications of the system - (a) energy spectra from radiotherapy sources, (b) mean mass-energy absorption coefficients and stopping powers for absolute absorbed dose standards and (c) dosimetry for diagnostic procedures; (a) and (b) are based on the transport codes BEAM and FLURZnrc while (c) is a Fortran/EGS code developed at ARPANSA. Efficiency gains ranged from 3 for (c) to close to the theoretical maximum of 6 for (a) and (b), with the gain depending on the amount of 'bookkeeping' to begin each task and the time taken to complete a single task. We have found the use of a load-balancing batch processing system with many PCs to be an economical way of achieving greater productivity for Monte Carlo calculations or of any computer intensive task requiring many runs with different parameters. Copyright (2000) Australasian College of Physical Scientists and

Ion Exchange Distribution Coefficient Tests and Computer Modeling at High Ionic Strength Supporting Technetium Removal Resin Maturation

Energy Technology Data Exchange (ETDEWEB)

Nash, Charles A. [Savannah River Site (SRS), Aiken, SC (United States). Savannah River National Lab. (SRNL); Hamm, L. Larry [Savannah River Site (SRS), Aiken, SC (United States). Savannah River National Lab. (SRNL); Smith, Frank G. [Savannah River Site (SRS), Aiken, SC (United States). Savannah River National Lab. (SRNL); McCabe, Daniel J. [Savannah River Site (SRS), Aiken, SC (United States). Savannah River National Lab. (SRNL)

2014-12-19

The primary treatment of the tank waste at the DOE Hanford site will be done in the Waste Treatment and Immobilization Plant (WTP) that is currently under construction. The baseline plan for this facility is to treat the waste, splitting it into High Level Waste (HLW) and Low Activity Waste (LAW). Both waste streams are then separately vitrified as glass and poured into canisters for disposition. The LAW glass will be disposed onsite in the Integrated Disposal Facility (IDF). There are currently no plans to treat the waste to remove technetium, so its disposition path is the LAW glass. Due to the water solubility properties of pertechnetate and long half-life of ⁹⁹Tc, effective management of ⁹⁹Tc is important to the overall success of the Hanford River Protection Project mission. To achieve the full target WTP throughput, additional LAW immobilization capacity is needed, and options are being explored to immobilize the supplemental LAW portion of the tank waste. Removal of ⁹⁹Tc, followed by off-site disposal, would eliminate a key risk contributor for the IDF Performance Assessment (PA) for supplemental waste forms, and has potential to reduce treatment and disposal costs. Washington River Protection Solutions (WRPS) is developing some conceptual flow sheets for supplemental LAW treatment and disposal that could benefit from technetium removal. One of these flowsheets will specifically examine removing ⁹⁹Tc from the LAW feed stream to supplemental immobilization. To enable an informed decision regarding the viability of technetium removal, further maturation of available technologies is being performed. This report contains results of experimental ion exchange distribution coefficient testing and computer modeling using the resin SuperLig^® 639^a to selectively remove perrhenate from high ionic strength simulated LAW. It is advantageous to operate at higher concentration in order to treat the waste

High-Bandwidth Tactical-Network Data Analysis in a High-Performance-Computing (HPC) Environment: Packet-Level Analysis

Science.gov (United States)

2015-09-01

individual fragments using the hash-based method. In general, fragments 6 appear in order and relatively close to each other in the file. A fragment...data product derived from the data model is shown in Fig. 5, a Google Earth12 Keyhole Markup Language (KML) file. This product includes aggregate...System BLOb binary large object FPGA field-programmable gate array HPC high-performance computing IP Internet Protocol KML Keyhole Markup Language

Bayesian optimization for computationally extensive probability distributions.

Science.gov (United States)

Tamura, Ryo; Hukushima, Koji

2018-01-01

An efficient method for finding a better maximizer of computationally extensive probability distributions is proposed on the basis of a Bayesian optimization technique. A key idea of the proposed method is to use extreme values of acquisition functions by Gaussian processes for the next training phase, which should be located near a local maximum or a global maximum of the probability distribution. Our Bayesian optimization technique is applied to the posterior distribution in the effective physical model estimation, which is a computationally extensive probability distribution. Even when the number of sampling points on the posterior distributions is fixed to be small, the Bayesian optimization provides a better maximizer of the posterior distributions in comparison to those by the random search method, the steepest descent method, or the Monte Carlo method. Furthermore, the Bayesian optimization improves the results efficiently by combining the steepest descent method and thus it is a powerful tool to search for a better maximizer of computationally extensive probability distributions.

Solving Problems in Various Domains by Hybrid Models of High Performance Computations

Directory of Open Access Journals (Sweden)

Yurii Rogozhin

2014-03-01

Full Text Available This work presents a hybrid model of high performance computations. The model is based on membrane system (P~system where some membranes may contain quantum device that is triggered by the data entering the membrane. This model is supposed to take advantages of both biomolecular and quantum paradigms and to overcome some of their inherent limitations. The proposed approach is demonstrated through two selected problems: SAT, and image retrieving.

FY 1996 Blue Book: High Performance Computing and Communications: Foundations for America`s Information Future

Data.gov (United States)

Networking and Information Technology Research and Development, Executive Office of the President — The Federal High Performance Computing and Communications HPCC Program will celebrate its fifth anniversary in October 1996 with an impressive array of...

FY 1997 Blue Book: High Performance Computing and Communications: Advancing the Frontiers of Information Technology

Data.gov (United States)

Networking and Information Technology Research and Development, Executive Office of the President — The Federal High Performance Computing and Communications HPCC Program will celebrate its fifth anniversary in October 1996 with an impressive array of...

Implementation of High Speed Distributed Data Acquisition System

Science.gov (United States)

Raju, Anju P.; Sekhar, Ambika

2012-09-01

This paper introduces a high speed distributed data acquisition system based on a field programmable gate array (FPGA). The aim is to develop a "distributed" data acquisition interface. The development of instruments such as personal computers and engineering workstations based on "standard" platforms is the motivation behind this effort. Using standard platforms as the controlling unit allows independence in hardware from a particular vendor and hardware platform. The distributed approach also has advantages from a functional point of view: acquisition resources become available to multiple instruments; the acquisition front-end can be physically remote from the rest of the instrument. High speed data acquisition system transmits data faster to a remote computer system through Ethernet interface. The data is acquired through 16 analog input channels. The input data commands are multiplexed and digitized and then the data is stored in 1K buffer for each input channel. The main control unit in this design is the 16 bit processor implemented in the FPGA. This 16 bit processor is used to set up and initialize the data source and the Ethernet controller, as well as control the flow of data from the memory element to the NIC. Using this processor we can initialize and control the different configuration registers in the Ethernet controller in a easy manner. Then these data packets are sending to the remote PC through the Ethernet interface. The main advantages of the using FPGA as standard platform are its flexibility, low power consumption, short design duration, fast time to market, programmability and high density. The main advantages of using Ethernet controller AX88796 over others are its non PCI interface, the presence of embedded SRAM where transmit and reception buffers are located and high-performance SRAM-like interface. The paper introduces the implementation of the distributed data acquisition using FPGA by VHDL. The main advantages of this system are high

Challenges and opportunities of modeling plasma–surface interactions in tungsten using high-performance computing

Energy Technology Data Exchange (ETDEWEB)

Wirth, Brian D., E-mail: bdwirth@utk.edu [Department of Nuclear Engineering, University of Tennessee, Knoxville, TN 37996 (United States); Nuclear Science and Engineering Directorate, Oak Ridge National Laboratory, Oak Ridge, TN (United States); Hammond, K.D. [Department of Nuclear Engineering, University of Tennessee, Knoxville, TN 37996 (United States); Krasheninnikov, S.I. [University of California, San Diego, La Jolla, CA (United States); Maroudas, D. [University of Massachusetts, Amherst, Amherst, MA 01003 (United States)

2015-08-15

The performance of plasma facing components (PFCs) is critical for ITER and future magnetic fusion reactors. The ITER divertor will be tungsten, which is the primary candidate material for future reactors. Recent experiments involving tungsten exposure to low-energy helium plasmas reveal significant surface modification, including the growth of nanometer-scale tendrils of “fuzz” and formation of nanometer-sized bubbles in the near-surface region. The large span of spatial and temporal scales governing plasma surface interactions are among the challenges to modeling divertor performance. Fortunately, recent innovations in computational modeling, increasingly powerful high-performance computers, and improved experimental characterization tools provide a path toward self-consistent, experimentally validated models of PFC and divertor performance. Recent advances in understanding tungsten–helium interactions are reviewed, including such processes as helium clustering, which serve as nuclei for gas bubbles; and trap mutation, dislocation loop punching and bubble bursting; which together initiate surface morphological modification.

Challenges and opportunities of modeling plasma–surface interactions in tungsten using high-performance computing

International Nuclear Information System (INIS)

Wirth, Brian D.; Hammond, K.D.; Krasheninnikov, S.I.; Maroudas, D.

2015-01-01

The performance of plasma facing components (PFCs) is critical for ITER and future magnetic fusion reactors. The ITER divertor will be tungsten, which is the primary candidate material for future reactors. Recent experiments involving tungsten exposure to low-energy helium plasmas reveal significant surface modification, including the growth of nanometer-scale tendrils of “fuzz” and formation of nanometer-sized bubbles in the near-surface region. The large span of spatial and temporal scales governing plasma surface interactions are among the challenges to modeling divertor performance. Fortunately, recent innovations in computational modeling, increasingly powerful high-performance computers, and improved experimental characterization tools provide a path toward self-consistent, experimentally validated models of PFC and divertor performance. Recent advances in understanding tungsten–helium interactions are reviewed, including such processes as helium clustering, which serve as nuclei for gas bubbles; and trap mutation, dislocation loop punching and bubble bursting; which together initiate surface morphological modification

Scalable domain decomposition solvers for stochastic PDEs in high performance computing

International Nuclear Information System (INIS)

Desai, Ajit; Pettit, Chris; Poirel, Dominique; Sarkar, Abhijit

2017-01-01

Stochastic spectral finite element models of practical engineering systems may involve solutions of linear systems or linearized systems for non-linear problems with billions of unknowns. For stochastic modeling, it is therefore essential to design robust, parallel and scalable algorithms that can efficiently utilize high-performance computing to tackle such large-scale systems. Domain decomposition based iterative solvers can handle such systems. And though these algorithms exhibit excellent scalabilities, significant algorithmic and implementational challenges exist to extend them to solve extreme-scale stochastic systems using emerging computing platforms. Intrusive polynomial chaos expansion based domain decomposition algorithms are extended here to concurrently handle high resolution in both spatial and stochastic domains using an in-house implementation. Sparse iterative solvers with efficient preconditioners are employed to solve the resulting global and subdomain level local systems through multi-level iterative solvers. We also use parallel sparse matrix–vector operations to reduce the floating-point operations and memory requirements. Numerical and parallel scalabilities of these algorithms are presented for the diffusion equation having spatially varying diffusion coefficient modeled by a non-Gaussian stochastic process. Scalability of the solvers with respect to the number of random variables is also investigated.

High performance computations using dynamical nucleation theory

International Nuclear Information System (INIS)

Windus, T L; Crosby, L D; Kathmann, S M

2008-01-01

Chemists continue to explore the use of very large computations to perform simulations that describe the molecular level physics of critical challenges in science. In this paper, we describe the Dynamical Nucleation Theory Monte Carlo (DNTMC) model - a model for determining molecular scale nucleation rate constants - and its parallel capabilities. The potential for bottlenecks and the challenges to running on future petascale or larger resources are delineated. A 'master-slave' solution is proposed to scale to the petascale and will be developed in the NWChem software. In addition, mathematical and data analysis challenges are described

Agglomeration Economies and the High-Tech Computer

OpenAIRE

Wallace, Nancy E.; Walls, Donald

2004-01-01

This paper considers the effects of agglomeration on the production decisions of firms in the high-tech computer cluster. We build upon an alternative definition of the high-tech computer cluster developed by Bardhan et al. (2003) and we exploit a new data source, the National Establishment Time-Series (NETS) Database, to analyze the spatial distribution of firms in this industry. An essential contribution of this research is the recognition that high-tech firms are heterogeneous collections ...

Computational Intelligence based techniques for islanding detection of distributed generation in distribution network: A review

International Nuclear Information System (INIS)

Laghari, J.A.; Mokhlis, H.; Karimi, M.; Bakar, A.H.A.; Mohamad, Hasmaini

2014-01-01

Highlights: • Unintentional and intentional islanding, their causes, and solutions are presented. • Remote, passive, active and hybrid islanding detection techniques are discussed. • The limitation of these techniques in accurately detect islanding are discussed. • Computational intelligence techniques ability in detecting islanding is discussed. • Review of ANN, fuzzy logic control, ANFIS, Decision tree techniques is provided. - Abstract: Accurate and fast islanding detection of distributed generation is highly important for its successful operation in distribution networks. Up to now, various islanding detection technique based on communication, passive, active and hybrid methods have been proposed. However, each technique suffers from certain demerits that cause inaccuracies in islanding detection. Computational intelligence based techniques, due to their robustness and flexibility in dealing with complex nonlinear systems, is an option that might solve this problem. This paper aims to provide a comprehensive review of computational intelligence based techniques applied for islanding detection of distributed generation. Moreover, the paper compares the accuracies of computational intelligence based techniques over existing techniques to provide a handful of information for industries and utility researchers to determine the best method for their respective system

Application of High Performance Computing to Earthquake Hazard and Disaster Estimation in Urban Area

Directory of Open Access Journals (Sweden)

Muneo Hori

2018-02-01

Full Text Available Integrated earthquake simulation (IES is a seamless simulation of analyzing all processes of earthquake hazard and disaster. There are two difficulties in carrying out IES, namely, the requirement of large-scale computation and the requirement of numerous analysis models for structures in an urban area, and they are solved by taking advantage of high performance computing (HPC and by developing a system of automated model construction. HPC is a key element in developing IES, as it needs to analyze wave propagation and amplification processes in an underground structure; a model of high fidelity for the underground structure exceeds a degree-of-freedom larger than 100 billion. Examples of IES for Tokyo Metropolis are presented; the numerical computation is made by using K computer, the supercomputer of Japan. The estimation of earthquake hazard and disaster for a given earthquake scenario is made by the ground motion simulation and the urban area seismic response simulation, respectively, for the target area of 10,000 m × 10,000 m.

Development of a Computational Steering Framework for High Performance Computing Environments on Blue Gene/P Systems

KAUST Repository

Danani, Bob K.

2012-07-01

Computational steering has revolutionized the traditional workflow in high performance computing (HPC) applications. The standard workflow that consists of preparation of an application’s input, running of a simulation, and visualization of simulation results in a post-processing step is now transformed into a real-time interactive workflow that significantly reduces development and testing time. Computational steering provides the capability to direct or re-direct the progress of a simulation application at run-time. It allows modification of application-defined control parameters at run-time using various user-steering applications. In this project, we propose a computational steering framework for HPC environments that provides an innovative solution and easy-to-use platform, which allows users to connect and interact with running application(s) in real-time. This framework uses RealityGrid as the underlying steering library and adds several enhancements to the library to enable steering support for Blue Gene systems. Included in the scope of this project is the development of a scalable and efficient steering relay server that supports many-to-many connectivity between multiple steered applications and multiple steering clients. Steered applications can range from intermediate simulation and physical modeling applications to complex computational fluid dynamics (CFD) applications or advanced visualization applications. The Blue Gene supercomputer presents special challenges for remote access because the compute nodes reside on private networks. This thesis presents an implemented solution and demonstrates it on representative applications. Thorough implementation details and application enablement steps are also presented in this thesis to encourage direct usage of this framework.

Distributed Computing for the Pierre Auger Observatory

International Nuclear Information System (INIS)

Chudoba, J.

2015-01-01

Pierre Auger Observatory operates the largest system of detectors for ultra-high energy cosmic ray measurements. Comparison of theoretical models of interactions with recorded data requires thousands of computing cores for Monte Carlo simulations. Since 2007 distributed resources connected via EGI grid are successfully used. The first and the second versions of production system based on bash scripts and MySQL database were able to submit jobs to all reliable sites supporting Virtual Organization auger. For many years VO auger belongs to top ten of EGI users based on the total used computing time. Migration of the production system to DIRAC interware started in 2014. Pilot jobs improve efficiency of computing jobs and eliminate problems with small and less reliable sites used for the bulk production. The new system has also possibility to use available resources in clouds. Dirac File Catalog replaced LFC for new files, which are organized in datasets defined via metadata. CVMFS is used for software distribution since 2014. In the presentation we give a comparison of the old and the new production system and report the experience on migrating to the new system. (paper)

Distributed Computing for the Pierre Auger Observatory

Science.gov (United States)

Chudoba, J.

2015-12-01

Pierre Auger Observatory operates the largest system of detectors for ultra-high energy cosmic ray measurements. Comparison of theoretical models of interactions with recorded data requires thousands of computing cores for Monte Carlo simulations. Since 2007 distributed resources connected via EGI grid are successfully used. The first and the second versions of production system based on bash scripts and MySQL database were able to submit jobs to all reliable sites supporting Virtual Organization auger. For many years VO auger belongs to top ten of EGI users based on the total used computing time. Migration of the production system to DIRAC interware started in 2014. Pilot jobs improve efficiency of computing jobs and eliminate problems with small and less reliable sites used for the bulk production. The new system has also possibility to use available resources in clouds. Dirac File Catalog replaced LFC for new files, which are organized in datasets defined via metadata. CVMFS is used for software distribution since 2014. In the presentation we give a comparison of the old and the new production system and report the experience on migrating to the new system.

Cloud object store for archive storage of high performance computing data using decoupling middleware

Science.gov (United States)

Bent, John M.; Faibish, Sorin; Grider, Gary

2015-06-30

Cloud object storage is enabled for archived data, such as checkpoints and results, of high performance computing applications using a middleware process. A plurality of archived files, such as checkpoint files and results, generated by a plurality of processes in a parallel computing system are stored by obtaining the plurality of archived files from the parallel computing system; converting the plurality of archived files to objects using a log structured file system middleware process; and providing the objects for storage in a cloud object storage system. The plurality of processes may run, for example, on a plurality of compute nodes. The log structured file system middleware process may be embodied, for example, as a Parallel Log-Structured File System (PLFS). The log structured file system middleware process optionally executes on a burst buffer node.

A distributed computing model for telemetry data processing

Science.gov (United States)

Barry, Matthew R.; Scott, Kevin L.; Weismuller, Steven P.

1994-05-01

We present a new approach to distributing processed telemetry data among spacecraft flight controllers within the control centers at NASA's Johnson Space Center. This approach facilitates the development of application programs which integrate spacecraft-telemetered data and ground-based synthesized data, then distributes this information to flight controllers for analysis and decision-making. The new approach combines various distributed computing models into one hybrid distributed computing model. The model employs both client-server and peer-to-peer distributed computing models cooperating to provide users with information throughout a diverse operations environment. Specifically, it provides an attractive foundation upon which we are building critical real-time monitoring and control applications, while simultaneously lending itself to peripheral applications in playback operations, mission preparations, flight controller training, and program development and verification. We have realized the hybrid distributed computing model through an information sharing protocol. We shall describe the motivations that inspired us to create this protocol, along with a brief conceptual description of the distributed computing models it employs. We describe the protocol design in more detail, discussing many of the program design considerations and techniques we have adopted. Finally, we describe how this model is especially suitable for supporting the implementation of distributed expert system applications.

A distributed computing model for telemetry data processing

Science.gov (United States)

Barry, Matthew R.; Scott, Kevin L.; Weismuller, Steven P.

1994-01-01

We present a new approach to distributing processed telemetry data among spacecraft flight controllers within the control centers at NASA's Johnson Space Center. This approach facilitates the development of application programs which integrate spacecraft-telemetered data and ground-based synthesized data, then distributes this information to flight controllers for analysis and decision-making. The new approach combines various distributed computing models into one hybrid distributed computing model. The model employs both client-server and peer-to-peer distributed computing models cooperating to provide users with information throughout a diverse operations environment. Specifically, it provides an attractive foundation upon which we are building critical real-time monitoring and control applications, while simultaneously lending itself to peripheral applications in playback operations, mission preparations, flight controller training, and program development and verification. We have realized the hybrid distributed computing model through an information sharing protocol. We shall describe the motivations that inspired us to create this protocol, along with a brief conceptual description of the distributed computing models it employs. We describe the protocol design in more detail, discussing many of the program design considerations and techniques we have adopted. Finally, we describe how this model is especially suitable for supporting the implementation of distributed expert system applications.

Study of application technology of ultra-high speed computer to the elucidation of complex phenomena

International Nuclear Information System (INIS)

Sekiguchi, Tomotsugu

1996-01-01

The basic design of numerical information library in the decentralized computer network was explained at the first step of constructing the application technology of ultra-high speed computer to the elucidation of complex phenomena. Establishment of the system makes possible to construct the efficient application environment of ultra-high speed computer system to be scalable with the different computing systems. We named the system Ninf (Network Information Library for High Performance Computing). The summary of application technology of library was described as follows: the application technology of library under the distributed environment, numeric constants, retrieval of value, library of special functions, computing library, Ninf library interface, Ninf remote library and registration. By the system, user is able to use the program concentrating the analyzing technology of numerical value with high precision, reliability and speed. (S.Y.)

Amorphous Zinc Oxide Integrated Wavy Channel Thin Film Transistor Based High Performance Digital Circuits

KAUST Repository

Hanna, Amir; Hussain, Aftab M.; Omran, Hesham; Alshareef, Sarah; Salama, Khaled N.; Hussain, Muhammad Mustafa

2015-01-01

High performance thin film transistor (TFT) can be a great driving force for display, sensor/actuator, integrated electronics, and distributed computation for Internet of Everything applications. While semiconducting oxides like zinc oxide (Zn

Matrix multiplication operations with data pre-conditioning in a high performance computing architecture

Science.gov (United States)

Eichenberger, Alexandre E; Gschwind, Michael K; Gunnels, John A

2013-11-05

Mechanisms for performing matrix multiplication operations with data pre-conditioning in a high performance computing architecture are provided. A vector load operation is performed to load a first vector operand of the matrix multiplication operation to a first target vector register. A load and splat operation is performed to load an element of a second vector operand and replicating the element to each of a plurality of elements of a second target vector register. A multiply add operation is performed on elements of the first target vector register and elements of the second target vector register to generate a partial product of the matrix multiplication operation. The partial product of the matrix multiplication operation is accumulated with other partial products of the matrix multiplication operation.

High performance computing, supercomputing, náročné počítání

Czech Academy of Sciences Publication Activity Database

Okrouhlík, Miloslav

2003-01-01

Roč. 10, č. 5 (2003), s. 429-438 ISSN 1210-2717 R&D Projects: GA ČR GA101/02/0072 Institutional research plan: CEZ:AV0Z2076919 Keywords : high performance computing * vector and parallel computers * programing tools for parellelization Subject RIV: BI - Acoustics

Computational Analysis of Powered Lift Augmentation for the LEAPTech Distributed Electric Propulsion Wing

Science.gov (United States)

Deere, Karen A.; Viken, Sally A.; Carter, Melissa B.; Viken, Jeffrey K.; Wiese, Michael R.; Farr, Norma L.

2017-01-01

A computational study of a distributed electric propulsion wing with a 40deg flap deflection has been completed using FUN3D. Two lift-augmentation power conditions were compared with the power-off configuration on the high-lift wing (40deg flap) at a 73 mph freestream flow and for a range of angles of attack from -5 degrees to 14 degrees. The computational study also included investigating the benefit of corotating versus counter-rotating propeller spin direction to powered-lift performance. The results indicate a large benefit in lift coefficient, over the entire range of angle of attack studied, by using corotating propellers that all spin counter to the wingtip vortex. For the landing condition, 73 mph, the unpowered 40deg flap configuration achieved a maximum lift coefficient of 2.3. With high-lift blowing the maximum lift coefficient increased to 5.61. Therefore, the lift augmentation is a factor of 2.4. Taking advantage of the fullspan lift augmentation at similar performance means that a wing powered with the distributed electric propulsion system requires only 42 percent of the wing area of the unpowered wing. This technology will allow wings to be 'cruise optimized', meaning that they will be able to fly closer to maximum lift over drag conditions at the design cruise speed of the aircraft.

Probabilistic performance estimators for computational chemistry methods: The empirical cumulative distribution function of absolute errors

Science.gov (United States)

Pernot, Pascal; Savin, Andreas

2018-06-01

Benchmarking studies in computational chemistry use reference datasets to assess the accuracy of a method through error statistics. The commonly used error statistics, such as the mean signed and mean unsigned errors, do not inform end-users on the expected amplitude of prediction errors attached to these methods. We show that, the distributions of model errors being neither normal nor zero-centered, these error statistics cannot be used to infer prediction error probabilities. To overcome this limitation, we advocate for the use of more informative statistics, based on the empirical cumulative distribution function of unsigned errors, namely, (1) the probability for a new calculation to have an absolute error below a chosen threshold and (2) the maximal amplitude of errors one can expect with a chosen high confidence level. Those statistics are also shown to be well suited for benchmarking and ranking studies. Moreover, the standard error on all benchmarking statistics depends on the size of the reference dataset. Systematic publication of these standard errors would be very helpful to assess the statistical reliability of benchmarking conclusions.

Requirements for high performance computing for lattice QCD. Report of the ECFA working panel

International Nuclear Information System (INIS)

Jegerlehner, F.; Kenway, R.D.; Martinelli, G.; Michael, C.; Pene, O.; Petersson, B.; Petronzio, R.; Sachrajda, C.T.; Schilling, K.

2000-01-01

This report, prepared at the request of the European Committee for Future Accelerators (ECFA), contains an assessment of the High Performance Computing resources which will be required in coming years by European physicists working in Lattice Field Theory and a review of the scientific opportunities which these resources would open. (orig.)

High-performance computing on the Intel Xeon Phi how to fully exploit MIC architectures

CERN Document Server

Wang, Endong; Shen, Bo; Zhang, Guangyong; Lu, Xiaowei; Wu, Qing; Wang, Yajuan

2014-01-01

The aim of this book is to explain to high-performance computing (HPC) developers how to utilize the Intel® Xeon Phi™ series products efficiently. To that end, it introduces some computing grammar, programming technology and optimization methods for using many-integrated-core (MIC) platforms and also offers tips and tricks for actual use, based on the authors' first-hand optimization experience.The material is organized in three sections. The first section, "Basics of MIC", introduces the fundamentals of MIC architecture and programming, including the specific Intel MIC programming environment

Department of Energy: MICS (Mathematical Information, and Computational Sciences Division). High performance computing and communications program

Energy Technology Data Exchange (ETDEWEB)

NONE

1996-06-01

This document is intended to serve two purposes. Its first purpose is that of a program status report of the considerable progress that the Department of Energy (DOE) has made since 1993, the time of the last such report (DOE/ER-0536, {open_quotes}The DOE Program in HPCC{close_quotes}), toward achieving the goals of the High Performance Computing and Communications (HPCC) Program. The second purpose is that of a summary report of the many research programs administered by the Mathematical, Information, and Computational Sciences (MICS) Division of the Office of Energy Research under the auspices of the HPCC Program and to provide, wherever relevant, easy access to pertinent information about MICS-Division activities via universal resource locators (URLs) on the World Wide Web (WWW). The information pointed to by the URL is updated frequently, and the interested reader is urged to access the WWW for the latest information.

High performance stream computing for particle beam transport simulations

International Nuclear Information System (INIS)

Appleby, R; Bailey, D; Higham, J; Salt, M

2008-01-01

Understanding modern particle accelerators requires simulating charged particle transport through the machine elements. These simulations can be very time consuming due to the large number of particles and the need to consider many turns of a circular machine. Stream computing offers an attractive way to dramatically improve the performance of such simulations by calculating the simultaneous transport of many particles using dedicated hardware. Modern Graphics Processing Units (GPUs) are powerful and affordable stream computing devices. The results of simulations of particle transport through the booster-to-storage-ring transfer line of the DIAMOND synchrotron light source using an NVidia GeForce 7900 GPU are compared to the standard transport code MAD. It is found that particle transport calculations are suitable for stream processing and large performance increases are possible. The accuracy and potential speed gains are compared and the prospects for future work in the area are discussed

An Overview of Cloud Computing in Distributed Systems

Science.gov (United States)

Divakarla, Usha; Kumari, Geetha

2010-11-01

Cloud computing is the emerging trend in the field of distributed computing. Cloud computing evolved from grid computing and distributed computing. Cloud plays an important role in huge organizations in maintaining huge data with limited resources. Cloud also helps in resource sharing through some specific virtual machines provided by the cloud service provider. This paper gives an overview of the cloud organization and some of the basic security issues pertaining to the cloud.

Comparative phyloinformatics of virus genes at micro and macro levels in a distributed computing environment.

Science.gov (United States)

Singh, Dadabhai T; Trehan, Rahul; Schmidt, Bertil; Bretschneider, Timo

2008-01-01

Preparedness for a possible global pandemic caused by viruses such as the highly pathogenic influenza A subtype H5N1 has become a global priority. In particular, it is critical to monitor the appearance of any new emerging subtypes. Comparative phyloinformatics can be used to monitor, analyze, and possibly predict the evolution of viruses. However, in order to utilize the full functionality of available analysis packages for large-scale phyloinformatics studies, a team of computer scientists, biostatisticians and virologists is needed--a requirement which cannot be fulfilled in many cases. Furthermore, the time complexities of many algorithms involved leads to prohibitive runtimes on sequential computer platforms. This has so far hindered the use of comparative phyloinformatics as a commonly applied tool in this area. In this paper the graphical-oriented workflow design system called Quascade and its efficient usage for comparative phyloinformatics are presented. In particular, we focus on how this task can be effectively performed in a distributed computing environment. As a proof of concept, the designed workflows are used for the phylogenetic analysis of neuraminidase of H5N1 isolates (micro level) and influenza viruses (macro level). The results of this paper are hence twofold. Firstly, this paper demonstrates the usefulness of a graphical user interface system to design and execute complex distributed workflows for large-scale phyloinformatics studies of virus genes. Secondly, the analysis of neuraminidase on different levels of complexity provides valuable insights of this virus's tendency for geographical based clustering in the phylogenetic tree and also shows the importance of glycan sites in its molecular evolution. The current study demonstrates the efficiency and utility of workflow systems providing a biologist friendly approach to complex biological dataset analysis using high performance computing. In particular, the utility of the platform Quascade

Efficient implementation of multidimensional fast fourier transform on a distributed-memory parallel multi-node computer

Science.gov (United States)

Bhanot, Gyan V [Princeton, NJ; Chen, Dong [Croton-On-Hudson, NY; Gara, Alan G [Mount Kisco, NY; Giampapa, Mark E [Irvington, NY; Heidelberger, Philip [Cortlandt Manor, NY; Steinmacher-Burow, Burkhard D [Mount Kisco, NY; Vranas, Pavlos M [Bedford Hills, NY

2012-01-10

The present in invention is directed to a method, system and program storage device for efficiently implementing a multidimensional Fast Fourier Transform (FFT) of a multidimensional array comprising a plurality of elements initially distributed in a multi-node computer system comprising a plurality of nodes in communication over a network, comprising: distributing the plurality of elements of the array in a first dimension across the plurality of nodes of the computer system over the network to facilitate a first one-dimensional FFT; performing the first one-dimensional FFT on the elements of the array distributed at each node in the first dimension; re-distributing the one-dimensional FFT-transformed elements at each node in a second dimension via "all-to-all" distribution in random order across other nodes of the computer system over the network; and performing a second one-dimensional FFT on elements of the array re-distributed at each node in the second dimension, wherein the random order facilitates efficient utilization of the network thereby efficiently implementing the multidimensional FFT. The "all-to-all" re-distribution of array elements is further efficiently implemented in applications other than the multidimensional FFT on the distributed-memory parallel supercomputer.

A high-performance model for shallow-water simulations in distributed and heterogeneous architectures

Science.gov (United States)

Conde, Daniel; Canelas, Ricardo B.; Ferreira, Rui M. L.

2017-04-01

unstructured nature of the mesh topology with the corresponding employed solution, based on space-filling curves, being analyzed and discussed. Intra-node parallelism is achieved through OpenMP for CPUs and CUDA for GPUs, depending on which kind of device the process is running. Here the main difficulty is associated with the Object-Oriented approach, where the presence of complex data structures can degrade model performance considerably. STAV-2D now supports fully distributed and heterogeneous simulations where multiple different devices can be used to accelerate computation time. The advantages, short-comings and specific solutions for the employed unified Object-Oriented approach, where the source code for CPU and GPU has the same compilation units (no device specific branches like seen in available models), are discussed and quantified with a thorough scalability and performance analysis. The assembled parallel model is expected to achieve faster than real-time simulations for high resolutions (from meters to sub-meter) in large scaled problems (from cities to watersheds), effectively bridging the gap between detailed and timely simulation results. Acknowledgements This research as partially supported by Portuguese and European funds, within programs COMPETE2020 and PORL-FEDER, through project PTDC/ECM-HID/6387/2014 and Doctoral Grant SFRH/BD/97933/2013 granted by the National Foundation for Science and Technology (FCT). References Canelas, R.; Murillo, J. & Ferreira, R.M.L. (2013), Two-dimensional depth-averaged modelling of dam-break flows over mobile beds. Journal of Hydraulic Research, 51(4), 392-407. Conde, D. A. S.; Baptista, M. A. V.; Sousa Oliveira, C. & Ferreira, R. M. L. (2013), A shallow-flow model for the propagation of tsunamis over complex geometries and mobile beds, Nat. Hazards and Earth Syst. Sci., 13, 2533-2542. Conde, D. A. S.; Telhado, M. J.; Viana Baptista, M. A. & Ferreira, R. M. L. (2015) Severity and exposure associated with tsunami actions in

Performance Analysis of Cloud Computing Architectures Using Discrete Event Simulation

Science.gov (United States)

Stocker, John C.; Golomb, Andrew M.

2011-01-01

Cloud computing offers the economic benefit of on-demand resource allocation to meet changing enterprise computing needs. However, the flexibility of cloud computing is disadvantaged when compared to traditional hosting in providing predictable application and service performance. Cloud computing relies on resource scheduling in a virtualized network-centric server environment, which makes static performance analysis infeasible. We developed a discrete event simulation model to evaluate the overall effectiveness of organizations in executing their workflow in traditional and cloud computing architectures. The two part model framework characterizes both the demand using a probability distribution for each type of service request as well as enterprise computing resource constraints. Our simulations provide quantitative analysis to design and provision computing architectures that maximize overall mission effectiveness. We share our analysis of key resource constraints in cloud computing architectures and findings on the appropriateness of cloud computing in various applications.

A Distributed Snapshot Protocol for Efficient Artificial Intelligence Computation in Cloud Computing Environments

Directory of Open Access Journals (Sweden)

JongBeom Lim

2018-01-01

Full Text Available Many artificial intelligence applications often require a huge amount of computing resources. As a result, cloud computing adoption rates are increasing in the artificial intelligence field. To support the demand for artificial intelligence applications and guarantee the service level agreement, cloud computing should provide not only computing resources but also fundamental mechanisms for efficient computing. In this regard, a snapshot protocol has been used to create a consistent snapshot of the global state in cloud computing environments. However, the existing snapshot protocols are not optimized in the context of artificial intelligence applications, where large-scale iterative computation is the norm. In this paper, we present a distributed snapshot protocol for efficient artificial intelligence computation in cloud computing environments. The proposed snapshot protocol is based on a distributed algorithm to run interconnected multiple nodes in a scalable fashion. Our snapshot protocol is able to deal with artificial intelligence applications, in which a large number of computing nodes are running. We reveal that our distributed snapshot protocol guarantees the correctness, safety, and liveness conditions.

Optimized distributed systems achieve significant performance improvement on sorted merging of massive VCF files.

Science.gov (United States)

Sun, Xiaobo; Gao, Jingjing; Jin, Peng; Eng, Celeste; Burchard, Esteban G; Beaty, Terri H; Ruczinski, Ingo; Mathias, Rasika A; Barnes, Kathleen; Wang, Fusheng; Qin, Zhaohui S

2018-06-01

Sorted merging of genomic data is a common data operation necessary in many sequencing-based studies. It involves sorting and merging genomic data from different subjects by their genomic locations. In particular, merging a large number of variant call format (VCF) files is frequently required in large-scale whole-genome sequencing or whole-exome sequencing projects. Traditional single-machine based methods become increasingly inefficient when processing large numbers of files due to the excessive computation time and Input/Output bottleneck. Distributed systems and more recent cloud-based systems offer an attractive solution. However, carefully designed and optimized workflow patterns and execution plans (schemas) are required to take full advantage of the increased computing power while overcoming bottlenecks to achieve high performance. In this study, we custom-design optimized schemas for three Apache big data platforms, Hadoop (MapReduce), HBase, and Spark, to perform sorted merging of a large number of VCF files. These schemas all adopt the divide-and-conquer strategy to split the merging job into sequential phases/stages consisting of subtasks that are conquered in an ordered, parallel, and bottleneck-free way. In two illustrating examples, we test the performance of our schemas on merging multiple VCF files into either a single TPED or a single VCF file, which are benchmarked with the traditional single/parallel multiway-merge methods, message passing interface (MPI)-based high-performance computing (HPC) implementation, and the popular VCFTools. Our experiments suggest all three schemas either deliver a significant improvement in efficiency or render much better strong and weak scalabilities over traditional methods. Our findings provide generalized scalable schemas for performing sorted merging on genetics and genomics data using these Apache distributed systems.

Topology and computational performance of attractor neural networks

International Nuclear Information System (INIS)

McGraw, Patrick N.; Menzinger, Michael

2003-01-01

To explore the relation between network structure and function, we studied the computational performance of Hopfield-type attractor neural nets with regular lattice, random, small-world, and scale-free topologies. The random configuration is the most efficient for storage and retrieval of patterns by the network as a whole. However, in the scale-free case retrieval errors are not distributed uniformly among the nodes. The portion of a pattern encoded by the subset of highly connected nodes is more robust and efficiently recognized than the rest of the pattern. The scale-free network thus achieves a very strong partial recognition. The implications of these findings for brain function and social dynamics are suggestive

Computational optimization of catalyst distributions at the nano-scale

International Nuclear Information System (INIS)

Ström, Henrik

2017-01-01

Highlights: • Macroscopic data sampled from a DSMC simulation contain statistical scatter. • Simulated annealing is evaluated as an optimization algorithm with DSMC. • Proposed method is more robust than a gradient search method. • Objective function uses the mass transfer rate instead of the reaction rate. • Combined algorithm is more efficient than a macroscopic overlay method. - Abstract: Catalysis is a key phenomenon in a great number of energy processes, including feedstock conversion, tar cracking, emission abatement and optimizations of energy use. Within heterogeneous, catalytic nano-scale systems, the chemical reactions typically proceed at very high rates at a gas–solid interface. However, the statistical uncertainties characteristic of molecular processes pose efficiency problems for computational optimizations of such nano-scale systems. The present work investigates the performance of a Direct Simulation Monte Carlo (DSMC) code with a stochastic optimization heuristic for evaluations of an optimal catalyst distribution. The DSMC code treats molecular motion with homogeneous and heterogeneous chemical reactions in wall-bounded systems and algorithms have been devised that allow optimization of the distribution of a catalytically active material within a three-dimensional duct (e.g. a pore). The objective function is the outlet concentration of computational molecules that have interacted with the catalytically active surface, and the optimization method used is simulated annealing. The application of a stochastic optimization heuristic is shown to be more efficient within the present DSMC framework than using a macroscopic overlay method. Furthermore, it is shown that the performance of the developed method is superior to that of a gradient search method for the current class of problems. Finally, the advantages and disadvantages of different types of objective functions are discussed.

FPGA cluster for high-performance AO real-time control system

Science.gov (United States)

Geng, Deli; Goodsell, Stephen J.; Basden, Alastair G.; Dipper, Nigel A.; Myers, Richard M.; Saunter, Chris D.

2006-06-01

Whilst the high throughput and low latency requirements for the next generation AO real-time control systems have posed a significant challenge to von Neumann architecture processor systems, the Field Programmable Gate Array (FPGA) has emerged as a long term solution with high performance on throughput and excellent predictability on latency. Moreover, FPGA devices have highly capable programmable interfacing, which lead to more highly integrated system. Nevertheless, a single FPGA is still not enough: multiple FPGA devices need to be clustered to perform the required subaperture processing and the reconstruction computation. In an AO real-time control system, the memory bandwidth is often the bottleneck of the system, simply because a vast amount of supporting data, e.g. pixel calibration maps and the reconstruction matrix, need to be accessed within a short period. The cluster, as a general computing architecture, has excellent scalability in processing throughput, memory bandwidth, memory capacity, and communication bandwidth. Problems, such as task distribution, node communication, system verification, are discussed.

9th International Symposium on Intelligent Distributed Computing

CERN Document Server

Camacho, David; Analide, Cesar; Seghrouchni, Amal; Badica, Costin

2016-01-01

This book represents the combined peer-reviewed proceedings of the ninth International Symposium on Intelligent Distributed Computing – IDC’2015, of the Workshop on Cyber Security and Resilience of Large-Scale Systems – WSRL’2015, and of the International Workshop on Future Internet and Smart Networks – FI&SN’2015. All the events were held in Guimarães, Portugal during October 7th-9th, 2015. The 46 contributions published in this book address many topics related to theory and applications of intelligent distributed computing, including: Intelligent Distributed Agent-Based Systems, Ambient Intelligence and Social Networks, Computational Sustainability, Intelligent Distributed Knowledge Representation and Processing, Smart Networks, Networked Intelligence and Intelligent Distributed Applications, amongst others.

Performance Management of High Performance Computing for Medical Image Processing in Amazon Web Services.

Science.gov (United States)

Bao, Shunxing; Damon, Stephen M; Landman, Bennett A; Gokhale, Aniruddha

2016-02-27

Adopting high performance cloud computing for medical image processing is a popular trend given the pressing needs of large studies. Amazon Web Services (AWS) provide reliable, on-demand, and inexpensive cloud computing services. Our research objective is to implement an affordable, scalable and easy-to-use AWS framework for the Java Image Science Toolkit (JIST). JIST is a plugin for Medical-Image Processing, Analysis, and Visualization (MIPAV) that provides a graphical pipeline implementation allowing users to quickly test and develop pipelines. JIST is DRMAA-compliant allowing it to run on portable batch system grids. However, as new processing methods are implemented and developed, memory may often be a bottleneck for not only lab computers, but also possibly some local grids. Integrating JIST with the AWS cloud alleviates these possible restrictions and does not require users to have deep knowledge of programming in Java. Workflow definition/management and cloud configurations are two key challenges in this research. Using a simple unified control panel, users have the ability to set the numbers of nodes and select from a variety of pre-configured AWS EC2 nodes with different numbers of processors and memory storage. Intuitively, we configured Amazon S3 storage to be mounted by pay-for-use Amazon EC2 instances. Hence, S3 storage is recognized as a shared cloud resource. The Amazon EC2 instances provide pre-installs of all necessary packages to run JIST. This work presents an implementation that facilitates the integration of JIST with AWS. We describe the theoretical cost/benefit formulae to decide between local serial execution versus cloud computing and apply this analysis to an empirical diffusion tensor imaging pipeline.

Performance management of high performance computing for medical image processing in Amazon Web Services

Science.gov (United States)

Bao, Shunxing; Damon, Stephen M.; Landman, Bennett A.; Gokhale, Aniruddha

2016-03-01

Adopting high performance cloud computing for medical image processing is a popular trend given the pressing needs of large studies. Amazon Web Services (AWS) provide reliable, on-demand, and inexpensive cloud computing services. Our research objective is to implement an affordable, scalable and easy-to-use AWS framework for the Java Image Science Toolkit (JIST). JIST is a plugin for Medical- Image Processing, Analysis, and Visualization (MIPAV) that provides a graphical pipeline implementation allowing users to quickly test and develop pipelines. JIST is DRMAA-compliant allowing it to run on portable batch system grids. However, as new processing methods are implemented and developed, memory may often be a bottleneck for not only lab computers, but also possibly some local grids. Integrating JIST with the AWS cloud alleviates these possible restrictions and does not require users to have deep knowledge of programming in Java. Workflow definition/management and cloud configurations are two key challenges in this research. Using a simple unified control panel, users have the ability to set the numbers of nodes and select from a variety of pre-configured AWS EC2 nodes with different numbers of processors and memory storage. Intuitively, we configured Amazon S3 storage to be mounted by pay-for- use Amazon EC2 instances. Hence, S3 storage is recognized as a shared cloud resource. The Amazon EC2 instances provide pre-installs of all necessary packages to run JIST. This work presents an implementation that facilitates the integration of JIST with AWS. We describe the theoretical cost/benefit formulae to decide between local serial execution versus cloud computing and apply this analysis to an empirical diffusion tensor imaging pipeline.