WorldWideScience

Sample records for distributed memory computers

  1. 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...

  2. Distributed Memory Parallel Computing with SEAWAT

    Science.gov (United States)

    Verkaik, J.; Huizer, S.; van Engelen, J.; Oude Essink, G.; Ram, R.; Vuik, K.

    2017-12-01

    Fresh groundwater reserves in coastal aquifers are threatened by sea-level rise, extreme weather conditions, increasing urbanization and associated groundwater extraction rates. To counteract these threats, accurate high-resolution numerical models are required to optimize the management of these precious reserves. The major model drawbacks are long run times and large memory requirements, limiting the predictive power of these models. Distributed memory parallel computing is an efficient technique for reducing run times and memory requirements, where the problem is divided over multiple processor cores. A new Parallel Krylov Solver (PKS) for SEAWAT is presented. PKS has recently been applied to MODFLOW and includes Conjugate Gradient (CG) and Biconjugate Gradient Stabilized (BiCGSTAB) linear accelerators. Both accelerators are preconditioned by an overlapping additive Schwarz preconditioner in a way that: a) subdomains are partitioned using Recursive Coordinate Bisection (RCB) load balancing, b) each subdomain uses local memory only and communicates with other subdomains by Message Passing Interface (MPI) within the linear accelerator, c) it is fully integrated in SEAWAT. Within SEAWAT, the PKS-CG solver replaces the Preconditioned Conjugate Gradient (PCG) solver for solving the variable-density groundwater flow equation and the PKS-BiCGSTAB solver replaces the Generalized Conjugate Gradient (GCG) solver for solving the advection-diffusion equation. PKS supports the third-order Total Variation Diminishing (TVD) scheme for computing advection. Benchmarks were performed on the Dutch national supercomputer (https://userinfo.surfsara.nl/systems/cartesius) using up to 128 cores, for a synthetic 3D Henry model (100 million cells) and the real-life Sand Engine model ( 10 million cells). The Sand Engine model was used to investigate the potential effect of the long-term morphological evolution of a large sand replenishment and climate change on fresh groundwater resources

  3. 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

  4. Ring interconnection for distributed memory automation and computing system

    Energy Technology Data Exchange (ETDEWEB)

    Vinogradov, V I [Inst. for Nuclear Research of the Russian Academy of Sciences, Moscow (Russian Federation)

    1996-12-31

    Problems of development of measurement, acquisition and central systems based on a distributed memory and a ring interface are discussed. It has been found that the RAM LINK-type protocol can be used for ringlet links in non-symmetrical distributed memory architecture multiprocessor system interaction. 5 refs.

  5. Adaptive Dynamic Process Scheduling on Distributed Memory Parallel Computers

    Directory of Open Access Journals (Sweden)

    Wei Shu

    1994-01-01

    Full Text Available One of the challenges in programming distributed memory parallel machines is deciding how to allocate work to processors. This problem is particularly important for computations with unpredictable dynamic behaviors or irregular structures. We present a scheme for dynamic scheduling of medium-grained processes that is useful in this context. The adaptive contracting within neighborhood (ACWN is a dynamic, distributed, load-dependent, and scalable scheme. It deals with dynamic and unpredictable creation of processes and adapts to different systems. The scheme is described and contrasted with two other schemes that have been proposed in this context, namely the randomized allocation and the gradient model. The performance of the three schemes on an Intel iPSC/2 hypercube is presented and analyzed. The experimental results show that even though the ACWN algorithm incurs somewhat larger overhead than the randomized allocation, it achieves better performance in most cases due to its adaptiveness. Its feature of quickly spreading the work helps it outperform the gradient model in performance and scalability.

  6. Computational cost of isogeometric multi-frontal solvers on parallel distributed memory machines

    KAUST Repository

    Woźniak, Maciej; Paszyński, Maciej R.; Pardo, D.; Dalcin, Lisandro; Calo, Victor M.

    2015-01-01

    This paper derives theoretical estimates of the computational cost for isogeometric multi-frontal direct solver executed on parallel distributed memory machines. We show theoretically that for the Cp-1 global continuity of the isogeometric solution

  7. Memory intensive functional architecture for distributed computer control systems

    International Nuclear Information System (INIS)

    Dimmler, D.G.

    1983-10-01

    A memory-intensive functional architectue for distributed data-acquisition, monitoring, and control systems with large numbers of nodes has been conceptually developed and applied in several large-scale and some smaller systems. This discussion concentrates on: (1) the basic architecture; (2) recent expansions of the architecture which now become feasible in view of the rapidly developing component technologies in microprocessors and functional large-scale integration circuits; and (3) implementation of some key hardware and software structures and one system implementation which is a system for performing control and data acquisition of a neutron spectrometer at the Brookhaven High Flux Beam Reactor. The spectrometer is equipped with a large-area position-sensitive neutron detector

  8. Distributed Cognition (DCOG): Foundations for a Computational Associative Memory Model

    National Research Council Canada - National Science Library

    Eggleston, Robert G; McCreight, Katherine L

    2006-01-01

    .... In this report, we describe the foundations of a different type of computational architecture; one that we believe will be less susceptible to cognitive brittleness and can better scale to complex and ill-structured work domains...

  9. Parallel grid generation algorithm for distributed memory computers

    Science.gov (United States)

    Moitra, Stuti; Moitra, Anutosh

    1994-01-01

    A parallel grid-generation algorithm and its implementation on the Intel iPSC/860 computer are described. The grid-generation scheme is based on an algebraic formulation of homotopic relations. Methods for utilizing the inherent parallelism of the grid-generation scheme are described, and implementation of multiple levELs of parallelism on multiple instruction multiple data machines are indicated. The algorithm is capable of providing near orthogonality and spacing control at solid boundaries while requiring minimal interprocessor communications. Results obtained on the Intel hypercube for a blended wing-body configuration are used to demonstrate the effectiveness of the algorithm. Fortran implementations bAsed on the native programming model of the iPSC/860 computer and the Express system of software tools are reported. Computational gains in execution time speed-up ratios are given.

  10. Sparse distributed memory overview

    Science.gov (United States)

    Raugh, Mike

    1990-01-01

    The Sparse Distributed Memory (SDM) project is investigating the theory and applications of massively parallel computing architecture, called sparse distributed memory, that will support the storage and retrieval of sensory and motor patterns characteristic of autonomous systems. The immediate objectives of the project are centered in studies of the memory itself and in the use of the memory to solve problems in speech, vision, and robotics. Investigation of methods for encoding sensory data is an important part of the research. Examples of NASA missions that may benefit from this work are Space Station, planetary rovers, and solar exploration. Sparse distributed memory offers promising technology for systems that must learn through experience and be capable of adapting to new circumstances, and for operating any large complex system requiring automatic monitoring and control. Sparse distributed memory is a massively parallel architecture motivated by efforts to understand how the human brain works. Sparse distributed memory is an associative memory, able to retrieve information from cues that only partially match patterns stored in the memory. It is able to store long temporal sequences derived from the behavior of a complex system, such as progressive records of the system's sensory data and correlated records of the system's motor controls.

  11. Virtual memory support for distributed computing environments using a shared data object model

    Science.gov (United States)

    Huang, F.; Bacon, J.; Mapp, G.

    1995-12-01

    Conventional storage management systems provide one interface for accessing memory segments and another for accessing secondary storage objects. This hinders application programming and affects overall system performance due to mandatory data copying and user/kernel boundary crossings, which in the microkernel case may involve context switches. Memory-mapping techniques may be used to provide programmers with a unified view of the storage system. This paper extends such techniques to support a shared data object model for distributed computing environments in which good support for coherence and synchronization is essential. The approach is based on a microkernel, typed memory objects, and integrated coherence control. A microkernel architecture is used to support multiple coherence protocols and the addition of new protocols. Memory objects are typed and applications can choose the most suitable protocols for different types of object to avoid protocol mismatch. Low-level coherence control is integrated with high-level concurrency control so that the number of messages required to maintain memory coherence is reduced and system-wide synchronization is realized without severely impacting the system performance. These features together contribute a novel approach to the support for flexible coherence under application control.

  12. Computational cost of isogeometric multi-frontal solvers on parallel distributed memory machines

    KAUST Repository

    Woźniak, Maciej

    2015-02-01

    This paper derives theoretical estimates of the computational cost for isogeometric multi-frontal direct solver executed on parallel distributed memory machines. We show theoretically that for the Cp-1 global continuity of the isogeometric solution, both the computational cost and the communication cost of a direct solver are of order O(log(N)p2) for the one dimensional (1D) case, O(Np2) for the two dimensional (2D) case, and O(N4/3p2) for the three dimensional (3D) case, where N is the number of degrees of freedom and p is the polynomial order of the B-spline basis functions. The theoretical estimates are verified by numerical experiments performed with three parallel multi-frontal direct solvers: MUMPS, PaStiX and SuperLU, available through PETIGA toolkit built on top of PETSc. Numerical results confirm these theoretical estimates both in terms of p and N. For a given problem size, the strong efficiency rapidly decreases as the number of processors increases, becoming about 20% for 256 processors for a 3D example with 1283 unknowns and linear B-splines with C0 global continuity, and 15% for a 3D example with 643 unknowns and quartic B-splines with C3 global continuity. At the same time, one cannot arbitrarily increase the problem size, since the memory required by higher order continuity spaces is large, quickly consuming all the available memory resources even in the parallel distributed memory version. Numerical results also suggest that the use of distributed parallel machines is highly beneficial when solving higher order continuity spaces, although the number of processors that one can efficiently employ is somehow limited.

  13. Studies of electron collisions with polyatomic molecules using distributed-memory parallel computers

    International Nuclear Information System (INIS)

    Winstead, C.; Hipes, P.G.; Lima, M.A.P.; McKoy, V.

    1991-01-01

    Elastic electron scattering cross sections from 5--30 eV are reported for the molecules C 2 H 4 , C 2 H 6 , C 3 H 8 , Si 2 H 6 , and GeH 4 , obtained using an implementation of the Schwinger multichannel method for distributed-memory parallel computer architectures. These results, obtained within the static-exchange approximation, are in generally good agreement with the available experimental data. These calculations demonstrate the potential of highly parallel computation in the study of collisions between low-energy electrons and polyatomic gases. The computational methodology discussed is also directly applicable to the calculation of elastic cross sections at higher levels of approximation (target polarization) and of electronic excitation cross sections

  14. ClimateSpark: An In-memory Distributed Computing Framework for Big Climate Data Analytics

    Science.gov (United States)

    Hu, F.; Yang, C. P.; Duffy, D.; Schnase, J. L.; Li, Z.

    2016-12-01

    Massive array-based climate data is being generated from global surveillance systems and model simulations. They are widely used to analyze the environment problems, such as climate changes, natural hazards, and public health. However, knowing the underlying information from these big climate datasets is challenging due to both data- and computing- intensive issues in data processing and analyzing. To tackle the challenges, this paper proposes ClimateSpark, an in-memory distributed computing framework to support big climate data processing. In ClimateSpark, the spatiotemporal index is developed to enable Apache Spark to treat the array-based climate data (e.g. netCDF4, HDF4) as native formats, which are stored in Hadoop Distributed File System (HDFS) without any preprocessing. Based on the index, the spatiotemporal query services are provided to retrieve dataset according to a defined geospatial and temporal bounding box. The data subsets will be read out, and a data partition strategy will be applied to equally split the queried data to each computing node, and store them in memory as climateRDDs for processing. By leveraging Spark SQL and User Defined Function (UDFs), the climate data analysis operations can be conducted by the intuitive SQL language. ClimateSpark is evaluated by two use cases using the NASA Modern-Era Retrospective Analysis for Research and Applications (MERRA) climate reanalysis dataset. One use case is to conduct the spatiotemporal query and visualize the subset results in animation; the other one is to compare different climate model outputs using Taylor-diagram service. Experimental results show that ClimateSpark can significantly accelerate data query and processing, and enable the complex analysis services served in the SQL-style fashion.

  15. ClimateSpark: An in-memory distributed computing framework for big climate data analytics

    Science.gov (United States)

    Hu, Fei; Yang, Chaowei; Schnase, John L.; Duffy, Daniel Q.; Xu, Mengchao; Bowen, Michael K.; Lee, Tsengdar; Song, Weiwei

    2018-06-01

    The unprecedented growth of climate data creates new opportunities for climate studies, and yet big climate data pose a grand challenge to climatologists to efficiently manage and analyze big data. The complexity of climate data content and analytical algorithms increases the difficulty of implementing algorithms on high performance computing systems. This paper proposes an in-memory, distributed computing framework, ClimateSpark, to facilitate complex big data analytics and time-consuming computational tasks. Chunking data structure improves parallel I/O efficiency, while a spatiotemporal index is built for the chunks to avoid unnecessary data reading and preprocessing. An integrated, multi-dimensional, array-based data model (ClimateRDD) and ETL operations are developed to address big climate data variety by integrating the processing components of the climate data lifecycle. ClimateSpark utilizes Spark SQL and Apache Zeppelin to develop a web portal to facilitate the interaction among climatologists, climate data, analytic operations and computing resources (e.g., using SQL query and Scala/Python notebook). Experimental results show that ClimateSpark conducts different spatiotemporal data queries/analytics with high efficiency and data locality. ClimateSpark is easily adaptable to other big multiple-dimensional, array-based datasets in various geoscience domains.

  16. 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

  17. 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.)

  18. 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.

  19. Construction and Application of an AMR Algorithm for Distributed Memory Computers

    OpenAIRE

    Deiterding, Ralf

    2003-01-01

    While the parallelization of blockstructured adaptive mesh refinement techniques is relatively straight-forward on shared memory architectures, appropriate distribution strategies for the emerging generation of distributed memory machines are a topic of on-going research. In this paper, a locality-preserving domain decomposition is proposed that partitions the entire AMR hierarchy from the base level on. It is shown that the approach reduces the communication costs and simplifies the im...

  20. Sparse distributed memory

    Science.gov (United States)

    Denning, Peter J.

    1989-01-01

    Sparse distributed memory was proposed be Pentti Kanerva as a realizable architecture that could store large patterns and retrieve them based on partial matches with patterns representing current sensory inputs. This memory exhibits behaviors, both in theory and in experiment, that resemble those previously unapproached by machines - e.g., rapid recognition of faces or odors, discovery of new connections between seemingly unrelated ideas, continuation of a sequence of events when given a cue from the middle, knowing that one doesn't know, or getting stuck with an answer on the tip of one's tongue. These behaviors are now within reach of machines that can be incorporated into the computing systems of robots capable of seeing, talking, and manipulating. Kanerva's theory is a break with the Western rationalistic tradition, allowing a new interpretation of learning and cognition that respects biology and the mysteries of individual human beings.

  1. 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.)

  2. 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.

  3. Efficient implementation of a 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

    2008-01-01

    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.

  4. Three-dimensional magnetic field computation on a distributed memory parallel processor

    International Nuclear Information System (INIS)

    Barion, M.L.

    1990-01-01

    The analysis of three-dimensional magnetic fields by finite element methods frequently proves too onerous a task for the computing resource on which it is attempted. When non-linear and transient effects are included, it may become impossible to calculate the field distribution to sufficient resolution. One approach to this problem is to exploit the natural parallelism in the finite element method via parallel processing. This paper reports on an implementation of a finite element code for non-linear three-dimensional low-frequency magnetic field calculation on Intel's iPSC/2

  5. Time complexity analysis for distributed memory computers: implementation of parallel conjugate gradient method

    NARCIS (Netherlands)

    Hoekstra, A.G.; Sloot, P.M.A.; Haan, M.J.; Hertzberger, L.O.; van Leeuwen, J.

    1991-01-01

    New developments in Computer Science, both hardware and software, offer researchers, such as physicists, unprecedented possibilities to solve their computational intensive problems.However, full exploitation of e.g. new massively parallel computers, parallel languages or runtime environments

  6. Parallelization of MCNP 4, a Monte Carlo neutron and photon transport code system, in highly parallel distributed memory type computer

    International Nuclear Information System (INIS)

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

    1993-11-01

    In order to improve the accuracy and calculating speed of shielding analyses, MCNP 4, a Monte Carlo neutron and photon transport code system, has been parallelized and measured of its efficiency in the highly parallel distributed memory type computer, AP1000. The code has been analyzed statically and dynamically, then the suitable algorithm for parallelization has been determined for the shielding analysis functions of MCNP 4. This includes a strategy where a new history is assigned to the idling processor element dynamically during the execution. Furthermore, to avoid the congestion of communicative processing, the batch concept, processing multi-histories by a unit, has been introduced. By analyzing a sample cask problem with 2,000,000 histories by the AP1000 with 512 processor elements, the 82 % of parallelization efficiency is achieved, and the calculational speed has been estimated to be around 50 times as fast as that of FACOM M-780. (author)

  7. Distributed-Memory Fast Maximal Independent Set

    Energy Technology Data Exchange (ETDEWEB)

    Kanewala Appuhamilage, Thejaka Amila J.; Zalewski, Marcin J.; Lumsdaine, Andrew

    2017-09-13

    The Maximal Independent Set (MIS) graph problem arises in many applications such as computer vision, information theory, molecular biology, and process scheduling. The growing scale of MIS problems suggests the use of distributed-memory hardware as a cost-effective approach to providing necessary compute and memory resources. Luby proposed four randomized algorithms to solve the MIS problem. All those algorithms are designed focusing on shared-memory machines and are analyzed using the PRAM model. These algorithms do not have direct efficient distributed-memory implementations. In this paper, we extend two of Luby’s seminal MIS algorithms, “Luby(A)” and “Luby(B),” to distributed-memory execution, and we evaluate their performance. We compare our results with the “Filtered MIS” implementation in the Combinatorial BLAS library for two types of synthetic graph inputs.

  8. 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

  9. A view of Kanerva's sparse distributed memory

    Science.gov (United States)

    Denning, P. J.

    1986-01-01

    Pentti Kanerva is working on a new class of computers, which are called pattern computers. Pattern computers may close the gap between capabilities of biological organisms to recognize and act on patterns (visual, auditory, tactile, or olfactory) and capabilities of modern computers. Combinations of numeric, symbolic, and pattern computers may one day be capable of sustaining robots. The overview of the requirements for a pattern computer, a summary of Kanerva's Sparse Distributed Memory (SDM), and examples of tasks this computer can be expected to perform well are given.

  10. 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.

  11. Self-Testing Computer Memory

    Science.gov (United States)

    Chau, Savio, N.; Rennels, David A.

    1988-01-01

    Memory system for computer repeatedly tests itself during brief, regular interruptions of normal processing of data. Detects and corrects transient faults as single-event upsets (changes in bits due to ionizing radiation) within milliseconds after occuring. Self-testing concept surpasses conventional by actively flushing latent defects out of memory and attempting to correct before accumulating beyond capacity for self-correction or detection. Cost of improvement modest increase in complexity of circuitry and operating time.

  12. A Comparison of Two Paradigms for Distributed Shared Memory

    NARCIS (Netherlands)

    Levelt, W.G.; Kaashoek, M.F.; Bal, H.E.; Tanenbaum, A.S.

    1992-01-01

    Two paradigms for distributed shared memory on loosely‐coupled computing systems are compared: the shared data‐object model as used in Orca, a programming language specially designed for loosely‐coupled computing systems, and the shared virtual memory model. For both paradigms two systems are

  13. 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.

  14. 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.

  15. 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

  16. Dynamic computing random access memory

    International Nuclear Information System (INIS)

    Traversa, F L; Bonani, F; Pershin, Y V; Di Ventra, M

    2014-01-01

    The present von Neumann computing paradigm involves a significant amount of information transfer between a central processing unit and memory, with concomitant limitations in the actual execution speed. However, it has been recently argued that a different form of computation, dubbed memcomputing (Di Ventra and Pershin 2013 Nat. Phys. 9 200–2) and inspired by the operation of our brain, can resolve the intrinsic limitations of present day architectures by allowing for computing and storing of information on the same physical platform. Here we show a simple and practical realization of memcomputing that utilizes easy-to-build memcapacitive systems. We name this architecture dynamic computing random access memory (DCRAM). We show that DCRAM provides massively-parallel and polymorphic digital logic, namely it allows for different logic operations with the same architecture, by varying only the control signals. In addition, by taking into account realistic parameters, its energy expenditures can be as low as a few fJ per operation. DCRAM is fully compatible with CMOS technology, can be realized with current fabrication facilities, and therefore can really serve as an alternative to the present computing technology. (paper)

  17. 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.

  18. Over-Distribution in Source Memory

    Science.gov (United States)

    Brainerd, C. J.; Reyna, V. F.; Holliday, R. E.; Nakamura, K.

    2012-01-01

    Semantic false memories are confounded with a second type of error, over-distribution, in which items are attributed to contradictory episodic states. Over-distribution errors have proved to be more common than false memories when the two are disentangled. We investigated whether over-distribution is prevalent in another classic false memory paradigm: source monitoring. It is. Conventional false memory responses (source misattributions) were predominantly over-distribution errors, but unlike semantic false memory, over-distribution also accounted for more than half of true memory responses (correct source attributions). Experimental control of over-distribution was achieved via a series of manipulations that affected either recollection of contextual details or item memory (concreteness, frequency, list-order, number of presentation contexts, and individual differences in verbatim memory). A theoretical model was used to analyze the data (conjoint process dissociation) that predicts that predicts that (a) over-distribution is directly proportional to item memory but inversely proportional to recollection and (b) item memory is not a necessary precondition for recollection of contextual details. The results were consistent with both predictions. PMID:21942494

  19. Total recall in distributive associative memories

    Science.gov (United States)

    Danforth, Douglas G.

    1991-01-01

    Iterative error correction of asymptotically large associative memories is equivalent to a one-step learning rule. This rule is the inverse of the activation function of the memory. Spectral representations of nonlinear activation functions are used to obtain the inverse in closed form for Sparse Distributed Memory, Selected-Coordinate Design, and Radial Basis Functions.

  20. The parallel processing of EGS4 code on distributed memory scalar parallel computer:Intel Paragon XP/S15-256

    Energy Technology Data Exchange (ETDEWEB)

    Takemiya, Hiroshi; Ohta, Hirofumi; Honma, Ichirou

    1996-03-01

    The parallelization of Electro-Magnetic Cascade Monte Carlo Simulation Code, EGS4 on distributed memory scalar parallel computer: Intel Paragon XP/S15-256 is described. EGS4 has the feature that calculation time for one incident particle is quite different from each other because of the dynamic generation of secondary particles and different behavior of each particle. Granularity for parallel processing, parallel programming model and the algorithm of parallel random number generation are discussed and two kinds of method, each of which allocates particles dynamically or statically, are used for the purpose of realizing high speed parallel processing of this code. Among four problems chosen for performance evaluation, the speedup factors for three problems have been attained to nearly 100 times with 128 processor. It has been found that when both the calculation time for each incident particles and its dispersion are large, it is preferable to use dynamic particle allocation method which can average the load for each processor. And it has also been found that when they are small, it is preferable to use static particle allocation method which reduces the communication overhead. Moreover, it is pointed out that to get the result accurately, it is necessary to use double precision variables in EGS4 code. Finally, the workflow of program parallelization is analyzed and tools for program parallelization through the experience of the EGS4 parallelization are discussed. (author).

  1. The computational nature of memory modification.

    Science.gov (United States)

    Gershman, Samuel J; Monfils, Marie-H; Norman, Kenneth A; Niv, Yael

    2017-03-15

    Retrieving a memory can modify its influence on subsequent behavior. We develop a computational theory of memory modification, according to which modification of a memory trace occurs through classical associative learning, but which memory trace is eligible for modification depends on a structure learning mechanism that discovers the units of association by segmenting the stream of experience into statistically distinct clusters (latent causes). New memories are formed when the structure learning mechanism infers that a new latent cause underlies current sensory observations. By the same token, old memories are modified when old and new sensory observations are inferred to have been generated by the same latent cause. We derive this framework from probabilistic principles, and present a computational implementation. Simulations demonstrate that our model can reproduce the major experimental findings from studies of memory modification in the Pavlovian conditioning literature.

  2. The computational nature of memory modification

    Science.gov (United States)

    Gershman, Samuel J; Monfils, Marie-H; Norman, Kenneth A; Niv, Yael

    2017-01-01

    Retrieving a memory can modify its influence on subsequent behavior. We develop a computational theory of memory modification, according to which modification of a memory trace occurs through classical associative learning, but which memory trace is eligible for modification depends on a structure learning mechanism that discovers the units of association by segmenting the stream of experience into statistically distinct clusters (latent causes). New memories are formed when the structure learning mechanism infers that a new latent cause underlies current sensory observations. By the same token, old memories are modified when old and new sensory observations are inferred to have been generated by the same latent cause. We derive this framework from probabilistic principles, and present a computational implementation. Simulations demonstrate that our model can reproduce the major experimental findings from studies of memory modification in the Pavlovian conditioning literature. DOI: http://dx.doi.org/10.7554/eLife.23763.001 PMID:28294944

  3. Distributed learning enhances relational memory consolidation.

    Science.gov (United States)

    Litman, Leib; Davachi, Lila

    2008-09-01

    It has long been known that distributed learning (DL) provides a mnemonic advantage over massed learning (ML). However, the underlying mechanisms that drive this robust mnemonic effect remain largely unknown. In two experiments, we show that DL across a 24 hr interval does not enhance immediate memory performance but instead slows the rate of forgetting relative to ML. Furthermore, we demonstrate that this savings in forgetting is specific to relational, but not item, memory. In the context of extant theories and knowledge of memory consolidation, these results suggest that an important mechanism underlying the mnemonic benefit of DL is enhanced memory consolidation. We speculate that synaptic strengthening mechanisms supporting long-term memory consolidation may be differentially mediated by the spacing of memory reactivation. These findings have broad implications for the scientific study of episodic memory consolidation and, more generally, for educational curriculum development and policy.

  4. Parallel structures in human and computer memory

    Science.gov (United States)

    Kanerva, Pentti

    1986-08-01

    If we think of our experiences as being recorded continuously on film, then human memory can be compared to a film library that is indexed by the contents of the film strips stored in it. Moreover, approximate retrieval cues suffice to retrieve information stored in this library: We recognize a familiar person in a fuzzy photograph or a familiar tune played on a strange instrument. This paper is about how to construct a computer memory that would allow a computer to recognize patterns and to recall sequences the way humans do. Such a memory is remarkably similar in structure to a conventional computer memory and also to the neural circuits in the cortex of the cerebellum of the human brain. The paper concludes that the frame problem of artificial intelligence could be solved by the use of such a memory if we were able to encode information about the world properly.

  5. Human Memory Organization for Computer Programs.

    Science.gov (United States)

    Norcio, A. F.; Kerst, Stephen M.

    1983-01-01

    Results of study investigating human memory organization in processing of computer programming languages indicate that algorithmic logic segments form a cognitive organizational structure in memory for programs. Statement indentation and internal program documentation did not enhance organizational process of recall of statements in five Fortran…

  6. Computing betweenness centrality in external memory

    DEFF Research Database (Denmark)

    Arge, Lars; Goodrich, Michael T.; Walderveen, Freek van

    2013-01-01

    Betweenness centrality is one of the most well-known measures of the importance of nodes in a social-network graph. In this paper we describe the first known external-memory and cache-oblivious algorithms for computing betweenness centrality. We present four different external-memory algorithms...

  7. Computer Icons and the Art of Memory.

    Science.gov (United States)

    McNair, John R.

    1996-01-01

    States that key aspects of "memoria," the ancient Art of Memory, especially its focus on vivid representational images set against distinct backgrounds, can be helpful in creating memorable, universal, and easily retrievable computer icons. (PA)

  8. 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...

  9. Memory Reconsolidation and Computational Learning

    Science.gov (United States)

    2010-03-01

    Siegelmann-Danieli and H.T. Siegelmann, "Robust Artificial Life Via Artificial Programmed Death," Artificial Inteligence 172(6-7), April 2008: 884-898. F...STATEMENT Unrestricted 13. SUPPLEMENTARY NOTES 20100402019 14. ABSTRACT Memory models are central to Artificial Intelligence and Machine...beyond [1]. The advances cited are a significant step toward creating Artificial Intelligence via neural networks at the human level. Our network

  10. 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

  11. 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

  12. Implementation of Parallel Dynamic Simulation on Shared-Memory vs. Distributed-Memory Environments

    Energy Technology Data Exchange (ETDEWEB)

    Jin, Shuangshuang; Chen, Yousu; Wu, Di; Diao, Ruisheng; Huang, Zhenyu

    2015-12-09

    Power system dynamic simulation computes the system response to a sequence of large disturbance, such as sudden changes in generation or load, or a network short circuit followed by protective branch switching operation. It consists of a large set of differential and algebraic equations, which is computational intensive and challenging to solve using single-processor based dynamic simulation solution. High-performance computing (HPC) based parallel computing is a very promising technology to speed up the computation and facilitate the simulation process. This paper presents two different parallel implementations of power grid dynamic simulation using Open Multi-processing (OpenMP) on shared-memory platform, and Message Passing Interface (MPI) on distributed-memory clusters, respectively. The difference of the parallel simulation algorithms and architectures of the two HPC technologies are illustrated, and their performances for running parallel dynamic simulation are compared and demonstrated.

  13. Resistive content addressable memory based in-memory computation architecture

    KAUST Repository

    Salama, Khaled N.; Zidan, Mohammed A.; Kurdahi, Fadi; Eltawil, Ahmed M.

    2016-01-01

    Various examples are provided examples related to resistive content addressable memory (RCAM) based in-memory computation architectures. In one example, a system includes a content addressable memory (CAM) including an array of cells having a memristor based crossbar and an interconnection switch matrix having a gateless memristor array, which is coupled to an output of the CAM. In another example, a method, includes comparing activated bit values stored a key register with corresponding bit values in a row of a CAM, setting a tag bit value to indicate that the activated bit values match the corresponding bit values, and writing masked key bit values to corresponding bit locations in the row of the CAM based on the tag bit value.

  14. Resistive content addressable memory based in-memory computation architecture

    KAUST Repository

    Salama, Khaled N.

    2016-12-08

    Various examples are provided examples related to resistive content addressable memory (RCAM) based in-memory computation architectures. In one example, a system includes a content addressable memory (CAM) including an array of cells having a memristor based crossbar and an interconnection switch matrix having a gateless memristor array, which is coupled to an output of the CAM. In another example, a method, includes comparing activated bit values stored a key register with corresponding bit values in a row of a CAM, setting a tag bit value to indicate that the activated bit values match the corresponding bit values, and writing masked key bit values to corresponding bit locations in the row of the CAM based on the tag bit value.

  15. The Distributed Nature of Working Memory

    NARCIS (Netherlands)

    Christophel, Thomas B.; Klink, P. Christiaan; Spitzer, Bernhard; Roelfsema, Pieter R.; Haynes, John-Dylan

    2017-01-01

    Studies in humans and non-human primates have provided evidence for storage of working memory contents in multiple regions ranging from sensory to parietal and prefrontal cortex. We discuss potential explanations for these distributed representations: (i) features in sensory regions versus

  16. 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.

  17. 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

  18. 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

  19. Distributed terascale volume visualization using distributed shared virtual memory

    KAUST Repository

    Beyer, Johanna; Hadwiger, Markus; Schneider, Jens; Jeong, Wonki; Pfister, Hanspeter

    2011-01-01

    Table 1 illustrates the impact of different distribution unit sizes, different screen resolutions, and numbers of GPU nodes. We use two and four GPUs (NVIDIA Quadro 5000 with 2.5 GB memory) and a mouse cortex EM dataset (see Figure 2) of resolution

  20. Distributed terascale volume visualization using distributed shared virtual memory

    KAUST Repository

    Beyer, Johanna

    2011-10-01

    Table 1 illustrates the impact of different distribution unit sizes, different screen resolutions, and numbers of GPU nodes. We use two and four GPUs (NVIDIA Quadro 5000 with 2.5 GB memory) and a mouse cortex EM dataset (see Figure 2) of resolution 21,494 x 25,790 x 1,850 = 955GB. The size of the virtual distribution units significantly influences the data distribution between nodes. Small distribution units result in a high depth complexity for compositing. Large distribution units lead to a low utilization of GPUs, because in the worst case only a single distribution unit will be in view, which is rendered by only a single node. The choice of an optimal distribution unit size depends on three major factors: the output screen resolution, the block cache size on each node, and the number of nodes. Currently, we are working on optimizing the compositing step and network communication between nodes. © 2011 IEEE.

  1. Lifetime-Based Memory Management for Distributed Data Processing Systems

    DEFF Research Database (Denmark)

    Lu, Lu; Shi, Xuanhua; Zhou, Yongluan

    2016-01-01

    create a large amount of long-living data objects in the heap, which may quickly saturate the garbage collector, especially when handling a large dataset, and hence would limit the scalability of the system. To eliminate this problem, we propose a lifetime-based memory management framework, which...... the garbage collection time by up to 99.9%, 2) to achieve up to 22.7x speed up in terms of execution time in cases without data spilling and 41.6x speedup in cases with data spilling, and 3) to consume up to 46.6% less memory.......In-memory caching of intermediate data and eager combining of data in shuffle buffers have been shown to be very effective in minimizing the re-computation and I/O cost in distributed data processing systems like Spark and Flink. However, it has also been widely reported that these techniques would...

  2. Associative Memory Computing Power and Its Simulation

    CERN Document Server

    Volpi, G; The ATLAS collaboration

    2014-01-01

    The associative memory (AM) system is a computing device made of hundreds of AM ASICs chips designed to perform “pattern matching” at very high speed. Since each AM chip stores a data base of 130000 pre-calculated patterns and large numbers of chips can be easily assembled together, it is possible to produce huge AM banks. Speed and size of the system are crucial for real-time High Energy Physics applications, such as the ATLAS Fast TracKer (FTK) Processor. Using 80 million channels of the ATLAS tracker, FTK finds tracks within 100 micro seconds. The simulation of such a parallelized system is an extremely complex task if executed in commercial computers based on normal CPUs. The algorithm performance is limited, due to the lack of parallelism, and in addition the memory requirement is very large. In fact the AM chip uses a content addressable memory (CAM) architecture. Any data inquiry is broadcast to all memory elements simultaneously, thus data retrieval time is independent of the database size. The gr...

  3. Associative Memory computing power and its simulation

    CERN Document Server

    Ancu, L S; The ATLAS collaboration; Britzger, D; Giannetti, P; Howarth, J W; Luongo, C; Pandini, C; Schmitt, S; Volpi, G

    2014-01-01

    The associative memory (AM) system is a computing device made of hundreds of AM ASICs chips designed to perform “pattern matching” at very high speed. Since each AM chip stores a data base of 130000 pre-calculated patterns and large numbers of chips can be easily assembled together, it is possible to produce huge AM banks. Speed and size of the system are crucial for real-time High Energy Physics applications, such as the ATLAS Fast TracKer (FTK) Processor. Using 80 million channels of the ATLAS tracker, FTK finds tracks within 100 micro seconds. The simulation of such a parallelized system is an extremely complex task if executed in commercial computers based on normal CPUs. The algorithm performance is limited, due to the lack of parallelism, and in addition the memory requirement is very large. In fact the AM chip uses a content addressable memory (CAM) architecture. Any data inquiry is broadcast to all memory elements simultaneously, thus data retrieval time is independent of the database size. The gr...

  4. Computing visibility on terrains in external memory

    NARCIS (Netherlands)

    Haverkort, H.J.; Toma, L.; Zhuang, Yi

    2007-01-01

    We describe a novel application of the distribution sweeping technique to computing visibility on terrains. Given an arbitrary viewpoint v, the basic problem we address is computing the visibility map or viewshed of v, which is the set of points in the terrain that are visible from v. We give the

  5. A general purpose subroutine for fast fourier transform on a distributed memory parallel machine

    Science.gov (United States)

    Dubey, A.; Zubair, M.; Grosch, C. E.

    1992-01-01

    One issue which is central in developing a general purpose Fast Fourier Transform (FFT) subroutine on a distributed memory parallel machine is the data distribution. It is possible that different users would like to use the FFT routine with different data distributions. Thus, there is a need to design FFT schemes on distributed memory parallel machines which can support a variety of data distributions. An FFT implementation on a distributed memory parallel machine which works for a number of data distributions commonly encountered in scientific applications is presented. The problem of rearranging the data after computing the FFT is also addressed. The performance of the implementation on a distributed memory parallel machine Intel iPSC/860 is evaluated.

  6. Overlapping clusters for distributed computation.

    Energy Technology Data Exchange (ETDEWEB)

    Mirrokni, Vahab (Google Research, New York, NY); Andersen, Reid (Microsoft Corporation, Redmond, WA); Gleich, David F.

    2010-11-01

    Scalable, distributed algorithms must address communication problems. We investigate overlapping clusters, or vertex partitions that intersect, for graph computations. This setup stores more of the graph than required but then affords the ease of implementation of vertex partitioned algorithms. Our hope is that this technique allows us to reduce communication in a computation on a distributed graph. The motivation above draws on recent work in communication avoiding algorithms. Mohiyuddin et al. (SC09) design a matrix-powers kernel that gives rise to an overlapping partition. Fritzsche et al. (CSC2009) develop an overlapping clustering for a Schwarz method. Both techniques extend an initial partitioning with overlap. Our procedure generates overlap directly. Indeed, Schwarz methods are commonly used to capitalize on overlap. Elsewhere, overlapping communities (Ahn et al, Nature 2009; Mishra et al. WAW2007) are now a popular model of structure in social networks. These have long been studied in statistics (Cole and Wishart, CompJ 1970). We present two types of results: (i) an estimated swapping probability {rho}{infinity}; and (ii) the communication volume of a parallel PageRank solution (link-following {alpha} = 0.85) using an additive Schwarz method. The volume ratio is the amount of extra storage for the overlap (2 means we store the graph twice). Below, as the ratio increases, the swapping probability and PageRank communication volume decreases.

  7. Paging memory from random access memory to backing storage in a parallel computer

    Science.gov (United States)

    Archer, Charles J; Blocksome, Michael A; Inglett, Todd A; Ratterman, Joseph D; Smith, Brian E

    2013-05-21

    Paging memory from random access memory (`RAM`) to backing storage in a parallel computer that includes a plurality of compute nodes, including: executing a data processing application on a virtual machine operating system in a virtual machine on a first compute node; providing, by a second compute node, backing storage for the contents of RAM on the first compute node; and swapping, by the virtual machine operating system in the virtual machine on the first compute node, a page of memory from RAM on the first compute node to the backing storage on the second compute node.

  8. Towards distributed multiscale computing for the VPH

    NARCIS (Netherlands)

    Hoekstra, A.G.; Coveney, P.

    2010-01-01

    Multiscale modeling is fundamental to the Virtual Physiological Human (VPH) initiative. Most detailed three-dimensional multiscale models lead to prohibitive computational demands. As a possible solution we present MAPPER, a computational science infrastructure for Distributed Multiscale Computing

  9. Languages, compilers and run-time environments for distributed memory machines

    CERN Document Server

    Saltz, J

    1992-01-01

    Papers presented within this volume cover a wide range of topics related to programming distributed memory machines. Distributed memory architectures, although having the potential to supply the very high levels of performance required to support future computing needs, present awkward programming problems. The major issue is to design methods which enable compilers to generate efficient distributed memory programs from relatively machine independent program specifications. This book is the compilation of papers describing a wide range of research efforts aimed at easing the task of programmin

  10. Migration of vectorized iterative solvers to distributed memory architectures

    Energy Technology Data Exchange (ETDEWEB)

    Pommerell, C. [AT& T Bell Labs., Murray Hill, NJ (United States); Ruehl, R. [CSCS-ETH, Manno (Switzerland)

    1994-12-31

    Both necessity and opportunity motivate the use of high-performance computers for iterative linear solvers. Necessity results from the size of the problems being solved-smaller problems are often better handled by direct methods. Opportunity arises from the formulation of the iterative methods in terms of simple linear algebra operations, even if this {open_quote}natural{close_quotes} parallelism is not easy to exploit in irregularly structured sparse matrices and with good preconditioners. As a result, high-performance implementations of iterative solvers have attracted a lot of interest in recent years. Most efforts are geared to vectorize or parallelize the dominating operation-structured or unstructured sparse matrix-vector multiplication, or to increase locality and parallelism by reformulating the algorithm-reducing global synchronization in inner products or local data exchange in preconditioners. Target architectures for iterative solvers currently include mostly vector supercomputers and architectures with one or few optimized (e.g., super-scalar and/or super-pipelined RISC) processors and hierarchical memory systems. More recently, parallel computers with physically distributed memory and a better price/performance ratio have been offered by vendors as a very interesting alternative to vector supercomputers. However, programming comfort on such distributed memory parallel processors (DMPPs) still lags behind. Here the authors are concerned with iterative solvers and their changing computing environment. In particular, they are considering migration from traditional vector supercomputers to DMPPs. Application requirements force one to use flexible and portable libraries. They want to extend the portability of iterative solvers rather than reimplementing everything for each new machine, or even for each new architecture.

  11. 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…

  12. The Distributed Memory Computing Conference (5th) Held in Charleston, South Carolina on April 8-12, 1990. Volume 1. Applications

    Science.gov (United States)

    1991-03-31

    194 R. Battiti Session 8: Ray Tracing Hypercube Algorithm for Radiosity in a Ray Tracing Environment ............. 206 S.A. Hermitage, T.L...for Radiosity in a Ray Tracing Environment Shirley A. Hermitage Terrance L. Huntsberger Department of Computer Science Beverly A. Huntsberger Augusta...Abstract or transmitted, and in most cases, ignores any diffuse reflection. Radiosity , on the other hand, attempts to account for a phenomenon that ray

  13. Parallel Breadth-First Search on Distributed Memory Systems

    Energy Technology Data Exchange (ETDEWEB)

    Computational Research Division; Buluc, Aydin; Madduri, Kamesh

    2011-04-15

    Data-intensive, graph-based computations are pervasive in several scientific applications, and are known to to be quite challenging to implement on distributed memory systems. In this work, we explore the design space of parallel algorithms for Breadth-First Search (BFS), a key subroutine in several graph algorithms. We present two highly-tuned par- allel approaches for BFS on large parallel systems: a level-synchronous strategy that relies on a simple vertex-based partitioning of the graph, and a two-dimensional sparse matrix- partitioning-based approach that mitigates parallel commu- nication overhead. For both approaches, we also present hybrid versions with intra-node multithreading. Our novel hybrid two-dimensional algorithm reduces communication times by up to a factor of 3.5, relative to a common vertex based approach. Our experimental study identifies execu- tion regimes in which these approaches will be competitive, and we demonstrate extremely high performance on lead- ing distributed-memory parallel systems. For instance, for a 40,000-core parallel execution on Hopper, an AMD Magny- Cours based system, we achieve a BFS performance rate of 17.8 billion edge visits per second on an undirected graph of 4.3 billion vertices and 68.7 billion edges with skewed degree distribution.

  14. Optimizing NEURON Simulation Environment Using Remote Memory Access with Recursive Doubling on Distributed Memory Systems.

    Science.gov (United States)

    Shehzad, Danish; Bozkuş, Zeki

    2016-01-01

    Increase in complexity of neuronal network models escalated the efforts to make NEURON simulation environment efficient. The computational neuroscientists divided the equations into subnets amongst multiple processors for achieving better hardware performance. On parallel machines for neuronal networks, interprocessor spikes exchange consumes large section of overall simulation time. In NEURON for communication between processors Message Passing Interface (MPI) is used. MPI_Allgather collective is exercised for spikes exchange after each interval across distributed memory systems. The increase in number of processors though results in achieving concurrency and better performance but it inversely affects MPI_Allgather which increases communication time between processors. This necessitates improving communication methodology to decrease the spikes exchange time over distributed memory systems. This work has improved MPI_Allgather method using Remote Memory Access (RMA) by moving two-sided communication to one-sided communication, and use of recursive doubling mechanism facilitates achieving efficient communication between the processors in precise steps. This approach enhanced communication concurrency and has improved overall runtime making NEURON more efficient for simulation of large neuronal network models.

  15. Optimizing NEURON Simulation Environment Using Remote Memory Access with Recursive Doubling on Distributed Memory Systems

    Directory of Open Access Journals (Sweden)

    Danish Shehzad

    2016-01-01

    Full Text Available Increase in complexity of neuronal network models escalated the efforts to make NEURON simulation environment efficient. The computational neuroscientists divided the equations into subnets amongst multiple processors for achieving better hardware performance. On parallel machines for neuronal networks, interprocessor spikes exchange consumes large section of overall simulation time. In NEURON for communication between processors Message Passing Interface (MPI is used. MPI_Allgather collective is exercised for spikes exchange after each interval across distributed memory systems. The increase in number of processors though results in achieving concurrency and better performance but it inversely affects MPI_Allgather which increases communication time between processors. This necessitates improving communication methodology to decrease the spikes exchange time over distributed memory systems. This work has improved MPI_Allgather method using Remote Memory Access (RMA by moving two-sided communication to one-sided communication, and use of recursive doubling mechanism facilitates achieving efficient communication between the processors in precise steps. This approach enhanced communication concurrency and has improved overall runtime making NEURON more efficient for simulation of large neuronal network models.

  16. Distributed Shared Memory for the Cell Broadband Engine (DSMCBE)

    DEFF Research Database (Denmark)

    Larsen, Morten Nørgaard; Skovhede, Kenneth; Vinter, Brian

    2009-01-01

    in and out of non-coherent local storage blocks for each special processor element. In this paper we present a software library, namely the Distributed Shared Memory for the Cell Broadband Engine (DSMCBE). By using techniques known from distributed shared memory DSMCBE allows programmers to program the CELL...

  17. Memory systems, computation, and the second law of thermodynamics

    International Nuclear Information System (INIS)

    Wolpert, D.H.

    1992-01-01

    A memory is a physical system for transferring information form one moment in time to another, where that information concerns something external to the system itself. This paper argues on information-theoretic and statistical mechanical grounds that useful memories must be of one of two types, exemplified by memory in abstract computer programs and by memory in photographs. Photograph-type memories work by exploring a collapse of state space flow to an attractor state. (This attractor state is the open-quotes initializedclose quotes state of the memory.) The central assumption of the theory of reversible computation tells us that in any such collapsing, regardless of whether the collapsing must increase in entropy of the system. In concert with the second law, this establishes the logical necessity of the empirical observation that photograph-type memories are temporally asymmetric (they can tell us about the past but not about the future). Under the assumption that human memory is a photograph-type memory, this result also explains why we humans can remember only our past and not our future. In contrast to photo-graph-type memories, computer-type memories do not require any initialization, and therefore are not directly affected by the second law. As a result, computer memories can be of the future as easily as of the past, even if the program running on the computer is logically irreversible. This is entirely in accord with the well-known temporal reversibility of the process of computation. This paper ends by arguing that the asymmetry of the psychological arrow of time is a direct consequence of the asymmetry of human memory. With the rest of this paper, this explains, explicitly and rigorously, why the psychological and thermodynamic arrows of time are correlated with one another. 24 refs

  18. 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...

  19. A distributed computer system for digitising machines

    International Nuclear Information System (INIS)

    Bairstow, R.; Barlow, J.; Waters, M.; Watson, J.

    1977-07-01

    This paper describes a Distributed Computing System, based on micro computers, for the monitoring and control of digitising tables used by the Rutherford Laboratory Bubble Chamber Research Group in the measurement of bubble chamber photographs. (author)

  20. Amorphous Semiconductors: From Photocatalyst to Computer Memory

    Science.gov (United States)

    Sundararajan, Mayur

    encouraging but inconclusive. Then the method was successfully demonstrated on mesoporous TiO2SiO 2 by showing a shift in its optical bandgap. One of the special class of amorphous semiconductors is chalcogenide glasses, which exhibit high ionic conductivity even at room temperature. When metal doped chalcogenide glasses are under an electric field, they become electronically conductive. These properties are exploited in the computer memory storage application of Conductive Bridging Random Access Memory (CBRAM). CBRAM is a non-volatile memory that is a strong contender to replace conventional volatile RAMs such as DRAM, SRAM, etc. This technology has already been commercialized, but the working mechanism is still not clearly understood especially the nature of the conductive bridge filament. In this project, the CBRAM memory cells are fabricated by thermal evaporation method with Agx(GeSe 2)1-x as the solid electrolyte layer, Ag as the active electrode and Au as the inert electrode. By careful use of cyclic voltammetry, the conductive filaments were grown on the surface and the bulk of the solid electrolyte. The comparison between the two filaments revealed major differences leading to contradiction with the existing working mechanism. After compiling all the results, a modified working mechanism is proposed. SAXS is a powerful tool to characterize nanostructure of glasses. The analysis of the SAXS data to get useful information are usually performed by different programs. In this project, Irena and GIFT programs were compared by performing the analysis of the SAXS data of glass and glass ceramics samples. Irena was shown to be not suitable for the analysis of SAXS data that has a significant contribution from interparticle interactions. GIFT was demonstrated to be better suited for such analysis. Additionally, the results obtained by programs for samples with low interparticle interactions were shown to be consistent.

  1. Memory-assisted measurement-device-independent quantum key distribution

    Science.gov (United States)

    Panayi, Christiana; Razavi, Mohsen; Ma, Xiongfeng; Lütkenhaus, Norbert

    2014-04-01

    A protocol with the potential of beating the existing distance records for conventional quantum key distribution (QKD) systems is proposed. It borrows ideas from quantum repeaters by using memories in the middle of the link, and that of measurement-device-independent QKD, which only requires optical source equipment at the user's end. For certain memories with short access times, our scheme allows a higher repetition rate than that of quantum repeaters with single-mode memories, thereby requiring lower coherence times. By accounting for various sources of nonideality, such as memory decoherence, dark counts, misalignment errors, and background noise, as well as timing issues with memories, we develop a mathematical framework within which we can compare QKD systems with and without memories. In particular, we show that with the state-of-the-art technology for quantum memories, it is potentially possible to devise memory-assisted QKD systems that, at certain distances of practical interest, outperform current QKD implementations.

  2. Large scale particle simulations in a virtual memory computer

    International Nuclear Information System (INIS)

    Gray, P.C.; Million, R.; Wagner, J.S.; Tajima, T.

    1983-01-01

    Virtual memory computers are capable of executing large-scale particle simulations even when the memory requirements exceeds the computer core size. The required address space is automatically mapped onto slow disc memory the the operating system. When the simulation size is very large, frequent random accesses to slow memory occur during the charge accumulation and particle pushing processes. Assesses to slow memory significantly reduce the excecution rate of the simulation. We demonstrate in this paper that with the proper choice of sorting algorithm, a nominal amount of sorting to keep physically adjacent particles near particles with neighboring array indices can reduce random access to slow memory, increase the efficiency of the I/O system, and hence, reduce the required computing time. (orig.)

  3. A simplified computational memory model from information processing

    Science.gov (United States)

    Zhang, Lanhua; Zhang, Dongsheng; Deng, Yuqin; Ding, Xiaoqian; Wang, Yan; Tang, Yiyuan; Sun, Baoliang

    2016-01-01

    This paper is intended to propose a computational model for memory from the view of information processing. The model, called simplified memory information retrieval network (SMIRN), is a bi-modular hierarchical functional memory network by abstracting memory function and simulating memory information processing. At first meta-memory is defined to express the neuron or brain cortices based on the biology and graph theories, and we develop an intra-modular network with the modeling algorithm by mapping the node and edge, and then the bi-modular network is delineated with intra-modular and inter-modular. At last a polynomial retrieval algorithm is introduced. In this paper we simulate the memory phenomena and functions of memorization and strengthening by information processing algorithms. The theoretical analysis and the simulation results show that the model is in accordance with the memory phenomena from information processing view. PMID:27876847

  4. A simplified computational memory model from information processing.

    Science.gov (United States)

    Zhang, Lanhua; Zhang, Dongsheng; Deng, Yuqin; Ding, Xiaoqian; Wang, Yan; Tang, Yiyuan; Sun, Baoliang

    2016-11-23

    This paper is intended to propose a computational model for memory from the view of information processing. The model, called simplified memory information retrieval network (SMIRN), is a bi-modular hierarchical functional memory network by abstracting memory function and simulating memory information processing. At first meta-memory is defined to express the neuron or brain cortices based on the biology and graph theories, and we develop an intra-modular network with the modeling algorithm by mapping the node and edge, and then the bi-modular network is delineated with intra-modular and inter-modular. At last a polynomial retrieval algorithm is introduced. In this paper we simulate the memory phenomena and functions of memorization and strengthening by information processing algorithms. The theoretical analysis and the simulation results show that the model is in accordance with the memory phenomena from information processing view.

  5. Distributed Processing in Cloud Computing

    OpenAIRE

    Mavridis, Ilias; Karatza, Eleni

    2016-01-01

    Proceedings of the First PhD Symposium on Sustainable Ultrascale Computing Systems (NESUS PhD 2016) Timisoara, Romania. February 8-11, 2016. Cloud computing offers a wide range of resources and services through the Internet that can been used for various purposes. The rapid growth of cloud computing has exempted many companies and institutions from the burden of maintaining expensive hardware and software infrastructure. With characteristics like high scalability, availability ...

  6. 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

  7. The Spacetime Memory of Geometric Phases and Quantum Computing

    CERN Document Server

    Binder, B

    2002-01-01

    Spacetime memory is defined with a holonomic approach to information processing, where multi-state stability is introduced by a non-linear phase-locked loop. Geometric phases serve as the carrier of physical information and geometric memory (of orientation) given by a path integral measure of curvature that is periodically refreshed. Regarding the resulting spin-orbit coupling and gauge field, the geometric nature of spacetime memory suggests to assign intrinsic computational properties to the electromagnetic field.

  8. 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.

  9. Distributed trace using central performance counter memory

    Science.gov (United States)

    Satterfield, David L.; Sexton, James C.

    2013-01-22

    A plurality of processing cores, are central storage unit having at least memory connected in a daisy chain manner, forming a daisy chain ring layout on an integrated chip. At least one of the plurality of processing cores places trace data on the daisy chain connection for transmitting the trace data to the central storage unit, and the central storage unit detects the trace data and stores the trace data in the memory co-located in with the central storage unit.

  10. Fel simulations using distributed computing

    NARCIS (Netherlands)

    Einstein, J.; Biedron, S.G.; Freund, H.P.; Milton, S.V.; Van Der Slot, P. J M; Bernabeu, G.

    2016-01-01

    While simulation tools are available and have been used regularly for simulating light sources, including Free-Electron Lasers, the increasing availability and lower cost of accelerated computing opens up new opportunities. This paper highlights a method of how accelerating and parallelizing code

  11. Exact distributions of two-sample rank statistics and block rank statistics using computer algebra

    NARCIS (Netherlands)

    Wiel, van de M.A.

    1998-01-01

    We derive generating functions for various rank statistics and we use computer algebra to compute the exact null distribution of these statistics. We present various techniques for reducing time and memory space used by the computations. We use the results to write Mathematica notebooks for

  12. Massively Parallel Polar Decomposition on Distributed-Memory Systems

    KAUST Repository

    Ltaief, Hatem; Sukkari, Dalal E.; Esposito, Aniello; Nakatsukasa, Yuji; Keyes, David E.

    2018-01-01

    We present a high-performance implementation of the Polar Decomposition (PD) on distributed-memory systems. Building upon on the QR-based Dynamically Weighted Halley (QDWH) algorithm, the key idea lies in finding the best rational approximation

  13. Computational modelling of memory retention from synapse to behaviour

    Science.gov (United States)

    van Rossum, Mark C. W.; Shippi, Maria

    2013-03-01

    One of our most intriguing mental abilities is the capacity to store information and recall it from memory. Computational neuroscience has been influential in developing models and concepts of learning and memory. In this tutorial review we focus on the interplay between learning and forgetting. We discuss recent advances in the computational description of the learning and forgetting processes on synaptic, neuronal, and systems levels, as well as recent data that open up new challenges for statistical physicists.

  14. Computational modelling of memory retention from synapse to behaviour

    International Nuclear Information System (INIS)

    Van Rossum, Mark C W; Shippi, Maria

    2013-01-01

    One of our most intriguing mental abilities is the capacity to store information and recall it from memory. Computational neuroscience has been influential in developing models and concepts of learning and memory. In this tutorial review we focus on the interplay between learning and forgetting. We discuss recent advances in the computational description of the learning and forgetting processes on synaptic, neuronal, and systems levels, as well as recent data that open up new challenges for statistical physicists. (paper)

  15. 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.

  16. Static Memory Deduplication for Performance Optimization in Cloud Computing

    Directory of Open Access Journals (Sweden)

    Gangyong Jia

    2017-04-01

    Full Text Available In a cloud computing environment, the number of virtual machines (VMs on a single physical server and the number of applications running on each VM are continuously growing. This has led to an enormous increase in the demand of memory capacity and subsequent increase in the energy consumption in the cloud. Lack of enough memory has become a major bottleneck for scalability and performance of virtualization interfaces in cloud computing. To address this problem, memory deduplication techniques which reduce memory demand through page sharing are being adopted. However, such techniques suffer from overheads in terms of number of online comparisons required for the memory deduplication. In this paper, we propose a static memory deduplication (SMD technique which can reduce memory capacity requirement and provide performance optimization in cloud computing. The main innovation of SMD is that the process of page detection is performed offline, thus potentially reducing the performance cost, especially in terms of response time. In SMD, page comparisons are restricted to the code segment, which has the highest shared content. Our experimental results show that SMD efficiently reduces memory capacity requirement and improves performance. We demonstrate that, compared to other approaches, the cost in terms of the response time is negligible.

  17. Static Memory Deduplication for Performance Optimization in Cloud Computing.

    Science.gov (United States)

    Jia, Gangyong; Han, Guangjie; Wang, Hao; Yang, Xuan

    2017-04-27

    In a cloud computing environment, the number of virtual machines (VMs) on a single physical server and the number of applications running on each VM are continuously growing. This has led to an enormous increase in the demand of memory capacity and subsequent increase in the energy consumption in the cloud. Lack of enough memory has become a major bottleneck for scalability and performance of virtualization interfaces in cloud computing. To address this problem, memory deduplication techniques which reduce memory demand through page sharing are being adopted. However, such techniques suffer from overheads in terms of number of online comparisons required for the memory deduplication. In this paper, we propose a static memory deduplication (SMD) technique which can reduce memory capacity requirement and provide performance optimization in cloud computing. The main innovation of SMD is that the process of page detection is performed offline, thus potentially reducing the performance cost, especially in terms of response time. In SMD, page comparisons are restricted to the code segment, which has the highest shared content. Our experimental results show that SMD efficiently reduces memory capacity requirement and improves performance. We demonstrate that, compared to other approaches, the cost in terms of the response time is negligible.

  18. Distributed computing system with dual independent communications paths between computers and employing split tokens

    Science.gov (United States)

    Rasmussen, Robert D. (Inventor); Manning, Robert M. (Inventor); Lewis, Blair F. (Inventor); Bolotin, Gary S. (Inventor); Ward, Richard S. (Inventor)

    1990-01-01

    This is a distributed computing system providing flexible fault tolerance; ease of software design and concurrency specification; and dynamic balance of the loads. The system comprises a plurality of computers each having a first input/output interface and a second input/output interface for interfacing to communications networks each second input/output interface including a bypass for bypassing the associated computer. A global communications network interconnects the first input/output interfaces for providing each computer the ability to broadcast messages simultaneously to the remainder of the computers. A meshwork communications network interconnects the second input/output interfaces providing each computer with the ability to establish a communications link with another of the computers bypassing the remainder of computers. Each computer is controlled by a resident copy of a common operating system. Communications between respective ones of computers is by means of split tokens each having a moving first portion which is sent from computer to computer and a resident second portion which is disposed in the memory of at least one of computer and wherein the location of the second portion is part of the first portion. The split tokens represent both functions to be executed by the computers and data to be employed in the execution of the functions. The first input/output interfaces each include logic for detecting a collision between messages and for terminating the broadcasting of a message whereby collisions between messages are detected and avoided.

  19. Impossibility results for distributed computing

    CERN Document Server

    Attiya, Hagit

    2014-01-01

    To understand the power of distributed systems, it is necessary to understand their inherent limitations: what problems cannot be solved in particular systems, or without sufficient resources (such as time or space). This book presents key techniques for proving such impossibility results and applies them to a variety of different problems in a variety of different system models. Insights gained from these results are highlighted, aspects of a problem that make it difficult are isolated, features of an architecture that make it inadequate for solving certain problems efficiently are identified

  20. LHCb: LHCb Distributed Computing Operations

    CERN Multimedia

    Stagni, F

    2011-01-01

    The proliferation of tools for monitoring both activities and infrastructure, together with the pressing need for prompt reaction in case of problems impacting data taking, data reconstruction, data reprocessing and user analysis brought to the need of better organizing the huge amount of information available. The monitoring system for the LHCb Grid Computing relies on many heterogeneous and independent sources of information offering different views for a better understanding of problems while an operations team and defined procedures have been put in place to handle them. This work summarizes the state-of-the-art of LHCb Grid operations emphasizing the reasons that brought to various choices and what are the tools currently in use to run our daily activities. We highlight the most common problems experienced across years of activities on the WLCG infrastructure, the services with their criticality, the procedures in place, the relevant metrics and the tools available and the ones still missing.

  1. Distributed computing by oblivious mobile robots

    CERN Document Server

    Flocchini, Paola; Santoro, Nicola

    2012-01-01

    The study of what can be computed by a team of autonomous mobile robots, originally started in robotics and AI, has become increasingly popular in theoretical computer science (especially in distributed computing), where it is now an integral part of the investigations on computability by mobile entities. The robots are identical computational entities located and able to move in a spatial universe; they operate without explicit communication and are usually unable to remember the past; they are extremely simple, with limited resources, and individually quite weak. However, collectively the ro

  2. 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

  3. CMS distributed computing workflow experience

    Science.gov (United States)

    Adelman-McCarthy, Jennifer; Gutsche, Oliver; Haas, Jeffrey D.; Prosper, Harrison B.; Dutta, Valentina; Gomez-Ceballos, Guillelmo; Hahn, Kristian; Klute, Markus; Mohapatra, Ajit; Spinoso, Vincenzo; Kcira, Dorian; Caudron, Julien; Liao, Junhui; Pin, Arnaud; Schul, Nicolas; De Lentdecker, Gilles; McCartin, Joseph; Vanelderen, Lukas; Janssen, Xavier; Tsyganov, Andrey; Barge, Derek; Lahiff, Andrew

    2011-12-01

    The vast majority of the CMS Computing capacity, which is organized in a tiered hierarchy, is located away from CERN. The 7 Tier-1 sites archive the LHC proton-proton collision data that is initially processed at CERN. These sites provide access to all recorded and simulated data for the Tier-2 sites, via wide-area network (WAN) transfers. All central data processing workflows are executed at the Tier-1 level, which contain re-reconstruction and skimming workflows of collision data as well as reprocessing of simulated data to adapt to changing detector conditions. This paper describes the operation of the CMS processing infrastructure at the Tier-1 level. The Tier-1 workflows are described in detail. The operational optimization of resource usage is described. In particular, the variation of different workflows during the data taking period of 2010, their efficiencies and latencies as well as their impact on the delivery of physics results is discussed and lessons are drawn from this experience. The simulation of proton-proton collisions for the CMS experiment is primarily carried out at the second tier of the CMS computing infrastructure. Half of the Tier-2 sites of CMS are reserved for central Monte Carlo (MC) production while the other half is available for user analysis. This paper summarizes the large throughput of the MC production operation during the data taking period of 2010 and discusses the latencies and efficiencies of the various types of MC production workflows. We present the operational procedures to optimize the usage of available resources and we the operational model of CMS for including opportunistic resources, such as the larger Tier-3 sites, into the central production operation.

  4. CMS distributed computing workflow experience

    International Nuclear Information System (INIS)

    Adelman-McCarthy, Jennifer; Gutsche, Oliver; Haas, Jeffrey D; Prosper, Harrison B; Dutta, Valentina; Gomez-Ceballos, Guillelmo; Hahn, Kristian; Klute, Markus; Mohapatra, Ajit; Spinoso, Vincenzo; Kcira, Dorian; Caudron, Julien; Liao Junhui; Pin, Arnaud; Schul, Nicolas; Lentdecker, Gilles De; McCartin, Joseph; Vanelderen, Lukas; Janssen, Xavier; Tsyganov, Andrey

    2011-01-01

    The vast majority of the CMS Computing capacity, which is organized in a tiered hierarchy, is located away from CERN. The 7 Tier-1 sites archive the LHC proton-proton collision data that is initially processed at CERN. These sites provide access to all recorded and simulated data for the Tier-2 sites, via wide-area network (WAN) transfers. All central data processing workflows are executed at the Tier-1 level, which contain re-reconstruction and skimming workflows of collision data as well as reprocessing of simulated data to adapt to changing detector conditions. This paper describes the operation of the CMS processing infrastructure at the Tier-1 level. The Tier-1 workflows are described in detail. The operational optimization of resource usage is described. In particular, the variation of different workflows during the data taking period of 2010, their efficiencies and latencies as well as their impact on the delivery of physics results is discussed and lessons are drawn from this experience. The simulation of proton-proton collisions for the CMS experiment is primarily carried out at the second tier of the CMS computing infrastructure. Half of the Tier-2 sites of CMS are reserved for central Monte Carlo (MC) production while the other half is available for user analysis. This paper summarizes the large throughput of the MC production operation during the data taking period of 2010 and discusses the latencies and efficiencies of the various types of MC production workflows. We present the operational procedures to optimize the usage of available resources and we the operational model of CMS for including opportunistic resources, such as the larger Tier-3 sites, into the central production operation.

  5. Working Memory and Distributed Vocabulary Learning.

    Science.gov (United States)

    Atkins, Paul W. B.; Baddeley, Alan D.

    1998-01-01

    Tested the hypothesis that individual differences in immediate-verbal-memory span predict success in second-language vocabulary acquisition. In the two-session study, adult subjects learned 56 English-Finnish translations. Tested one week later, subjects were less likely to remember those words they had difficulty learning, even though they had…

  6. 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...

  7. Mobile Agents in Networking and Distributed Computing

    CERN Document Server

    Cao, Jiannong

    2012-01-01

    The book focuses on mobile agents, which are computer programs that can autonomously migrate between network sites. This text introduces the concepts and principles of mobile agents, provides an overview of mobile agent technology, and focuses on applications in networking and distributed computing.

  8. Translation techniques for distributed-shared memory programming models

    Energy Technology Data Exchange (ETDEWEB)

    Fuller, Douglas James [Iowa State Univ., Ames, IA (United States)

    2005-01-01

    The high performance computing community has experienced an explosive improvement in distributed-shared memory hardware. Driven by increasing real-world problem complexity, this explosion has ushered in vast numbers of new systems. Each new system presents new challenges to programmers and application developers. Part of the challenge is adapting to new architectures with new performance characteristics. Different vendors release systems with widely varying architectures that perform differently in different situations. Furthermore, since vendors need only provide a single performance number (total MFLOPS, typically for a single benchmark), they only have strong incentive initially to optimize the API of their choice. Consequently, only a fraction of the available APIs are well optimized on most systems. This causes issues porting and writing maintainable software, let alone issues for programmers burdened with mastering each new API as it is released. Also, programmers wishing to use a certain machine must choose their API based on the underlying hardware instead of the application. This thesis argues that a flexible, extensible translator for distributed-shared memory APIs can help address some of these issues. For example, a translator might take as input code in one API and output an equivalent program in another. Such a translator could provide instant porting for applications to new systems that do not support the application's library or language natively. While open-source APIs are abundant, they do not perform optimally everywhere. A translator would also allow performance testing using a single base code translated to a number of different APIs. Most significantly, this type of translator frees programmers to select the most appropriate API for a given application based on the application (and developer) itself instead of the underlying hardware.

  9. 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.

  10. CMS Distributed Computing Workflow Experience

    CERN Document Server

    Haas, Jeffrey David

    2010-01-01

    The vast majority of the CMS Computing capacity, which is organized in a tiered hierarchy, is located away from CERN. The 7 Tier-1 sites archive the LHC proton-proton collision data that is initially processed at CERN. These sites provide access to all recorded and simulated data for the Tier-2 sites, via wide-area network (WAN) transfers. All central data processing workflows are executed at the Tier-1 level, which contain re-reconstruction and skimming workflows of collision data as well as reprocessing of simulated data to adapt to changing detector conditions. This paper describes the operation of the CMS processing infrastructure at the Tier-1 level. The Tier-1 workflows are described in detail. The operational optimization of resource usage is described. In particular, the variation of different workflows during the data taking period of 2010, their efficiencies and latencies as well as their impact on the delivery of physics results is discussed and lessons are drawn from this experience. The simul...

  11. 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

  12. 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...

  13. 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...

  14. 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.

  15. Memory-assisted measurement-device-independent quantum key distribution

    International Nuclear Information System (INIS)

    Panayi, Christiana; Razavi, Mohsen; Ma, Xiongfeng; Lütkenhaus, Norbert

    2014-01-01

    A protocol with the potential of beating the existing distance records for conventional quantum key distribution (QKD) systems is proposed. It borrows ideas from quantum repeaters by using memories in the middle of the link, and that of measurement-device-independent QKD, which only requires optical source equipment at the user's end. For certain memories with short access times, our scheme allows a higher repetition rate than that of quantum repeaters with single-mode memories, thereby requiring lower coherence times. By accounting for various sources of nonideality, such as memory decoherence, dark counts, misalignment errors, and background noise, as well as timing issues with memories, we develop a mathematical framework within which we can compare QKD systems with and without memories. In particular, we show that with the state-of-the-art technology for quantum memories, it is potentially possible to devise memory-assisted QKD systems that, at certain distances of practical interest, outperform current QKD implementations. (paper)

  16. Associative Memory computing power and its simulation.

    CERN Document Server

    Volpi, G; The ATLAS collaboration

    2014-01-01

    The associative memory (AM) chip is ASIC device specifically designed to perform ``pattern matching'' at very high speed and with parallel access to memory locations. The most extensive use for such device will be the ATLAS Fast Tracker (FTK) processor, where more than 8000 chips will be installed in 128 VME boards, specifically designed for high throughput in order to exploit the chip's features. Each AM chip will store a database of about 130000 pre-calculated patterns, allowing FTK to use about 1 billion patterns for the whole system, with any data inquiry broadcast to all memory elements simultaneously within the same clock cycle (10 ns), thus data retrieval time is independent of the database size. Speed and size of the system are crucial for real-time High Energy Physics applications, such as the ATLAS FTK processor. Using 80 million channels of the ATLAS tracker, FTK finds tracks within 100 $\\mathrm{\\mu s}$. The simulation of such a parallelized system is an extremely complex task when executed in comm...

  17. Recognition of simple visual images using a sparse distributed memory: Some implementations and experiments

    Science.gov (United States)

    Jaeckel, Louis A.

    1990-01-01

    Previously, a method was described of representing a class of simple visual images so that they could be used with a Sparse Distributed Memory (SDM). Herein, two possible implementations are described of a SDM, for which these images, suitably encoded, will serve both as addresses to the memory and as data to be stored in the memory. A key feature of both implementations is that a pattern that is represented as an unordered set with a variable number of members can be used as an address to the memory. In the 1st model, an image is encoded as a 9072 bit string to be used as a read or write address; the bit string may also be used as data to be stored in the memory. Another representation, in which an image is encoded as a 256 bit string, may be used with either model as data to be stored in the memory, but not as an address. In the 2nd model, an image is not represented as a vector of fixed length to be used as an address. Instead, a rule is given for determining which memory locations are to be activated in response to an encoded image. This activation rule treats the pieces of an image as an unordered set. With this model, the memory can be simulated, based on a method of computing the approximate result of a read operation.

  18. 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)

  19. Distributed computing environment for Mine Warfare Command

    OpenAIRE

    Pritchard, Lane L.

    1993-01-01

    Approved for public release; distribution is unlimited. The Mine Warfare Command in Charleston, South Carolina has been converting its information systems architecture from a centralized mainframe based system to a decentralized network of personal computers over the past several years. This thesis analyzes the progress Of the evolution as of May of 1992. The building blocks of a distributed architecture are discussed in relation to the choices the Mine Warfare Command has made to date. Ar...

  20. Parallel discrete ordinates algorithms on distributed and common memory systems

    International Nuclear Information System (INIS)

    Wienke, B.R.; Hiromoto, R.E.; Brickner, R.G.

    1987-01-01

    The S/sub n/ algorithm employs iterative techniques in solving the linear Boltzmann equation. These methods, both ordered and chaotic, were compared on both the Denelcor HEP and the Intel hypercube. Strategies are linked to the organization and accessibility of memory (common memory versus distributed memory architectures), with common concern for acquisition of global information. Apart from this, the inherent parallelism of the algorithm maps directly onto the two architectures. Results comparing execution times, speedup, and efficiency are based on a representative 16-group (full upscatter and downscatter) sample problem. Calculations were performed on both the Los Alamos National Laboratory (LANL) Denelcor HEP and the LANL Intel hypercube. The Denelcor HEP is a 64-bit multi-instruction, multidate MIMD machine consisting of up to 16 process execution modules (PEMs), each capable of executing 64 processes concurrently. Each PEM can cooperate on a job, or run several unrelated jobs, and share a common global memory through a crossbar switch. The Intel hypercube, on the other hand, is a distributed memory system composed of 128 processing elements, each with its own local memory. Processing elements are connected in a nearest-neighbor hypercube configuration and sharing of data among processors requires execution of explicit message-passing constructs

  1. Monte Carlo photon transport on shared memory and distributed memory parallel processors

    International Nuclear Information System (INIS)

    Martin, W.R.; Wan, T.C.; Abdel-Rahman, T.S.; Mudge, T.N.; Miura, K.

    1987-01-01

    Parallelized Monte Carlo algorithms for analyzing photon transport in an inertially confined fusion (ICF) plasma are considered. Algorithms were developed for shared memory (vector and scalar) and distributed memory (scalar) parallel processors. The shared memory algorithm was implemented on the IBM 3090/400, and timing results are presented for dedicated runs with two, three, and four processors. Two alternative distributed memory algorithms (replication and dispatching) were implemented on a hypercube parallel processor (1 through 64 nodes). The replication algorithm yields essentially full efficiency for all cube sizes; with the 64-node configuration, the absolute performance is nearly the same as with the CRAY X-MP. The dispatching algorithm also yields efficiencies above 80% in a large simulation for the 64-processor configuration

  2. 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

  3. 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...

  4. Hybrid computing using a neural network with dynamic external memory.

    Science.gov (United States)

    Graves, Alex; Wayne, Greg; Reynolds, Malcolm; Harley, Tim; Danihelka, Ivo; Grabska-Barwińska, Agnieszka; Colmenarejo, Sergio Gómez; Grefenstette, Edward; Ramalho, Tiago; Agapiou, John; Badia, Adrià Puigdomènech; Hermann, Karl Moritz; Zwols, Yori; Ostrovski, Georg; Cain, Adam; King, Helen; Summerfield, Christopher; Blunsom, Phil; Kavukcuoglu, Koray; Hassabis, Demis

    2016-10-27

    Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

  5. Computing with memory for energy-efficient robust systems

    CERN Document Server

    Paul, Somnath

    2013-01-01

    This book analyzes energy and reliability as major challenges faced by designers of computing frameworks in the nanometer technology regime.  The authors describe the existing solutions to address these challenges and then reveal a new reconfigurable computing platform, which leverages high-density nanoscale memory for both data storage and computation to maximize the energy-efficiency and reliability. The energy and reliability benefits of this new paradigm are illustrated and the design challenges are discussed. Various hardware and software aspects of this exciting computing paradigm are de

  6. Design of multiple sequence alignment algorithms on parallel, distributed memory supercomputers.

    Science.gov (United States)

    Church, Philip C; Goscinski, Andrzej; Holt, Kathryn; Inouye, Michael; Ghoting, Amol; Makarychev, Konstantin; Reumann, Matthias

    2011-01-01

    The challenge of comparing two or more genomes that have undergone recombination and substantial amounts of segmental loss and gain has recently been addressed for small numbers of genomes. However, datasets of hundreds of genomes are now common and their sizes will only increase in the future. Multiple sequence alignment of hundreds of genomes remains an intractable problem due to quadratic increases in compute time and memory footprint. To date, most alignment algorithms are designed for commodity clusters without parallelism. Hence, we propose the design of a multiple sequence alignment algorithm on massively parallel, distributed memory supercomputers to enable research into comparative genomics on large data sets. Following the methodology of the sequential progressiveMauve algorithm, we design data structures including sequences and sorted k-mer lists on the IBM Blue Gene/P supercomputer (BG/P). Preliminary results show that we can reduce the memory footprint so that we can potentially align over 250 bacterial genomes on a single BG/P compute node. We verify our results on a dataset of E.coli, Shigella and S.pneumoniae genomes. Our implementation returns results matching those of the original algorithm but in 1/2 the time and with 1/4 the memory footprint for scaffold building. In this study, we have laid the basis for multiple sequence alignment of large-scale datasets on a massively parallel, distributed memory supercomputer, thus enabling comparison of hundreds instead of a few genome sequences within reasonable time.

  7. 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)

  8. Research computing in a distributed cloud environment

    International Nuclear Information System (INIS)

    Fransham, K; Agarwal, A; Armstrong, P; Bishop, A; Charbonneau, A; Desmarais, R; Hill, N; Gable, I; Gaudet, S; Goliath, S; Impey, R; Leavett-Brown, C; Ouellete, J; Paterson, M; Pritchet, C; Penfold-Brown, D; Podaima, W; Schade, D; Sobie, R J

    2010-01-01

    The recent increase in availability of Infrastructure-as-a-Service (IaaS) computing clouds provides a new way for researchers to run complex scientific applications. However, using cloud resources for a large number of research jobs requires significant effort and expertise. Furthermore, running jobs on many different clouds presents even more difficulty. In order to make it easy for researchers to deploy scientific applications across many cloud resources, we have developed a virtual machine resource manager (Cloud Scheduler) for distributed compute clouds. In response to a user's job submission to a batch system, the Cloud Scheduler manages the distribution and deployment of user-customized virtual machines across multiple clouds. We describe the motivation for and implementation of a distributed cloud using the Cloud Scheduler that is spread across both commercial and dedicated private sites, and present some early results of scientific data analysis using the system.

  9. Multiple-User, Multitasking, Virtual-Memory Computer System

    Science.gov (United States)

    Generazio, Edward R.; Roth, Don J.; Stang, David B.

    1993-01-01

    Computer system designed and programmed to serve multiple users in research laboratory. Provides for computer control and monitoring of laboratory instruments, acquisition and anlaysis of data from those instruments, and interaction with users via remote terminals. System provides fast access to shared central processing units and associated large (from megabytes to gigabytes) memories. Underlying concept of system also applicable to monitoring and control of industrial processes.

  10. PRISMA database machine: A distributed, main-memory approach

    NARCIS (Netherlands)

    Schmidt, J.W.; Apers, Peter M.G.; Ceri, S.; Kersten, Martin L.; Oerlemans, Hans C.M.; Missikoff, M.

    1988-01-01

    The PRISMA project is a large-scale research effort in the design and implementation of a highly parallel machine for data and knowledge processing. The PRISMA database machine is a distributed, main-memory database management system implemented in an object-oriented language that runs on top of a

  11. Dynamic overset grid communication on distributed memory parallel processors

    Science.gov (United States)

    Barszcz, Eric; Weeratunga, Sisira K.; Meakin, Robert L.

    1993-01-01

    A parallel distributed memory implementation of intergrid communication for dynamic overset grids is presented. Included are discussions of various options considered during development. Results are presented comparing an Intel iPSC/860 to a single processor Cray Y-MP. Results for grids in relative motion show the iPSC/860 implementation to be faster than the Cray implementation.

  12. Graphical Visualization on Computational Simulation Using Shared Memory

    International Nuclear Information System (INIS)

    Lima, A B; Correa, Eberth

    2014-01-01

    The Shared Memory technique is a powerful tool for parallelizing computer codes. In particular it can be used to visualize the results ''on the fly'' without stop running the simulation. In this presentation we discuss and show how to use the technique conjugated with a visualization code using openGL

  13. Persistent Memory in Single Node Delay-Coupled Reservoir Computing.

    Directory of Open Access Journals (Sweden)

    André David Kovac

    Full Text Available Delays are ubiquitous in biological systems, ranging from genetic regulatory networks and synaptic conductances, to predator/pray population interactions. The evidence is mounting, not only to the presence of delays as physical constraints in signal propagation speed, but also to their functional role in providing dynamical diversity to the systems that comprise them. The latter observation in biological systems inspired the recent development of a computational architecture that harnesses this dynamical diversity, by delay-coupling a single nonlinear element to itself. This architecture is a particular realization of Reservoir Computing, where stimuli are injected into the system in time rather than in space as is the case with classical recurrent neural network realizations. This architecture also exhibits an internal memory which fades in time, an important prerequisite to the functioning of any reservoir computing device. However, fading memory is also a limitation to any computation that requires persistent storage. In order to overcome this limitation, the current work introduces an extended version to the single node Delay-Coupled Reservoir, that is based on trained linear feedback. We show by numerical simulations that adding task-specific linear feedback to the single node Delay-Coupled Reservoir extends the class of solvable tasks to those that require nonfading memory. We demonstrate, through several case studies, the ability of the extended system to carry out complex nonlinear computations that depend on past information, whereas the computational power of the system with fading memory alone quickly deteriorates. Our findings provide the theoretical basis for future physical realizations of a biologically-inspired ultrafast computing device with extended functionality.

  14. Persistent Memory in Single Node Delay-Coupled Reservoir Computing.

    Science.gov (United States)

    Kovac, André David; Koall, Maximilian; Pipa, Gordon; Toutounji, Hazem

    2016-01-01

    Delays are ubiquitous in biological systems, ranging from genetic regulatory networks and synaptic conductances, to predator/pray population interactions. The evidence is mounting, not only to the presence of delays as physical constraints in signal propagation speed, but also to their functional role in providing dynamical diversity to the systems that comprise them. The latter observation in biological systems inspired the recent development of a computational architecture that harnesses this dynamical diversity, by delay-coupling a single nonlinear element to itself. This architecture is a particular realization of Reservoir Computing, where stimuli are injected into the system in time rather than in space as is the case with classical recurrent neural network realizations. This architecture also exhibits an internal memory which fades in time, an important prerequisite to the functioning of any reservoir computing device. However, fading memory is also a limitation to any computation that requires persistent storage. In order to overcome this limitation, the current work introduces an extended version to the single node Delay-Coupled Reservoir, that is based on trained linear feedback. We show by numerical simulations that adding task-specific linear feedback to the single node Delay-Coupled Reservoir extends the class of solvable tasks to those that require nonfading memory. We demonstrate, through several case studies, the ability of the extended system to carry out complex nonlinear computations that depend on past information, whereas the computational power of the system with fading memory alone quickly deteriorates. Our findings provide the theoretical basis for future physical realizations of a biologically-inspired ultrafast computing device with extended functionality.

  15. 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.

  16. Sparse Distributed Memory: understanding the speed and robustness of expert memory

    Directory of Open Access Journals (Sweden)

    Marcelo Salhab Brogliato

    2014-04-01

    Full Text Available How can experts, sometimes in exacting detail, almost immediately and very precisely recall memory items from a vast repertoire? The problem in which we will be interested concerns models of theoretical neuroscience that could explain the speed and robustness of an expert's recollection. The approach is based on Sparse Distributed Memory, which has been shown to be plausible, both in a neuroscientific and in a psychological manner, in a number of ways. A crucial characteristic concerns the limits of human recollection, the `tip-of-tongue' memory event--which is found at a non-linearity in the model. We expand the theoretical framework, deriving an optimization formula to solve to this non-linearity. Numerical results demonstrate how the higher frequency of rehearsal, through work or study, immediately increases the robustness and speed associated with expert memory.

  17. Operation of the ATLAS distributed computing

    CERN Document Server

    Barreiro Megino, Fernando Harald; The ATLAS collaboration

    2018-01-01

    We describe the central operation of the ATLAS distributed computing system. The majority of compute intensive activities within ATLAS are carried out on some 350,000 CPU cores on the Grid, augmented by opportunistic usage of significant HPC and volunteer resources. The increasing scale, and challenging new payloads, demand fine-tuning of operational procedures together with timely developments of the production system. We describe several such developments, motivated directly from operational experience. Optimization of inefficient task requests, from both official production and users, is made possible by automatic detection of payload properties. User education, job shaping or preventative throttling help to increase the overall throughput of the available resources.

  18. A Screen Space GPGPU Surface LIC Algorithm for Distributed Memory Data Parallel Sort Last Rendering Infrastructures

    Energy Technology Data Exchange (ETDEWEB)

    Loring, Burlen; Karimabadi, Homa; Rortershteyn, Vadim

    2014-07-01

    The surface line integral convolution(LIC) visualization technique produces dense visualization of vector fields on arbitrary surfaces. We present a screen space surface LIC algorithm for use in distributed memory data parallel sort last rendering infrastructures. The motivations for our work are to support analysis of datasets that are too large to fit in the main memory of a single computer and compatibility with prevalent parallel scientific visualization tools such as ParaView and VisIt. By working in screen space using OpenGL we can leverage the computational power of GPUs when they are available and run without them when they are not. We address efficiency and performance issues that arise from the transformation of data from physical to screen space by selecting an alternate screen space domain decomposition. We analyze the algorithm's scaling behavior with and without GPUs on two high performance computing systems using data from turbulent plasma simulations.

  19. Optical computing, optical memory, and SBIRs at Foster-Miller

    Science.gov (United States)

    Domash, Lawrence H.

    1994-03-01

    A desktop design and manufacturing system for binary diffractive elements, MacBEEP, was developed with the optical researcher in mind. Optical processing systems for specialized tasks such as cellular automation computation and fractal measurement were constructed. A new family of switchable holograms has enabled several applications for control of laser beams in optical memories. New spatial light modulators and optical logic elements have been demonstrated based on a more manufacturable semiconductor technology. Novel synthetic and polymeric nonlinear materials for optical storage are under development in an integrated memory architecture. SBIR programs enable creative contributions from smaller companies, both product oriented and technology oriented, and support advances that might not otherwise be developed.

  20. 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.

  1. Decentralized Resource Management in Distributed Computer Systems.

    Science.gov (United States)

    1982-02-01

    directly exchanging user state information. Eventcounts and sequencers correspond to semaphores in the sense that synchronization primitives are used to...and techniques are required to achieve synchronization in distributed computers without reliance on any centralized entity such as a semaphore ...known solutions to the access synchronization problem was Dijkstra’s semaphore [12]. The importance of the semaphore is that it correctly addresses the

  2. ATLAS Distributed Computing: Its Central Services core

    CERN Document Server

    Lee, Christopher Jon; The ATLAS collaboration

    2018-01-01

    The ATLAS Distributed Computing (ADC) Project is responsible for the off-line processing of data produced by the ATLAS experiment at the Large Hadron Collider (LHC) at CERN. It facilitates data and workload management for ATLAS computing on the Worldwide LHC Computing Grid (WLCG). ADC Central Services operations (CSops)is a vital part of ADC, responsible for the deployment and configuration of services needed by ATLAS computing and operation of those services on CERN IT infrastructure, providing knowledge of CERN IT services to ATLAS service managers and developers, and supporting them in case of issues. Currently this entails the management of thirty seven different OpenStack projects, with more than five thousand cores allocated for these virtual machines, as well as overseeing the distribution of twenty nine petabytes of storage space in EOS for ATLAS. As the LHC begins to get ready for the next long shut-down, which will bring in many new upgrades to allow for more data to be captured by the on-line syste...

  3. Data analytics in the ATLAS Distributed Computing

    CERN Document Server

    Vukotic, Ilija; The ATLAS collaboration; Bryant, Lincoln

    2015-01-01

    The ATLAS Data analytics effort is focused on creating systems which provide the ATLAS ADC with new capabilities for understanding distributed systems and overall operational performance. These capabilities include: warehousing information from multiple systems (the production and distributed analysis system - PanDA, the distributed data management system - Rucio, the file transfer system, various monitoring services etc. ); providing a platform to execute arbitrary data mining and machine learning algorithms over aggregated data; satisfy a variety of use cases for different user roles; host new third party analytics services on a scalable compute platform. We describe the implemented system where: data sources are existing RDBMS (Oracle) and Flume collectors; a Hadoop cluster is used to store the data; native Hadoop and Apache Pig scripts are used for data aggregation; and R for in-depth analytics. Part of the data is indexed in ElasticSearch so both simpler investigations and complex dashboards can be made ...

  4. Distributed-Memory Breadth-First Search on Massive Graphs

    Energy Technology Data Exchange (ETDEWEB)

    Buluc, Aydin [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Computational Research Division; Beamer, Scott [Univ. of California, Berkeley, CA (United States). Dept. of Electrical Engineering and Computer Sciences; Madduri, Kamesh [Pennsylvania State Univ., University Park, PA (United States). Computer Science & Engineering Dept.; Asanovic, Krste [Univ. of California, Berkeley, CA (United States). Dept. of Electrical Engineering and Computer Sciences; Patterson, David [Univ. of California, Berkeley, CA (United States). Dept. of Electrical Engineering and Computer Sciences

    2017-09-26

    This chapter studies the problem of traversing large graphs using the breadth-first search order on distributed-memory supercomputers. We consider both the traditional level-synchronous top-down algorithm as well as the recently discovered direction optimizing algorithm. We analyze the performance and scalability trade-offs in using different local data structures such as CSR and DCSC, enabling in-node multithreading, and graph decompositions such as 1D and 2D decomposition.

  5. A portable implementation of ARPACK for distributed memory parallel architectures

    Energy Technology Data Exchange (ETDEWEB)

    Maschhoff, K.J.; Sorensen, D.C.

    1996-12-31

    ARPACK is a package of Fortran 77 subroutines which implement the Implicitly Restarted Arnoldi Method used for solving large sparse eigenvalue problems. A parallel implementation of ARPACK is presented which is portable across a wide range of distributed memory platforms and requires minimal changes to the serial code. The communication layers used for message passing are the Basic Linear Algebra Communication Subprograms (BLACS) developed for the ScaLAPACK project and Message Passing Interface(MPI).

  6. 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)

  7. 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.

  8. Distributed computer control system for reactor optimization

    International Nuclear Information System (INIS)

    Williams, A.H.

    1983-01-01

    At the Oldbury power station a prototype distributed computer control system has been installed. This system is designed to support research and development into improved reactor temperature control methods. This work will lead to the development and demonstration of new optimal control systems for improvement of plant efficiency and increase of generated output. The system can collect plant data from special test instrumentation connected to dedicated scanners and from the station's existing data processing system. The system can also, via distributed microprocessor-based interface units, make adjustments to the desired reactor channel gas exit temperatures. The existing control equipment will then adjust the height of control rods to maintain operation at these temperatures. The design of the distributed system is based on extensive experience with distributed systems for direct digital control, operator display and plant monitoring. The paper describes various aspects of this system, with particular emphasis on: (1) the hierarchal system structure; (2) the modular construction of the system to facilitate installation, commissioning and testing, and to reduce maintenance to module replacement; (3) the integration of the system into the station's existing data processing system; (4) distributed microprocessor-based interfaces to the reactor controls, with extensive security facilities implemented by hardware and software; (5) data transfer using point-to-point and bussed data links; (6) man-machine communication based on VDUs with computer input push-buttons and touch-sensitive screens; and (7) the use of a software system supporting a high-level engineer-orientated programming language, at all levels in the system, together with comprehensive data link management

  9. emMAW: computing minimal absent words in external memory.

    Science.gov (United States)

    Héliou, Alice; Pissis, Solon P; Puglisi, Simon J

    2017-09-01

    The biological significance of minimal absent words has been investigated in genomes of organisms from all domains of life. For instance, three minimal absent words of the human genome were found in Ebola virus genomes. There exists an O(n) -time and O(n) -space algorithm for computing all minimal absent words of a sequence of length n on a fixed-sized alphabet based on suffix arrays. A standard implementation of this algorithm, when applied to a large sequence of length n , requires more than 20 n  bytes of RAM. Such memory requirements are a significant hurdle to the computation of minimal absent words in large datasets. We present emMAW, the first external-memory algorithm for computing minimal absent words. A free open-source implementation of our algorithm is made available. This allows for computation of minimal absent words on far bigger data sets than was previously possible. Our implementation requires less than 3 h on a standard workstation to process the full human genome when as little as 1 GB of RAM is made available. We stress that our implementation, despite making use of external memory, is fast; indeed, even on relatively smaller datasets when enough RAM is available to hold all necessary data structures, it is less than two times slower than state-of-the-art internal-memory implementations. https://github.com/solonas13/maw (free software under the terms of the GNU GPL). alice.heliou@lix.polytechnique.fr or solon.pissis@kcl.ac.uk. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

  10. Injecting Artificial Memory Errors Into a Running Computer Program

    Science.gov (United States)

    Bornstein, Benjamin J.; Granat, Robert A.; Wagstaff, Kiri L.

    2008-01-01

    Single-event upsets (SEUs) or bitflips are computer memory errors caused by radiation. BITFLIPS (Basic Instrumentation Tool for Fault Localized Injection of Probabilistic SEUs) is a computer program that deliberately injects SEUs into another computer program, while the latter is running, for the purpose of evaluating the fault tolerance of that program. BITFLIPS was written as a plug-in extension of the open-source Valgrind debugging and profiling software. BITFLIPS can inject SEUs into any program that can be run on the Linux operating system, without needing to modify the program s source code. Further, if access to the original program source code is available, BITFLIPS offers fine-grained control over exactly when and which areas of memory (as specified via program variables) will be subjected to SEUs. The rate of injection of SEUs is controlled by specifying either a fault probability or a fault rate based on memory size and radiation exposure time, in units of SEUs per byte per second. BITFLIPS can also log each SEU that it injects and, if program source code is available, report the magnitude of effect of the SEU on a floating-point value or other program variable.

  11. Pseudo-interactive monitoring in distributed computing

    International Nuclear Information System (INIS)

    Sfiligoi, I.; Bradley, D.; Livny, M.

    2009-01-01

    Distributed computing, and in particular Grid computing, enables physicists to use thousands of CPU days worth of computing every day, by submitting thousands of compute jobs. Unfortunately, a small fraction of such jobs regularly fail; the reasons vary from disk and network problems to bugs in the user code. A subset of these failures result in jobs being stuck for long periods of time. In order to debug such failures, interactive monitoring is highly desirable; users need to browse through the job log files and check the status of the running processes. Batch systems typically don't provide such services; at best, users get job logs at job termination, and even this may not be possible if the job is stuck in an infinite loop. In this paper we present a novel approach of using regular batch system capabilities of Condor to enable users to access the logs and processes of any running job. This does not provide true interactive access, so commands like vi are not viable, but it does allow operations like ls, cat, top, ps, lsof, netstat and dumping the stack of any process owned by the user; we call this pseudo-interactive monitoring. It is worth noting that the same method can be used to monitor Grid jobs in a glidein-based environment. We further believe that the same mechanism could be applied to many other batch systems.

  12. Pseudo-interactive monitoring in distributed computing

    International Nuclear Information System (INIS)

    Sfiligoi, I; Bradley, D; Livny, M

    2010-01-01

    Distributed computing, and in particular Grid computing, enables physicists to use thousands of CPU days worth of computing every day, by submitting thousands of compute jobs. Unfortunately, a small fraction of such jobs regularly fail; the reasons vary from disk and network problems to bugs in the user code. A subset of these failures result in jobs being stuck for long periods of time. In order to debug such failures, interactive monitoring is highly desirable; users need to browse through the job log files and check the status of the running processes. Batch systems typically don't provide such services; at best, users get job logs at job termination, and even this may not be possible if the job is stuck in an infinite loop. In this paper we present a novel approach of using regular batch system capabilities of Condor to enable users to access the logs and processes of any running job. This does not provide true interactive access, so commands like vi are not viable, but it does allow operations like ls, cat, top, ps, lsof, netstat and dumping the stack of any process owned by the user; we call this pseudo-interactive monitoring. It is worth noting that the same method can be used to monitor Grid jobs in a glidein-based environment. We further believe that the same mechanism could be applied to many other batch systems.

  13. Pseudo-interactive monitoring in distributed computing

    Energy Technology Data Exchange (ETDEWEB)

    Sfiligoi, I.; /Fermilab; Bradley, D.; Livny, M.; /Wisconsin U., Madison

    2009-05-01

    Distributed computing, and in particular Grid computing, enables physicists to use thousands of CPU days worth of computing every day, by submitting thousands of compute jobs. Unfortunately, a small fraction of such jobs regularly fail; the reasons vary from disk and network problems to bugs in the user code. A subset of these failures result in jobs being stuck for long periods of time. In order to debug such failures, interactive monitoring is highly desirable; users need to browse through the job log files and check the status of the running processes. Batch systems typically don't provide such services; at best, users get job logs at job termination, and even this may not be possible if the job is stuck in an infinite loop. In this paper we present a novel approach of using regular batch system capabilities of Condor to enable users to access the logs and processes of any running job. This does not provide true interactive access, so commands like vi are not viable, but it does allow operations like ls, cat, top, ps, lsof, netstat and dumping the stack of any process owned by the user; we call this pseudo-interactive monitoring. It is worth noting that the same method can be used to monitor Grid jobs in a glidein-based environment. We further believe that the same mechanism could be applied to many other batch systems.

  14. Contention Modeling for Multithreaded Distributed Shared Memory Machines: The Cray XMT

    Energy Technology Data Exchange (ETDEWEB)

    Secchi, Simone; Tumeo, Antonino; Villa, Oreste

    2011-07-27

    Distributed Shared Memory (DSM) machines are a wide class of multi-processor computing systems where a large virtually-shared address space is mapped on a network of physically distributed memories. High memory latency and network contention are two of the main factors that limit performance scaling of such architectures. Modern high-performance computing DSM systems have evolved toward exploitation of massive hardware multi-threading and fine-grained memory hashing to tolerate irregular latencies, avoid network hot-spots and enable high scaling. In order to model the performance of such large-scale machines, parallel simulation has been proved to be a promising approach to achieve good accuracy in reasonable times. One of the most critical factors in solving the simulation speed-accuracy trade-off is network modeling. The Cray XMT is a massively multi-threaded supercomputing architecture that belongs to the DSM class, since it implements a globally-shared address space abstraction on top of a physically distributed memory substrate. In this paper, we discuss the development of a contention-aware network model intended to be integrated in a full-system XMT simulator. We start by measuring the effects of network contention in a 128-processor XMT machine and then investigate the trade-off that exists between simulation accuracy and speed, by comparing three network models which operate at different levels of accuracy. The comparison and model validation is performed by executing a string-matching algorithm on the full-system simulator and on the XMT, using three datasets that generate noticeably different contention patterns.

  15. A new communication scheme for the neutron diffusion nodal method in a distributed computing environment

    International Nuclear Information System (INIS)

    Kirk, B.L.; Azmy, Y.

    1994-01-01

    A modified scheme is developed for solving the two-dimensional nodal diffusion equations on distributed memory computers. The scheme is aimed at minimizing the volume of communication among processors while maximizing the tasks in parallel. Results show a significant improvement in parallel efficiency on the Intel iPSC/860 hypercube compared to previous algorithms

  16. Higher order correlations in computed particle distributions

    International Nuclear Information System (INIS)

    Hanerfeld, H.; Herrmannsfeldt, W.; Miller, R.H.

    1989-03-01

    The rms emittances calculated for beam distributions using computer simulations are frequently dominated by higher order aberrations. Thus there are substantial open areas in the phase space plots. It has long been observed that the rms emittance is not an invariant to beam manipulations. The usual emittance calculation removes the correlation between transverse displacement and transverse momentum. In this paper, we explore the possibility of defining higher order correlations that can be removed from the distribution to result in a lower limit to the realizable emittance. The intent is that by inserting the correct combinations of linear lenses at the proper position, the beam may recombine in a way that cancels the effects of some higher order forces. An example might be the non-linear transverse space charge forces which cause a beam to spread. If the beam is then refocused so that the same non-linear forces reverse the inward velocities, the resulting phase space distribution may reasonably approximate the original distribution. The approach to finding the location and strength of the proper lens to optimize the transported beam is based on work by Bruce Carlsten of Los Alamos National Laboratory. 11 refs., 4 figs

  17. [Distribution of neural memory, loading factor, its regulation and optimization].

    Science.gov (United States)

    Radchenko, A N

    1999-01-01

    Recording and retrieving functions of the neural memory are simulated as a control of local conformational processes in neural synaptic fields. The localization of conformational changes is related to the afferent temporal-spatial pulse pattern flow, the microstructure of connections and a plurality of temporal delays in synaptic fields and afferent pathways. The loci of conformations are described by sets of afferent addresses named address domains. Being superimposed on each other, address domains form a multilayer covering of the address space of the neuron or the ensemble. The superposition factor determines the dissemination of the conformational process, and the fuzzing of memory, and its accuracy and reliability. The engram is formed as detects in the packing of the address space and hence can be retrieved in inverse form. The accuracy of the retrieved information depends on the threshold level of conformational transitions, the distribution of conformational changes in synaptic fields of the neuronal population, and the memory loading factor. The latter is represented in the model by a slow potential. It reflects total conformational changes and displaces the membrane potential to monostable conformational regimes, by governing the exit from the recording regime, the potentiation of the neurone, and the readiness to reproduction. A relative amplitude of the slow potential and the coefficient of postconformational modification of ionic conductivity, which provides maximum reliability, accuracy, and capacity of memory, are calculated.

  18. Distributed memory in a heterogeneous network, as used in the CERN-PS complex timing system

    CERN Document Server

    Kovaltsov, V I

    1995-01-01

    The Distributed Table Manager (DTM) is a fast and efficient utility for distributing named binary data structures called Tables, of arbitrary size and structure, around a heterogeneous network of computers to a set of registered clients. The Tables are transmitted over a UDP network between DTM servers in network format, where the servers perform the conversions to and from host format for local clients. The servers provide clients with synchronization mechanisms, a choice of network data flows, and table options such as keeping table disc copies, shared memory or heap memory table allocation, table read/write permissions, and table subnet broadcasting. DTM has been designed to be easily maintainable, and to automatically recover from the type of errors typically encountered in a large control system network. The DTM system is based on a three level server daemon hierarchy, in which an inter daemon protocol handles network failures, and incorporates recovery procedures which will guarantee table consistency w...

  19. Computing shifts to monitor ATLAS distributed computing infrastructure and operations

    CERN Document Server

    AUTHOR|(INSPIRE)INSPIRE-00068610; The ATLAS collaboration; Barberis, Dario; Crepe-Renaudin, Sabine Chrystel; De, Kaushik; Fassi, Farida; Stradling, Alden; Svatos, Michal; Vartapetian, Armen; Wolters, Helmut

    2017-01-01

    The ATLAS Distributed Computing (ADC) group established a new Computing Run Coordinator (CRC) shift at the start of LHC Run 2 in 2015. The main goal was to rely on a person with a good overview of the ADC activities to ease the ADC experts’ workload. The CRC shifter keeps track of ADC tasks related to their fields of expertise and responsibility. At the same time, the shifter maintains a global view of the day-to-day operations of the ADC system. During Run 1, this task was accomplished by a person of the expert team called the ADC Manager on Duty (AMOD), a position that was removed during the shutdown period due to the reduced number and availability of ADC experts foreseen for Run 2. The CRC position was proposed to cover some of the AMODs former functions, while allowing more people involved in computing to participate. In this way, CRC shifters help with the training of future ADC experts. The CRC shifters coordinate daily ADC shift operations, including tracking open issues, reporting, and representing...

  20. Computing shifts to monitor ATLAS distributed computing infrastructure and operations

    CERN Document Server

    Adam Bourdarios, Claire; The ATLAS collaboration

    2016-01-01

    The ATLAS Distributed Computing (ADC) group established a new Computing Run Coordinator (CRC) shift at the start of LHC Run2 in 2015. The main goal was to rely on a person with a good overview of the ADC activities to ease the ADC experts' workload. The CRC shifter keeps track of ADC tasks related to their fields of expertise and responsibility. At the same time, the shifter maintains a global view of the day-to-day operations of the ADC system. During Run1, this task was accomplished by the ADC Manager on Duty (AMOD), a position that was removed during the shutdown period due to the reduced number and availability of ADC experts foreseen for Run2. The CRC position was proposed to cover some of the AMOD’s former functions, while allowing more people involved in computing to participate. In this way, CRC shifters help train future ADC experts. The CRC shifters coordinate daily ADC shift operations, including tracking open issues, reporting, and representing ADC in relevant meetings. The CRC also facilitates ...

  1. Techniques for Reducing Consistency-Related Communication in Distributed Shared Memory System

    OpenAIRE

    Zwaenepoel, W; Bennett, J.K.; Carter, J.B.

    1995-01-01

    Distributed shared memory 8DSM) is an abstraction of shared memory on a distributed memory machine. Hardware DSM systems support this abstraction at the architecture level; software DSM systems support the abstraction within the runtime system. One of the key problems in building an efficient software DSM system is to reduce the amount of communication needed to keep the distributed memories consistent. In this paper we present four techniques for doing so: 1) software release consistency; 2)...

  2. A multipurpose computing center with distributed resources

    Science.gov (United States)

    Chudoba, J.; Adam, M.; Adamová, D.; Kouba, T.; Mikula, A.; Říkal, V.; Švec, J.; Uhlířová, J.; Vokáč, P.; Svatoš, M.

    2017-10-01

    The Computing Center of the Institute of Physics (CC IoP) of the Czech Academy of Sciences serves a broad spectrum of users with various computing needs. It runs WLCG Tier-2 center for the ALICE and the ATLAS experiments; the same group of services is used by astroparticle physics projects the Pierre Auger Observatory (PAO) and the Cherenkov Telescope Array (CTA). OSG stack is installed for the NOvA experiment. Other groups of users use directly local batch system. Storage capacity is distributed to several locations. DPM servers used by the ATLAS and the PAO are all in the same server room, but several xrootd servers for the ALICE experiment are operated in the Nuclear Physics Institute in Řež, about 10 km away. The storage capacity for the ATLAS and the PAO is extended by resources of the CESNET - the Czech National Grid Initiative representative. Those resources are in Plzen and Jihlava, more than 100 km away from the CC IoP. Both distant sites use a hierarchical storage solution based on disks and tapes. They installed one common dCache instance, which is published in the CC IoP BDII. ATLAS users can use these resources using the standard ATLAS tools in the same way as the local storage without noticing this geographical distribution. Computing clusters LUNA and EXMAG dedicated to users mostly from the Solid State Physics departments offer resources for parallel computing. They are part of the Czech NGI infrastructure MetaCentrum with distributed batch system based on torque with a custom scheduler. Clusters are installed remotely by the MetaCentrum team and a local contact helps only when needed. Users from IoP have exclusive access only to a part of these two clusters and take advantage of higher priorities on the rest (1500 cores in total), which can also be used by any user of the MetaCentrum. IoP researchers can also use distant resources located in several towns of the Czech Republic with a capacity of more than 12000 cores in total.

  3. Reprogrammable logic in memristive crossbar for in-memory computing

    Science.gov (United States)

    Cheng, Long; Zhang, Mei-Yun; Li, Yi; Zhou, Ya-Xiong; Wang, Zhuo-Rui; Hu, Si-Yu; Long, Shi-Bing; Liu, Ming; Miao, Xiang-Shui

    2017-12-01

    Memristive stateful logic has emerged as a promising next-generation in-memory computing paradigm to address escalating computing-performance pressures in traditional von Neumann architecture. Here, we present a nonvolatile reprogrammable logic method that can process data between different rows and columns in a memristive crossbar array based on material implication (IMP) logic. Arbitrary Boolean logic can be executed with a reprogrammable cell containing four memristors in a crossbar array. In the fabricated Ti/HfO2/W memristive array, some fundamental functions, such as universal NAND logic and data transfer, were experimentally implemented. Moreover, using eight memristors in a 2  ×  4 array, a one-bit full adder was theoretically designed and verified by simulation to exhibit the feasibility of our method to accomplish complex computing tasks. In addition, some critical logic-related performances were further discussed, such as the flexibility of data processing, cascading problem and bit error rate. Such a method could be a step forward in developing IMP-based memristive nonvolatile logic for large-scale in-memory computing architecture.

  4. Real time computer system with distributed microprocessors

    International Nuclear Information System (INIS)

    Heger, D.; Steusloff, H.; Syrbe, M.

    1979-01-01

    The usual centralized structure of computer systems, especially of process computer systems, cannot sufficiently use the progress of very large-scale integrated semiconductor technology with respect to increasing the reliability and performance and to decreasing the expenses especially of the external periphery. This and the increasing demands on process control systems has led the authors to generally examine the structure of such systems and to adapt it to the new surroundings. Computer systems with distributed, optical fibre-coupled microprocessors allow a very favourable problem-solving with decentralized controlled buslines and functional redundancy with automatic fault diagnosis and reconfiguration. A fit programming system supports these hardware properties: PEARL for multicomputer systems, dynamic loader, processor and network operating system. The necessary design principles for this are proved mainly theoretically and by value analysis. An optimal overall system of this new generation of process control systems was established, supported by results of 2 PDV projects (modular operating systems, input/output colour screen system as control panel), for the purpose of testing by apllying the system for the control of 28 pit furnaces of a steel work. (orig.) [de

  5. Parallel SN algorithms in shared- and distributed-memory environments

    International Nuclear Information System (INIS)

    Haghighat, Alireza; Hunter, Melissa A.; Mattis, Ronald E.

    1995-01-01

    Different 2-D spatial domain partitioning Sn transport theory algorithms have been developed on the basis of the Block-Jacobi iterative scheme. These algorithms have been incorporated into TWOTRAN-II, and tested on a shared-memory CRAY Y-MP C90 and a distributed-memory IBM SP1. For a series of fixed source r-z geometry homogeneous problems, parallel efficiencies in a range of 50-90% are achieved on the C90 with 6 processors, and lower values (20-60%) are obtained on the SP1. It is demonstrated that better performance is attainable if one addresses issues such as convergence rate, load-balancing, and granularity for both architectures, as well as message passing (network bandwidth and latency) for SP1. (author). 17 refs, 4 figs

  6. Towards Modeling False Memory With Computational Knowledge Bases.

    Science.gov (United States)

    Li, Justin; Kohanyi, Emma

    2017-01-01

    One challenge to creating realistic cognitive models of memory is the inability to account for the vast common-sense knowledge of human participants. Large computational knowledge bases such as WordNet and DBpedia may offer a solution to this problem but may pose other challenges. This paper explores some of these difficulties through a semantic network spreading activation model of the Deese-Roediger-McDermott false memory task. In three experiments, we show that these knowledge bases only capture a subset of human associations, while irrelevant information introduces noise and makes efficient modeling difficult. We conclude that the contents of these knowledge bases must be augmented and, more important, that the algorithms must be refined and optimized, before large knowledge bases can be widely used for cognitive modeling. Copyright © 2016 Cognitive Science Society, Inc.

  7. Translation Memory and Computer Assisted Translation Tool for Medieval Texts

    Directory of Open Access Journals (Sweden)

    Törcsvári Attila

    2013-05-01

    Full Text Available Translation memories (TMs, as part of Computer Assisted Translation (CAT tools, support translators reusing portions of formerly translated text. Fencing books are good candidates for using TMs due to the high number of repeated terms. Medieval texts suffer a number of drawbacks that make hard even “simple” rewording to the modern version of the same language. The analyzed difficulties are: lack of systematic spelling, unusual word orders and typos in the original. A hypothesis is made and verified that even simple modernization increases legibility and it is feasible, also it is worthwhile to apply translation memories due to the numerous and even extremely long repeated terms. Therefore, methods and algorithms are presented 1. for automated transcription of medieval texts (when a limited training set is available, and 2. collection of repeated patterns. The efficiency of the algorithms is analyzed for recall and precision.

  8. An Alternative Algorithm for Computing Watersheds on Shared Memory Parallel Computers

    NARCIS (Netherlands)

    Meijster, A.; Roerdink, J.B.T.M.

    1995-01-01

    In this paper a parallel implementation of a watershed algorithm is proposed. The algorithm can easily be implemented on shared memory parallel computers. The watershed transform is generally considered to be inherently sequential since the discrete watershed of an image is defined using recursion.

  9. 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.

  10. A memory-array architecture for computer vision

    Energy Technology Data Exchange (ETDEWEB)

    Balsara, P.T.

    1989-01-01

    With the fast advances in the area of computer vision and robotics there is a growing need for machines that can understand images at a very high speed. A conventional von Neumann computer is not suited for this purpose because it takes a tremendous amount of time to solve most typical image processing problems. Exploiting the inherent parallelism present in various vision tasks can significantly reduce the processing time. Fortunately, parallelism is increasingly affordable as hardware gets cheaper. Thus it is now imperative to study computer vision in a parallel processing framework. The author should first design a computational structure which is well suited for a wide range of vision tasks and then develop parallel algorithms which can run efficiently on this structure. Recent advances in VLSI technology have led to several proposals for parallel architectures for computer vision. In this thesis he demonstrates that a memory array architecture with efficient local and global communication capabilities can be used for high speed execution of a wide range of computer vision tasks. This architecture, called the Access Constrained Memory Array Architecture (ACMAA), is efficient for VLSI implementation because of its modular structure, simple interconnect and limited global control. Several parallel vision algorithms have been designed for this architecture. The choice of vision problems demonstrates the versatility of ACMAA for a wide range of vision tasks. These algorithms were simulated on a high level ACMAA simulator running on the Intel iPSC/2 hypercube, a parallel architecture. The results of this simulation are compared with those of sequential algorithms running on a single hypercube node. Details of the ACMAA processor architecture are also presented.

  11. 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)

  12. Xcache in the ATLAS Distributed Computing Environment

    CERN Document Server

    Hanushevsky, Andrew; The ATLAS collaboration

    2018-01-01

    Built upon the Xrootd Proxy Cache (Xcache), we developed additional features to adapt the ATLAS distributed computing and data environment, especially its data management system RUCIO, to help improve the cache hit rate, as well as features that make the Xcache easy to use, similar to the way the Squid cache is used by the HTTP protocol. We are optimizing Xcache for the HPC environments, and adapting the HL-LHC Data Lakes design as its component for data delivery. We packaged the software in CVMFS, in Docker and Singularity containers in order to standardize the deployment and reduce the cost to resolve issues at remote sites. We are also integrating it into RUCIO as a volatile storage systems, and into various ATLAS workflow such as user analysis,

  13. 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

  14. 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.

  15. 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.)

  16. Periodic bidirectional associative memory neural networks with distributed delays

    Science.gov (United States)

    Chen, Anping; Huang, Lihong; Liu, Zhigang; Cao, Jinde

    2006-05-01

    Some sufficient conditions are obtained for the existence and global exponential stability of a periodic solution to the general bidirectional associative memory (BAM) neural networks with distributed delays by using the continuation theorem of Mawhin's coincidence degree theory and the Lyapunov functional method and the Young's inequality technique. These results are helpful for designing a globally exponentially stable and periodic oscillatory BAM neural network, and the conditions can be easily verified and be applied in practice. An example is also given to illustrate our results.

  17. Retrieval and organizational strategies in conceptual memory a computer model

    CERN Document Server

    Kolodner, Janet L

    2014-01-01

    'Someday we expect that computers will be able to keep us informed about the news. People have imagined being able to ask their home computers questions such as "What's going on in the world?"…'. Originally published in 1984, this book is a fascinating look at the world of memory and computers before the internet became the mainstream phenomenon it is today. It looks at the early development of a computer system that could keep us informed in a way that we now take for granted. Presenting a theory of remembering, based on human information processing, it begins to address many of the hard problems implicated in the quest to make computers remember. The book had two purposes in presenting this theory of remembering. First, to be used in implementing intelligent computer systems, including fact retrieval systems and intelligent systems in general. Any intelligent program needs to use and store and use a great deal of knowledge. The strategies and structures in the book were designed to be used for that purpos...

  18. 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.)

  19. DISTRIBUTED COMPUTING SUPPORT CONTRACT USER SURVEY

    CERN Multimedia

    2001-01-01

    IT Division operates a Distributed Computing Support Service, which offers support to owners and users of all variety of desktops throughout CERN as well as more dedicated services for certain groups, divisions and experiments. It also provides the staff who operate the central and satellite Computing Helpdesks, it supports printers throughout the site and it provides the installation activities of the IT Division PC Service. We have published a questionnaire which seeks to gather your feedback on how the services are seen, how they are progressing and how they can be improved. Please take a few minutes to fill in this questionnaire. Replies will be treated in confidence if desired although you may also request an opportunity to be contacted by CERN's service management directly. Please tell us if you met problems but also if you had a successful conclusion to your request for assistance. You will find the questionnaire at the web site http://wwwinfo/support/survey/desktop-contract There will also be a link ...

  20. DISTRIBUTED COMPUTING SUPPORT SERVICE USER SURVEY

    CERN Multimedia

    2001-01-01

    IT Division operates a Distributed Computing Support Service, which offers support to owners and users of all variety of desktops throughout CERN as well as more dedicated services for certain groups, divisions and experiments. It also provides the staff who operate the central and satellite Computing Helpdesks, it supports printers throughout the site and it provides the installation activities of the IT Division PC Service. We have published a questionnaire, which seeks to gather your feedback on how the services are seen, how they are progressing and how they can be improved. Please take a few minutes to fill in this questionnaire. Replies will be treated in confidence if desired although you may also request an opportunity to be contacted by CERN's service management directly. Please tell us if you met problems but also if you had a successful conclusion to your request for assistance. You will find the questionnaire at the web site http://wwwinfo/support/survey/desktop-contract There will also be a link...

  1. Distributed computing for FTU data handling

    Energy Technology Data Exchange (ETDEWEB)

    Bertocchi, A. E-mail: bertocchi@frascati.enea.it; Bracco, G.; Buceti, G.; Centioli, C.; Giovannozzi, E.; Iannone, F.; Panella, M.; Vitale, V

    2002-06-01

    The growth of data warehouse in tokamak experiment is leading fusion laboratories to provide new IT solutions in data handling. In the last three years, the Frascati Tokamak Upgrade (FTU) experimental database was migrated from IBM-mainframe to Unix distributed computing environment. The migration efforts have taken into account the following items: (1) a new data storage solution based on storage area network over fibre channel; (2) andrew file system (AFS) for wide area network file sharing; (3) 'one measure/one file' philosophy replacing 'one shot/one file' to provide a faster read/write data access; (4) more powerful services, such as AFS, CORBA and MDSplus to allow users to access FTU database from different clients, regardless their O.S.; (5) large availability of data analysis tools, from the locally developed utility SHOW to the multi-platform Matlab, interactive data language and jScope (all these tools are now able to access also the Joint European Torus data, in the framework of the remote data access activity); (6) a batch-computing cluster of Alpha/CompaqTru64 CPU based on CODINE/GRD to optimize utilization of software and hardware resources.

  2. Distributed computing grid experiences in CMS

    CERN Document Server

    Andreeva, Julia; Barrass, T; Bonacorsi, D; Bunn, Julian; Capiluppi, P; Corvo, M; Darmenov, N; De Filippis, N; Donno, F; Donvito, G; Eulisse, G; Fanfani, A; Fanzago, F; Filine, A; Grandi, C; Hernández, J M; Innocente, V; Jan, A; Lacaprara, S; Legrand, I; Metson, S; Newbold, D; Newman, H; Pierro, A; Silvestris, L; Steenberg, C; Stockinger, H; Taylor, Lucas; Thomas, M; Tuura, L; Van Lingen, F; Wildish, Tony

    2005-01-01

    The CMS experiment is currently developing a computing system capable of serving, processing and archiving the large number of events that will be generated when the CMS detector starts taking data. During 2004 CMS undertook a large scale data challenge to demonstrate the ability of the CMS computing system to cope with a sustained data- taking rate equivalent to 25% of startup rate. Its goals were: to run CMS event reconstruction at CERN for a sustained period at 25 Hz input rate; to distribute the data to several regional centers; and enable data access at those centers for analysis. Grid middleware was utilized to help complete all aspects of the challenge. To continue to provide scalable access from anywhere in the world to the data, CMS is developing a layer of software that uses Grid tools to gain access to data and resources, and that aims to provide physicists with a user friendly interface for submitting their analysis jobs. This paper describes the data challenge experience with Grid infrastructure ...

  3. Automating usability of ATLAS distributed computing resources

    International Nuclear Information System (INIS)

    Tupputi, S A; Girolamo, A Di; Kouba, T; Schovancová, J

    2014-01-01

    The automation of ATLAS Distributed Computing (ADC) operations is essential to reduce manpower costs and allow performance-enhancing actions, which improve the reliability of the system. In this perspective a crucial case is the automatic handling of outages of ATLAS computing sites storage resources, which are continuously exploited at the edge of their capabilities. It is challenging to adopt unambiguous decision criteria for storage resources of non-homogeneous types, sizes and roles. The recently developed Storage Area Automatic Blacklisting (SAAB) tool has provided a suitable solution, by employing an inference algorithm which processes history of storage monitoring tests outcome. SAAB accomplishes both the tasks of providing global monitoring as well as automatic operations on single sites. The implementation of the SAAB tool has been the first step in a comprehensive review of the storage areas monitoring and central management at all levels. Such review has involved the reordering and optimization of SAM tests deployment and the inclusion of SAAB results in the ATLAS Site Status Board with both dedicated metrics and views. The resulting structure allows monitoring the storage resources status with fine time-granularity and automatic actions to be taken in foreseen cases, like automatic outage handling and notifications to sites. Hence, the human actions are restricted to reporting and following up problems, where and when needed. In this work we show SAAB working principles and features. We present also the decrease of human interactions achieved within the ATLAS Computing Operation team. The automation results in a prompt reaction to failures, which leads to the optimization of resource exploitation.

  4. Robust dynamical decoupling for quantum computing and quantum memory.

    Science.gov (United States)

    Souza, Alexandre M; Alvarez, Gonzalo A; Suter, Dieter

    2011-06-17

    Dynamical decoupling (DD) is a popular technique for protecting qubits from the environment. However, unless special care is taken, experimental errors in the control pulses used in this technique can destroy the quantum information instead of preserving it. Here, we investigate techniques for making DD sequences robust against different types of experimental errors while retaining good decoupling efficiency in a fluctuating environment. We present experimental data from solid-state nuclear spin qubits and introduce a new DD sequence that is suitable for quantum computing and quantum memory.

  5. Computational performance of a smoothed particle hydrodynamics simulation for shared-memory parallel computing

    Science.gov (United States)

    Nishiura, Daisuke; Furuichi, Mikito; Sakaguchi, Hide

    2015-09-01

    The computational performance of a smoothed particle hydrodynamics (SPH) simulation is investigated for three types of current shared-memory parallel computer devices: many integrated core (MIC) processors, graphics processing units (GPUs), and multi-core CPUs. We are especially interested in efficient shared-memory allocation methods for each chipset, because the efficient data access patterns differ between compute unified device architecture (CUDA) programming for GPUs and OpenMP programming for MIC processors and multi-core CPUs. We first introduce several parallel implementation techniques for the SPH code, and then examine these on our target computer architectures to determine the most effective algorithms for each processor unit. In addition, we evaluate the effective computing performance and power efficiency of the SPH simulation on each architecture, as these are critical metrics for overall performance in a multi-device environment. In our benchmark test, the GPU is found to produce the best arithmetic performance as a standalone device unit, and gives the most efficient power consumption. The multi-core CPU obtains the most effective computing performance. The computational speed of the MIC processor on Xeon Phi approached that of two Xeon CPUs. This indicates that using MICs is an attractive choice for existing SPH codes on multi-core CPUs parallelized by OpenMP, as it gains computational acceleration without the need for significant changes to the source code.

  6. A Case Study on Neural Inspired Dynamic Memory Management Strategies for High Performance Computing.

    Energy Technology Data Exchange (ETDEWEB)

    Vineyard, Craig Michael [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Verzi, Stephen Joseph [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

    2017-09-01

    As high performance computing architectures pursue more computational power there is a need for increased memory capacity and bandwidth as well. A multi-level memory (MLM) architecture addresses this need by combining multiple memory types with different characteristics as varying levels of the same architecture. How to efficiently utilize this memory infrastructure is an unknown challenge, and in this research we sought to investigate whether neural inspired approaches can meaningfully help with memory management. In particular we explored neurogenesis inspired re- source allocation, and were able to show a neural inspired mixed controller policy can beneficially impact how MLM architectures utilize memory.

  7. 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.

  8. A distributed-memory hierarchical solver for general sparse linear systems

    Energy Technology Data Exchange (ETDEWEB)

    Chen, Chao [Stanford Univ., CA (United States). Inst. for Computational and Mathematical Engineering; Pouransari, Hadi [Stanford Univ., CA (United States). Dept. of Mechanical Engineering; Rajamanickam, Sivasankaran [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Center for Computing Research; Boman, Erik G. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Center for Computing Research; Darve, Eric [Stanford Univ., CA (United States). Inst. for Computational and Mathematical Engineering and Dept. of Mechanical Engineering

    2017-12-20

    We present a parallel hierarchical solver for general sparse linear systems on distributed-memory machines. For large-scale problems, this fully algebraic algorithm is faster and more memory-efficient than sparse direct solvers because it exploits the low-rank structure of fill-in blocks. Depending on the accuracy of low-rank approximations, the hierarchical solver can be used either as a direct solver or as a preconditioner. The parallel algorithm is based on data decomposition and requires only local communication for updating boundary data on every processor. Moreover, the computation-to-communication ratio of the parallel algorithm is approximately the volume-to-surface-area ratio of the subdomain owned by every processor. We also provide various numerical results to demonstrate the versatility and scalability of the parallel algorithm.

  9. Neuronal model with distributed delay: analysis and simulation study for gamma distribution memory kernel.

    Science.gov (United States)

    Karmeshu; Gupta, Varun; Kadambari, K V

    2011-06-01

    A single neuronal model incorporating distributed delay (memory)is proposed. The stochastic model has been formulated as a Stochastic Integro-Differential Equation (SIDE) which results in the underlying process being non-Markovian. A detailed analysis of the model when the distributed delay kernel has exponential form (weak delay) has been carried out. The selection of exponential kernel has enabled the transformation of the non-Markovian model to a Markovian model in an extended state space. For the study of First Passage Time (FPT) with exponential delay kernel, the model has been transformed to a system of coupled Stochastic Differential Equations (SDEs) in two-dimensional state space. Simulation studies of the SDEs provide insight into the effect of weak delay kernel on the Inter-Spike Interval(ISI) distribution. A measure based on Jensen-Shannon divergence is proposed which can be used to make a choice between two competing models viz. distributed delay model vis-á-vis LIF model. An interesting feature of the model is that the behavior of (CV(t))((ISI)) (Coefficient of Variation) of the ISI distribution with respect to memory kernel time constant parameter η reveals that neuron can switch from a bursting state to non-bursting state as the noise intensity parameter changes. The membrane potential exhibits decaying auto-correlation structure with or without damped oscillatory behavior depending on the choice of parameters. This behavior is in agreement with empirically observed pattern of spike count in a fixed time window. The power spectral density derived from the auto-correlation function is found to exhibit single and double peaks. The model is also examined for the case of strong delay with memory kernel having the form of Gamma distribution. In contrast to fast decay of damped oscillations of the ISI distribution for the model with weak delay kernel, the decay of damped oscillations is found to be slower for the model with strong delay kernel.

  10. 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.

  11. Perspective: Memcomputing: Leveraging memory and physics to compute efficiently

    Science.gov (United States)

    Di Ventra, Massimiliano; Traversa, Fabio L.

    2018-05-01

    It is well known that physical phenomena may be of great help in computing some difficult problems efficiently. A typical example is prime factorization that may be solved in polynomial time by exploiting quantum entanglement on a quantum computer. There are, however, other types of (non-quantum) physical properties that one may leverage to compute efficiently a wide range of hard problems. In this perspective, we discuss how to employ one such property, memory (time non-locality), in a novel physics-based approach to computation: Memcomputing. In particular, we focus on digital memcomputing machines (DMMs) that are scalable. DMMs can be realized with non-linear dynamical systems with memory. The latter property allows the realization of a new type of Boolean logic, one that is self-organizing. Self-organizing logic gates are "terminal-agnostic," namely, they do not distinguish between the input and output terminals. When appropriately assembled to represent a given combinatorial/optimization problem, the corresponding self-organizing circuit converges to the equilibrium points that express the solutions of the problem at hand. In doing so, DMMs take advantage of the long-range order that develops during the transient dynamics. This collective dynamical behavior, reminiscent of a phase transition, or even the "edge of chaos," is mediated by families of classical trajectories (instantons) that connect critical points of increasing stability in the system's phase space. The topological character of the solution search renders DMMs robust against noise and structural disorder. Since DMMs are non-quantum systems described by ordinary differential equations, not only can they be built in hardware with the available technology, they can also be simulated efficiently on modern classical computers. As an example, we will show the polynomial-time solution of the subset-sum problem for the worst cases, and point to other types of hard problems where simulations of DMMs

  12. Quantum Internet: from Communication to Distributed Computing!

    OpenAIRE

    Caleffi, Marcello; Cacciapuoti, Angela Sara; Bianchi, Giuseppe

    2018-01-01

    In this invited paper, the authors discuss the exponential computing speed-up achievable by interconnecting quantum computers through a quantum internet. They also identify key future research challenges and open problems for quantum internet design and deployment.

  13. Massively Parallel Polar Decomposition on Distributed-Memory Systems

    KAUST Repository

    Ltaief, Hatem

    2018-01-01

    We present a high-performance implementation of the Polar Decomposition (PD) on distributed-memory systems. Building upon on the QR-based Dynamically Weighted Halley (QDWH) algorithm, the key idea lies in finding the best rational approximation for the scalar sign function, which also corresponds to the polar factor for symmetric matrices, to further accelerate the QDWH convergence. Based on the Zolotarev rational functions—introduced by Zolotarev (ZOLO) in 1877— this new PD algorithm ZOLO-PD converges within two iterations even for ill-conditioned matrices, instead of the original six iterations needed for QDWH. ZOLO-PD uses the property of Zolotarev functions that optimality is maintained when two functions are composed in an appropriate manner. The resulting ZOLO-PD has a convergence rate up to seventeen, in contrast to the cubic convergence rate for QDWH. This comes at the price of higher arithmetic costs and memory footprint. These extra floating-point operations can, however, be processed in an embarrassingly parallel fashion. We demonstrate performance using up to 102, 400 cores on two supercomputers. We demonstrate that, in the presence of a large number of processing units, ZOLO-PD is able to outperform QDWH by up to 2.3X speedup, especially in situations where QDWH runs out of work, for instance, in the strong scaling mode of operation.

  14. Sensorimotor memory of object weight distribution during multidigit grasp.

    Science.gov (United States)

    Albert, Frederic; Santello, Marco; Gordon, Andrew M

    2009-10-09

    We studied the ability to transfer three-digit force sharing patterns learned through consecutive lifts of an object with an asymmetric center of mass (CM). After several object lifts, we asked subjects to rotate and translate the object to the contralateral hand and perform one additional lift. This task was performed under two weight conditions (550 and 950 g) to determine the extent to which subjects would be able to transfer weight and CM information. Learning transfer was quantified by measuring the extent to which force sharing patterns and peak object roll on the first post-translation trial resembled those measured on the pre-translation trial with the same CM. We found that the overall gain of fingertip forces was transferred following object rotation, but that the scaling of individual digit forces was specific to the learned digit-object configuration, and thus was not transferred following rotation. As a result, on the first post-translation trial there was a significantly larger object roll following object lift-off than on the pre-translation trial. This suggests that sensorimotor memories for weight, requiring scaling of fingertip force gain, may differ from memories for mass distribution.

  15. Computational Model-Based Prediction of Human Episodic Memory Performance Based on Eye Movements

    Science.gov (United States)

    Sato, Naoyuki; Yamaguchi, Yoko

    Subjects' episodic memory performance is not simply reflected by eye movements. We use a ‘theta phase coding’ model of the hippocampus to predict subjects' memory performance from their eye movements. Results demonstrate the ability of the model to predict subjects' memory performance. These studies provide a novel approach to computational modeling in the human-machine interface.

  16. Computer Use and Its Effect on the Memory Process in Young and Adults

    Science.gov (United States)

    Alliprandini, Paula Mariza Zedu; Straub, Sandra Luzia Wrobel; Brugnera, Elisangela; de Oliveira, Tânia Pitombo; Souza, Isabela Augusta Andrade

    2013-01-01

    This work investigates the effect of computer use in the memory process in young and adults under the Perceptual and Memory experimental conditions. The memory condition involved the phases acquisition of information and recovery, on time intervals (2 min, 24 hours and 1 week) on situations of pre and post-test (before and after the participants…

  17. Earth observation scientific workflows in a distributed computing environment

    CSIR Research Space (South Africa)

    Van Zyl, TL

    2011-09-01

    Full Text Available capabilities has focused on the web services approach as exemplified by the OGC's Web Processing Service and by GRID computing. The approach to leveraging distributed computing resources described in this paper uses instead remote objects via RPy...

  18. 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...

  19. Particle simulation on a distributed memory highly parallel processor

    International Nuclear Information System (INIS)

    Sato, Hiroyuki; Ikesaka, Morio

    1990-01-01

    This paper describes parallel molecular dynamics simulation of atoms governed by local force interaction. The space in the model is divided into cubic subspaces and mapped to the processor array of the CAP-256, a distributed memory, highly parallel processor developed at Fujitsu Labs. We developed a new technique to avoid redundant calculation of forces between atoms in different processors. Experiments showed the communication overhead was less than 5%, and the idle time due to load imbalance was less than 11% for two model problems which contain 11,532 and 46,128 argon atoms. From the software simulation, the CAP-II which is under development is estimated to be about 45 times faster than CAP-256 and will be able to run the same problem about 40 times faster than Fujitsu's M-380 mainframe when 256 processors are used. (author)

  20. Energy-aware memory management for embedded multimedia systems a computer-aided design approach

    CERN Document Server

    Balasa, Florin

    2011-01-01

    Energy-Aware Memory Management for Embedded Multimedia Systems: A Computer-Aided Design Approach presents recent computer-aided design (CAD) ideas that address memory management tasks, particularly the optimization of energy consumption in the memory subsystem. It explains how to efficiently implement CAD solutions, including theoretical methods and novel algorithms. The book covers various energy-aware design techniques, including data-dependence analysis techniques, memory size estimation methods, extensions of mapping approaches, and memory banking approaches. It shows how these techniques

  1. AGIS: Integration of new technologies used in ATLAS Distributed Computing

    OpenAIRE

    Anisenkov, Alexey; Di Girolamo, Alessandro; Alandes Pradillo, Maria

    2017-01-01

    The variety of the ATLAS Distributed Computing infrastructure requires a central information system to define the topology of computing resources and to store different parameters and configuration data which are needed by various ATLAS software components. The ATLAS Grid Information System (AGIS) is the system designed to integrate configuration and status information about resources, services and topology of the computing infrastructure used by ATLAS Distributed Computing applications and s...

  2. The distribution and the functions of autobiographical memories: Why do older adults remember autobiographical memories from their youth?

    Science.gov (United States)

    Wolf, Tabea; Zimprich, Daniel

    2016-09-01

    In the present study, the distribution of autobiographical memories was examined from a functional perspective: we examined whether the extent to which long-term autobiographical memories were rated as having a self-, a directive, or a social function affects the location (mean age) and scale (standard deviation) of the memory distribution. Analyses were based on a total of 5598 autobiographical memories generated by 149 adults aged between 50 and 81 years in response to 51 cue-words. Participants provided their age at the time when the recalled events had happened and rated how frequently they recall these events for self-, directive, and social purposes. While more frequently using autobiographical memories for self-functions was associated with an earlier mean age, memories frequently shared with others showed a narrower distribution around a later mean age. The directive function, by contrast, did not affect the memory distribution. The results strengthen the assumption that experiences from an individual's late adolescence serve to maintain a sense of self-continuity throughout the lifespan. Experiences that are frequently shared with others, in contrast, stem from a narrow age range located in young adulthood.

  3. Distributed Computations Environment Protection Using Artificial Immune Systems

    Directory of Open Access Journals (Sweden)

    A. V. Moiseev

    2011-12-01

    Full Text Available In this article the authors describe possibility of artificial immune systems applying for distributed computations environment protection from definite types of malicious impacts.

  4. 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.

  5. modeling workflow management in a distributed computing system

    African Journals Online (AJOL)

    Dr Obe

    communication system, which allows for computerized support. ... Keywords: Distributed computing system; Petri nets;Workflow management. 1. ... A distributed operating system usually .... the questionnaire is returned with invalid data,.

  6. Providing for organizational memory in computer supported meetings

    OpenAIRE

    Schwabe, Gerhard

    1994-01-01

    Meeting memory features are poorly integrated into current group support systems (GSS). In this article, I discuss how to introduce meeting memory functionality into a GSS. The article first introduces the benefits of effective meetings and organizational memory to an organization. Then, the following challenges to design are discussed: How to store semantically rich output, how to build up the meeting memory with a minimum of additional effort, how to integrate meeting memory into organizati...

  7. All-spin logic operations: Memory device and reconfigurable computing

    Science.gov (United States)

    Patra, Moumita; Maiti, Santanu K.

    2018-02-01

    Exploiting spin degree of freedom of electron a new proposal is given to characterize spin-based logical operations using a quantum interferometer that can be utilized as a programmable spin logic device (PSLD). The ON and OFF states of both inputs and outputs are described by spin state only, circumventing spin-to-charge conversion at every stage as often used in conventional devices with the inclusion of extra hardware that can eventually diminish the efficiency. All possible logic functions can be engineered from a single device without redesigning the circuit which certainly offers the opportunities of designing new generation spintronic devices. Moreover, we also discuss the utilization of the present model as a memory device and suitable computing operations with proposed experimental setups.

  8. Irrelevant sensory stimuli interfere with working memory storage: evidence from a computational model of prefrontal neurons.

    Science.gov (United States)

    Bancroft, Tyler D; Hockley, William E; Servos, Philip

    2013-03-01

    The encoding of irrelevant stimuli into the memory store has previously been suggested as a mechanism of interference in working memory (e.g., Lange & Oberauer, Memory, 13, 333-339, 2005; Nairne, Memory & Cognition, 18, 251-269, 1990). Recently, Bancroft and Servos (Experimental Brain Research, 208, 529-532, 2011) used a tactile working memory task to provide experimental evidence that irrelevant stimuli were, in fact, encoded into working memory. In the present study, we replicated Bancroft and Servos's experimental findings using a biologically based computational model of prefrontal neurons, providing a neurocomputational model of overwriting in working memory. Furthermore, our modeling results show that inhibition acts to protect the contents of working memory, and they suggest a need for further experimental research into the capacity of vibrotactile working memory.

  9. AGIS: Integration of new technologies used in ATLAS Distributed Computing

    CERN Document Server

    AUTHOR|(INSPIRE)INSPIRE-00291854; The ATLAS collaboration; Di Girolamo, Alessandro; Alandes Pradillo, Maria

    2017-01-01

    The variety of the ATLAS Distributed Computing infrastructure requires a central information system to define the topology of computing resources and to store different parameters and configuration data which are needed by various ATLAS software components. The ATLAS Grid Information System (AGIS) is the system designed to integrate configuration and status information about resources, services and topology of the computing infrastructure used by ATLAS Distributed Computing applications and services. Being an intermediate middleware system between clients and external information sources (like central BDII, GOCDB, MyOSG), AGIS defines the relations between experiment specific used resources and physical distributed computing capabilities. Being in production during LHC Runl AGIS became the central information system for Distributed Computing in ATLAS and it is continuously evolving to fulfil new user requests, enable enhanced operations and follow the extension of the ATLAS Computing model. The ATLAS Computin...

  10. 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.

  11. Interoperable mesh components for large-scale, distributed-memory simulations

    International Nuclear Information System (INIS)

    Devine, K; Leung, V; Diachin, L; Miller, M

    2009-01-01

    SciDAC applications have a demonstrated need for advanced software tools to manage the complexities associated with sophisticated geometry, mesh, and field manipulation tasks, particularly as computer architectures move toward the petascale. In this paper, we describe a software component - an abstract data model and programming interface - designed to provide support for parallel unstructured mesh operations. We describe key issues that must be addressed to successfully provide high-performance, distributed-memory unstructured mesh services and highlight some recent research accomplishments in developing new load balancing and MPI-based communication libraries appropriate for leadership class computing. Finally, we give examples of the use of parallel adaptive mesh modification in two SciDAC applications.

  12. 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)

  13. Computational and empirical simulations of selective memory impairments: Converging evidence for a single-system account of memory dissociations.

    Science.gov (United States)

    Curtis, Evan T; Jamieson, Randall K

    2018-04-01

    Current theory has divided memory into multiple systems, resulting in a fractionated account of human behaviour. By an alternative perspective, memory is a single system. However, debate over the details of different single-system theories has overshadowed the converging agreement among them, slowing the reunification of memory. Evidence in favour of dividing memory often takes the form of dissociations observed in amnesia, where amnesic patients are impaired on some memory tasks but not others. The dissociations are taken as evidence for separate explicit and implicit memory systems. We argue against this perspective. We simulate two key dissociations between classification and recognition in a computational model of memory, A Theory of Nonanalytic Association. We assume that amnesia reflects a quantitative difference in the quality of encoding. We also present empirical evidence that replicates the dissociations in healthy participants, simulating amnesic behaviour by reducing study time. In both analyses, we successfully reproduce the dissociations. We integrate our computational and empirical successes with the success of alternative models and manipulations and argue that our demonstrations, taken in concert with similar demonstrations with similar models, provide converging evidence for a more general set of single-system analyses that support the conclusion that a wide variety of memory phenomena can be explained by a unified and coherent set of principles.

  14. Power profiling of Cholesky and QR factorizations on distributed memory systems

    KAUST Repository

    Bosilca, George; Ltaief, Hatem; Dongarra, Jack

    2012-01-01

    with a dynamic distributed scheduler (DAGuE) to leverage distributed memory systems. We present performance results (Gflop/s) as well as the power profile (Watts) of two common dense factorizations needed to solve linear systems of equations, namely

  15. Spin-transfer torque magnetoresistive random-access memory technologies for normally off computing (invited)

    International Nuclear Information System (INIS)

    Ando, K.; Yuasa, S.; Fujita, S.; Ito, J.; Yoda, H.; Suzuki, Y.; Nakatani, Y.; Miyazaki, T.

    2014-01-01

    Most parts of present computer systems are made of volatile devices, and the power to supply them to avoid information loss causes huge energy losses. We can eliminate this meaningless energy loss by utilizing the non-volatile function of advanced spin-transfer torque magnetoresistive random-access memory (STT-MRAM) technology and create a new type of computer, i.e., normally off computers. Critical tasks to achieve normally off computers are implementations of STT-MRAM technologies in the main memory and low-level cache memories. STT-MRAM technology for applications to the main memory has been successfully developed by using perpendicular STT-MRAMs, and faster STT-MRAM technologies for applications to the cache memory are now being developed. The present status of STT-MRAMs and challenges that remain for normally off computers are discussed

  16. Differentiation and Response Bias in Episodic Memory: Evidence from Reaction Time Distributions

    Science.gov (United States)

    Criss, Amy H.

    2010-01-01

    In differentiation models, the processes of encoding and retrieval produce an increase in the distribution of memory strength for targets and a decrease in the distribution of memory strength for foils as the amount of encoding increases. This produces an increase in the hit rate and decrease in the false-alarm rate for a strongly encoded compared…

  17. Programs for Testing Processor-in-Memory Computing Systems

    Science.gov (United States)

    Katz, Daniel S.

    2006-01-01

    The Multithreaded Microbenchmarks for Processor-In-Memory (PIM) Compilers, Simulators, and Hardware are computer programs arranged in a series for use in testing the performances of PIM computing systems, including compilers, simulators, and hardware. The programs at the beginning of the series test basic functionality; the programs at subsequent positions in the series test increasingly complex functionality. The programs are intended to be used while designing a PIM system, and can be used to verify that compilers, simulators, and hardware work correctly. The programs can also be used to enable designers of these system components to examine tradeoffs in implementation. Finally, these programs can be run on non-PIM hardware (either single-threaded or multithreaded) using the POSIX pthreads standard to verify that the benchmarks themselves operate correctly. [POSIX (Portable Operating System Interface for UNIX) is a set of standards that define how programs and operating systems interact with each other. pthreads is a library of pre-emptive thread routines that comply with one of the POSIX standards.

  18. Modeling Workflow Management in a Distributed Computing System ...

    African Journals Online (AJOL)

    Distributed computing is becoming increasingly important in our daily life. This is because it enables the people who use it to share information more rapidly and increases their productivity. A major characteristic feature or distributed computing is the explicit representation of process logic within a communication system, ...

  19. Programming Languages for Distributed Computing Systems

    NARCIS (Netherlands)

    Bal, H.E.; Steiner, J.G.; Tanenbaum, A.S.

    1989-01-01

    When distributed systems first appeared, they were programmed in traditional sequential languages, usually with the addition of a few library procedures for sending and receiving messages. As distributed applications became more commonplace and more sophisticated, this ad hoc approach became less

  20. Building mail server on distributed computing system

    International Nuclear Information System (INIS)

    Akihiro Shibata; Osamu Hamada; Tomoko Oshikubo; Takashi Sasaki

    2001-01-01

    The electronic mail has become the indispensable function in daily job, and the server stability and performance are required. Using DCE and DFS we have built the distributed electronic mail sever, that is, servers such as SMTP, IMAP are distributed symmetrically, and provides the seamless access

  1. 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.

  2. The Principals and Practice of Distributed High Throughput Computing

    CERN Multimedia

    CERN. Geneva

    2016-01-01

    The potential of Distributed Processing Systems to deliver computing capabilities with qualities ranging from high availability and reliability to easy expansion in functionality and capacity were recognized and formalized in the 1970’s. For more three decade these principals Distributed Computing guided the development of the HTCondor resource and job management system. The widely adopted suite of software tools offered by HTCondor are based on novel distributed computing technologies and are driven by the evolving needs of High Throughput scientific applications. We will review the principals that underpin our work, the distributed computing frameworks and technologies we developed and the lessons we learned from delivering effective and dependable software tools in an ever changing landscape computing technologies and needs that range today from a desktop computer to tens of thousands of cores offered by commercial clouds. About the speaker Miron Livny received a B.Sc. degree in Physics and Mat...

  3. Large-scale particle simulations in a virtual-memory computer

    International Nuclear Information System (INIS)

    Gray, P.C.; Wagner, J.S.; Tajima, T.; Million, R.

    1982-08-01

    Virtual memory computers are capable of executing large-scale particle simulations even when the memory requirements exceed the computer core size. The required address space is automatically mapped onto slow disc memory by the operating system. When the simulation size is very large, frequent random accesses to slow memory occur during the charge accumulation and particle pushing processes. Accesses to slow memory significantly reduce the execution rate of the simulation. We demonstrate in this paper that with the proper choice of sorting algorithm, a nominal amount of sorting to keep physically adjacent particles near particles with neighboring array indices can reduce random access to slow memory, increase the efficiency of the I/O system, and hence, reduce the required computing time

  4. Working Memory Interventions with Children: Classrooms or Computers?

    Science.gov (United States)

    Colmar, Susan; Double, Kit

    2017-01-01

    The importance of working memory to classroom functioning and academic outcomes has led to the development of many interventions designed to enhance students' working memory. In this article we briefly review the evidence for the relative effectiveness of classroom and computerised working memory interventions in bringing about measurable and…

  5. Simulation of radiation effects on three-dimensional computer optical memories

    International Nuclear Information System (INIS)

    Moscovitch, M.; Emfietzoglou, D.

    1997-01-01

    A model was developed to simulate the effects of heavy charged-particle (HCP) radiation on the information stored in three-dimensional computer optical memories. The model is based on (i) the HCP track radial dose distribution, (ii) the spatial and temporal distribution of temperature in the track, (iii) the matrix-specific radiation-induced changes that will affect the response, and (iv) the kinetics of transition of photochromic molecules from the colored to the colorless isomeric form (bit flip). It is shown that information stored in a volume of several nanometers radius around the particle close-quote s track axis may be lost. The magnitude of the effect is dependent on the particle close-quote s track structure. copyright 1997 American Institute of Physics

  6. Simulation of radiation effects on three-dimensional computer optical memories

    Science.gov (United States)

    Moscovitch, M.; Emfietzoglou, D.

    1997-01-01

    A model was developed to simulate the effects of heavy charged-particle (HCP) radiation on the information stored in three-dimensional computer optical memories. The model is based on (i) the HCP track radial dose distribution, (ii) the spatial and temporal distribution of temperature in the track, (iii) the matrix-specific radiation-induced changes that will affect the response, and (iv) the kinetics of transition of photochromic molecules from the colored to the colorless isomeric form (bit flip). It is shown that information stored in a volume of several nanometers radius around the particle's track axis may be lost. The magnitude of the effect is dependent on the particle's track structure.

  7. From parallel to distributed computing for reactive scattering calculations

    International Nuclear Information System (INIS)

    Lagana, A.; Gervasi, O.; Baraglia, R.

    1994-01-01

    Some reactive scattering codes have been ported on different innovative computer architectures ranging from massively parallel machines to clustered workstations. The porting has required a drastic restructuring of the codes to single out computationally decoupled cpu intensive subsections. The suitability of different theoretical approaches for parallel and distributed computing restructuring is discussed and the efficiency of related algorithms evaluated

  8. 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.

  9. Distributed computing environment monitoring and user expectations

    International Nuclear Information System (INIS)

    Cottrell, R.L.A.; Logg, C.A.

    1996-01-01

    This paper discusses the growing needs for distributed system monitoring and compares it to current practices. It then goes to identify the components of distributed system monitoring and shows how they are implemented and successfully used at one site today to address the Local area Network (WAN), and host monitoring. It shows how this monitoring can be used to develop realistic service level expectations and also identifies the costs. Finally, the paper briefly discusses the future challenges in network monitoring. (author)

  10. Evaluation of External Memory Access Performance on a High-End FPGA Hybrid Computer

    Directory of Open Access Journals (Sweden)

    Konstantinos Kalaitzis

    2016-10-01

    Full Text Available The motivation of this research was to evaluate the main memory performance of a hybrid super computer such as the Convey HC-x, and ascertain how the controller performs in several access scenarios, vis-à-vis hand-coded memory prefetches. Such memory patterns are very useful in stencil computations. The theoretical bandwidth of the memory of the Convey is compared with the results of our measurements. The accurate study of the memory subsystem is particularly useful for users when they are developing their application-specific personality. Experiments were performed to measure the bandwidth between the coprocessor and the memory subsystem. The experiments aimed mainly at measuring the reading access speed of the memory from Application Engines (FPGAs. Different ways of accessing data were used in order to find the most efficient way to access memory. This way was proposed for future work in the Convey HC-x. When performing a series of accesses to memory, non-uniform latencies occur. The Memory Controller of the Convey HC-x in the coprocessor attempts to cover this latency. We measure memory efficiency as a ratio of the number of memory accesses and the number of execution cycles. The result of this measurement converges to one in most cases. In addition, we performed experiments with hand-coded memory accesses. The analysis of the experimental results shows how the memory subsystem and Memory Controllers work. From this work we conclude that the memory controllers do an excellent job, largely because (transparently to the user they seem to cache large amounts of data, and hence hand-coding is not needed in most situations.

  11. Continuous-variable quantum computing in optical time-frequency modes using quantum memories.

    Science.gov (United States)

    Humphreys, Peter C; Kolthammer, W Steven; Nunn, Joshua; Barbieri, Marco; Datta, Animesh; Walmsley, Ian A

    2014-09-26

    We develop a scheme for time-frequency encoded continuous-variable cluster-state quantum computing using quantum memories. In particular, we propose a method to produce, manipulate, and measure two-dimensional cluster states in a single spatial mode by exploiting the intrinsic time-frequency selectivity of Raman quantum memories. Time-frequency encoding enables the scheme to be extremely compact, requiring a number of memories that are a linear function of only the number of different frequencies in which the computational state is encoded, independent of its temporal duration. We therefore show that quantum memories can be a powerful component for scalable photonic quantum information processing architectures.

  12. A 32-bit computer for large memory applications on the FASTBUS

    International Nuclear Information System (INIS)

    Kellner, R.; Blossom, J.M.; Hung, J.P.

    1985-01-01

    A FASTBUS based 32-bit computer is being built at Los Alamos National Laboratory for use in systems requiring large fast memory in the FASTBUS environment. A separate local execution bus allows data reduction to proceed concurrently with other FASTBUS operations. The computer, which can operate in either master or slave mode, includes the National Semiconductor NS32032 chip set with demand paged memory management, floating point slave processor, interrupt control unit, timers, and time-of-day clock. The 16.0 megabytes of random access memory are interleaved to allow windowed direct memory access on and off the FASTBUS at 80 megabytes per second

  13. Computer program for source distribution process in radiation facility

    International Nuclear Information System (INIS)

    Al-Kassiri, H.; Abdul Ghani, B.

    2007-08-01

    Computer simulation for dose distribution using Visual Basic has been done according to the arrangement and activities of Co-60 sources. This program provides dose distribution in treated products depending on the product density and desired dose. The program is useful for optimization of sources distribution during loading process. there is good agreement between calculated data for the program and experimental data.(Author)

  14. A lightweight communication library for distributed computing

    NARCIS (Netherlands)

    Groen, D.; Rieder, S.; Grosso, P.; de Laat, C.; Portegies Zwart, S.

    2010-01-01

    We present MPWide, a platform-independent communication library for performing message passing between computers. Our library allows coupling of several local message passing interface (MPI) applications through a long-distance network and is specifically optimized for such communications. The

  15. AGIS: Evolution of Distributed Computing Information system for ATLAS

    CERN Document Server

    Anisenkov, Alexey; The ATLAS collaboration; Alandes Pradillo, Maria; Karavakis, Edward

    2015-01-01

    The variety of the ATLAS Computing Infrastructure requires a central information system to define the topology of computing resources and to store the different parameters and configuration data which are needed by the various ATLAS software components. The ATLAS Grid Information System is the system designed to integrate configuration and status information about resources, services and topology of the computing infrastructure used by ATLAS Distributed Computing applications and services.

  16. Reduction of Used Memory Ensemble Kalman Filtering (RumEnKF): A data assimilation scheme for memory intensive, high performance computing

    Science.gov (United States)

    Hut, Rolf; Amisigo, Barnabas A.; Steele-Dunne, Susan; van de Giesen, Nick

    2015-12-01

    Reduction of Used Memory Ensemble Kalman Filtering (RumEnKF) is introduced as a variant on the Ensemble Kalman Filter (EnKF). RumEnKF differs from EnKF in that it does not store the entire ensemble, but rather only saves the first two moments of the ensemble distribution. In this way, the number of ensemble members that can be calculated is less dependent on available memory, and mainly on available computing power (CPU). RumEnKF is developed to make optimal use of current generation super computer architecture, where the number of available floating point operations (flops) increases more rapidly than the available memory and where inter-node communication can quickly become a bottleneck. RumEnKF reduces the used memory compared to the EnKF when the number of ensemble members is greater than half the number of state variables. In this paper, three simple models are used (auto-regressive, low dimensional Lorenz and high dimensional Lorenz) to show that RumEnKF performs similarly to the EnKF. Furthermore, it is also shown that increasing the ensemble size has a similar impact on the estimation error from the three algorithms.

  17. Distributed computing environment monitoring and user expectations

    International Nuclear Information System (INIS)

    Cottrell, R.L.A.; Logg, C.A.

    1995-11-01

    This paper discusses the growing needs for distributed system monitoring and compares it to current practices. It then goes on to identify the components of distributed system monitoring and shows how they are implemented and successfully used at one site today to address the Local Area Network (LAN), network services and applications, the Wide Area Network (WAN), and host monitoring. It shows how this monitoring can be used to develop realistic service level expectations and also identifies the costs. Finally, the paper briefly discusses the future challenges in network monitoring

  18. 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.)

  19. A QDWH-Based SVD Software Framework on Distributed-Memory Manycore Systems

    KAUST Repository

    Sukkari, Dalal

    2017-01-01

    This paper presents a high performance software framework for computing a dense SVD on distributed- memory manycore systems. Originally introduced by Nakatsukasa et al. (Nakatsukasa et al. 2010; Nakatsukasa and Higham 2013), the SVD solver relies on the polar decomposition using the QR Dynamically-Weighted Halley algorithm (QDWH). Although the QDWH-based SVD algorithm performs a significant amount of extra floating-point operations compared to the traditional SVD with the one-stage bidiagonal reduction, the inherent high level of concurrency associated with Level 3 BLAS compute-bound kernels ultimately compensates for the arithmetic complexity overhead. Using the ScaLAPACK two-dimensional block cyclic data distribution with a rectangular processor topology, the resulting QDWH-SVD further reduces excessive communications during the panel factorization, while increasing the degree of parallelism during the update of the trailing submatrix, as opposed to relying to the default square processor grid. After detailing the algorithmic complexity and the memory footprint of the algorithm, we conduct a thorough performance analysis and study the impact of the grid topology on the performance by looking at the communication and computation profiling trade-offs. We report performance results against state-of-the-art existing QDWH software implementations (e.g., Elemental) and their SVD extensions on large-scale distributed-memory manycore systems based on commodity Intel x86 Haswell processors and Knights Landing (KNL) architecture. The QDWH-SVD framework achieves up to 3/8-fold on the Haswell/KNL-based platforms, respectively, against ScaLAPACK PDGESVD and turns out to be a competitive alternative for well and ill-conditioned matrices. We finally come up herein with a performance model based on these empirical results. Our QDWH-based polar decomposition and its SVD extension are freely available at https://github.com/ecrc/qdwh.git and https

  20. Distributed metadata in a high performance computing environment

    Science.gov (United States)

    Bent, John M.; Faibish, Sorin; Zhang, Zhenhua; Liu, Xuezhao; Tang, Haiying

    2017-07-11

    A computer-executable method, system, and computer program product for managing meta-data in a distributed storage system, wherein the distributed storage system includes one or more burst buffers enabled to operate with a distributed key-value store, the co computer-executable method, system, and computer program product comprising receiving a request for meta-data associated with a block of data stored in a first burst buffer of the one or more burst buffers in the distributed storage system, wherein the meta data is associated with a key-value, determining which of the one or more burst buffers stores the requested metadata, and upon determination that a first burst buffer of the one or more burst buffers stores the requested metadata, locating the key-value in a portion of the distributed key-value store accessible from the first burst buffer.

  1. Wearable Intrinsically Soft, Stretchable, Flexible Devices for Memories and Computing.

    Science.gov (United States)

    Rajan, Krishna; Garofalo, Erik; Chiolerio, Alessandro

    2018-01-27

    A recent trend in the development of high mass consumption electron devices is towards electronic textiles (e-textiles), smart wearable devices, smart clothes, and flexible or printable electronics. Intrinsically soft, stretchable, flexible, Wearable Memories and Computing devices (WMCs) bring us closer to sci-fi scenarios, where future electronic systems are totally integrated in our everyday outfits and help us in achieving a higher comfort level, interacting for us with other digital devices such as smartphones and domotics, or with analog devices, such as our brain/peripheral nervous system. WMC will enable each of us to contribute to open and big data systems as individual nodes, providing real-time information about physical and environmental parameters (including air pollution monitoring, sound and light pollution, chemical or radioactive fallout alert, network availability, and so on). Furthermore, WMC could be directly connected to human brain and enable extremely fast operation and unprecedented interface complexity, directly mapping the continuous states available to biological systems. This review focuses on recent advances in nanotechnology and materials science and pays particular attention to any result and promising technology to enable intrinsically soft, stretchable, flexible WMC.

  2. A lightweight communication library for distributed computing

    International Nuclear Information System (INIS)

    Groen, Derek; Rieder, Steven; Zwart, Simon Portegies; Grosso, Paola; Laat, Cees de

    2010-01-01

    We present MPWide, a platform-independent communication library for performing message passing between computers. Our library allows coupling of several local message passing interface (MPI) applications through a long-distance network and is specifically optimized for such communications. The implementation is deliberately kept lightweight and platform independent, and the library can be installed and used without administrative privileges. The only requirements are a C++ compiler and at least one open port to a wide-area network on each site. In this paper we present the library, describe the user interface, present performance tests and apply MPWide in a large-scale cosmological N-body simulation on a network of two computers, one in Amsterdam and the other in Tokyo.

  3. AGIS: Integration of new technologies used in ATLAS Distributed Computing

    Science.gov (United States)

    Anisenkov, Alexey; Di Girolamo, Alessandro; Alandes Pradillo, Maria

    2017-10-01

    The variety of the ATLAS Distributed Computing infrastructure requires a central information system to define the topology of computing resources and to store different parameters and configuration data which are needed by various ATLAS software components. The ATLAS Grid Information System (AGIS) is the system designed to integrate configuration and status information about resources, services and topology of the computing infrastructure used by ATLAS Distributed Computing applications and services. Being an intermediate middleware system between clients and external information sources (like central BDII, GOCDB, MyOSG), AGIS defines the relations between experiment specific used resources and physical distributed computing capabilities. Being in production during LHC Runl AGIS became the central information system for Distributed Computing in ATLAS and it is continuously evolving to fulfil new user requests, enable enhanced operations and follow the extension of the ATLAS Computing model. The ATLAS Computing model and data structures used by Distributed Computing applications and services are continuously evolving and trend to fit newer requirements from ADC community. In this note, we describe the evolution and the recent developments of AGIS functionalities, related to integration of new technologies recently become widely used in ATLAS Computing, like flexible computing utilization of opportunistic Cloud and HPC resources, ObjectStore services integration for Distributed Data Management (Rucio) and ATLAS workload management (PanDA) systems, unified storage protocols declaration required for PandDA Pilot site movers and others. The improvements of information model and general updates are also shown, in particular we explain how other collaborations outside ATLAS could benefit the system as a computing resources information catalogue. AGIS is evolving towards a common information system, not coupled to a specific experiment.

  4. AGIS: Integration of new technologies used in ATLAS Distributed Computing

    CERN Document Server

    Anisenkov, Alexey; The ATLAS collaboration; Alandes Pradillo, Maria

    2016-01-01

    AGIS is the information system designed to integrate configuration and status information about resources, services and topology of the computing infrastructure used by ATLAS Distributed Computing (ADC) applications and services. In this note, we describe the evolution and the recent developments of AGIS functionalities, related to integration of new technologies recently become widely used in ATLAS Computing like flexible computing utilization of opportunistic Cloud and HPC resources, ObjectStore services integration for Distributed Data Management (Rucio) and ATLAS workload management (PanDA) systems, unified storage protocols declaration required for PandDA Pilot site movers and others.

  5. Predictive access control for distributed computation

    DEFF Research Database (Denmark)

    Yang, Fan; Hankin, Chris; Nielson, Flemming

    2013-01-01

    We show how to use aspect-oriented programming to separate security and trust issues from the logical design of mobile, distributed systems. The main challenge is how to enforce various types of security policies, in particular predictive access control policies — policies based on the future beh...... behavior of a program. A novel feature of our approach is that we can define policies concerning secondary use of data....

  6. 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.

  7. 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.

  8. 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.

  9. 7th International Symposium on Intelligent Distributed Computing

    CERN Document Server

    Jung, Jason; Badica, Costin

    2014-01-01

    This book represents the combined peer-reviewed proceedings of the Seventh International Symposium on Intelligent Distributed Computing - IDC-2013, of the Second Workshop on Agents for Clouds - A4C-2013, of the Fifth International Workshop on Multi-Agent Systems Technology and Semantics - MASTS-2013, and of the International Workshop on Intelligent Robots - iR-2013. All the events were held in Prague, Czech Republic during September 4-6, 2013. The 41 contributions published in this book address many topics related to theory and applications of intelligent distributed computing and multi-agent systems, including: agent-based data processing, ambient intelligence, bio-informatics, collaborative systems, cryptography and security, distributed algorithms, grid and cloud computing, information extraction, intelligent robotics, knowledge management, linked data, mobile agents, ontologies, pervasive computing, self-organizing systems, peer-to-peer computing, social networks and trust, and swarm intelligence.  .

  10. Clock distribution system for digital computers

    International Nuclear Information System (INIS)

    Loomis, H.H.; Wyman, R.H.

    1981-01-01

    An apparatus is disclosed for eliminating, in each clock distribution amplifier of a clock distribution system, sequential pulse catch-up error due to one pulse ''overtaking'' a prior clock pulse. The apparatus includes timing means to produce a periodic electromagnetic signal with a fundamental frequency having a fundamental frequency component v'01(T); an array of N signal characteristic detector means, with detector means no. 1 receiving the timing means signal and producing a change-of-state signal v1(T) in response to receipt of a signal above a predetermined threshold; N substantially identical filter means, one filter means being operatively associated with each detector means, for receiving the change-of-state signal vn(T) and producing a modified change-of-state signal v'n(T) (N 1, . . . , n) having a fundamental frequency component that is substantially proportional to v'01(T- theta n(T) with a cumulative phase shift theta n(T) having a time derivative that may be made uniformly and arbitrarily small; and with the detector means n+1 (1 < or = n< n) receiving a modified change-of-state signal vn(T) from filter means no. N and, in response to receipt of such a signal above a predetermined threshold, producing a change-of-state signal vn+1

  11. Actors: A Model of Concurrent Computation in Distributed Systems.

    Science.gov (United States)

    1985-06-01

    Artificial Intelligence Labora- tory of the Massachusetts Institute of Technology. Support for the labora- tory’s aritificial intelligence research is...RD-A157 917 ACTORS: A MODEL OF CONCURRENT COMPUTATION IN 1/3- DISTRIBUTED SY𔃿TEMS(U) MASSACHUSETTS INST OF TECH CRMBRIDGE ARTIFICIAL INTELLIGENCE ...Computation In Distributed Systems Gui A. Aghai MIT Artificial Intelligence Laboratory Thsdocument ha. been cipp-oved I= pblicrelease and sale; itsI

  12. CMS on the GRID: Toward a fully distributed computing architecture

    International Nuclear Information System (INIS)

    Innocente, Vincenzo

    2003-01-01

    The computing systems required to collect, analyse and store the physics data at LHC would need to be distributed and global in scope. CMS is actively involved in several grid-related projects to develop and deploy a fully distributed computing architecture. We present here recent developments of tools for automating job submission and for serving data to remote analysis stations. Plans for further test and deployment of a production grid are also described

  13. The Sensitivity of Memory Consolidation and Reconsolidation to Inhibitors of Protein Synthesis and Kinases: Computational Analysis

    Science.gov (United States)

    Zhang, Yili; Smolen, Paul; Baxter, Douglas A.; Byrne, John H.

    2010-01-01

    Memory consolidation and reconsolidation require kinase activation and protein synthesis. Blocking either process during or shortly after training or recall disrupts memory stabilization, which suggests the existence of a critical time window during which these processes are necessary. Using a computational model of kinase synthesis and…

  14. 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.

  15. Scaling Techniques for Massive Scale-Free Graphs in Distributed (External) Memory

    KAUST Repository

    Pearce, Roger; Gokhale, Maya; Amato, Nancy M.

    2013-01-01

    We present techniques to process large scale-free graphs in distributed memory. Our aim is to scale to trillions of edges, and our research is targeted at leadership class supercomputers and clusters with local non-volatile memory, e.g., NAND Flash

  16. 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...

  17. Developing a Distributed Computing Architecture at Arizona State University.

    Science.gov (United States)

    Armann, Neil; And Others

    1994-01-01

    Development of Arizona State University's computing architecture, designed to ensure that all new distributed computing pieces will work together, is described. Aspects discussed include the business rationale, the general architectural approach, characteristics and objectives of the architecture, specific services, and impact on the university…

  18. 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.

  19. Computational dissection of human episodic memory reveals mental process-specific genetic profiles

    Science.gov (United States)

    Luksys, Gediminas; Fastenrath, Matthias; Coynel, David; Freytag, Virginie; Gschwind, Leo; Heck, Angela; Jessen, Frank; Maier, Wolfgang; Milnik, Annette; Riedel-Heller, Steffi G.; Scherer, Martin; Spalek, Klara; Vogler, Christian; Wagner, Michael; Wolfsgruber, Steffen; Papassotiropoulos, Andreas; de Quervain, Dominique J.-F.

    2015-01-01

    Episodic memory performance is the result of distinct mental processes, such as learning, memory maintenance, and emotional modulation of memory strength. Such processes can be effectively dissociated using computational models. Here we performed gene set enrichment analyses of model parameters estimated from the episodic memory performance of 1,765 healthy young adults. We report robust and replicated associations of the amine compound SLC (solute-carrier) transporters gene set with the learning rate, of the collagen formation and transmembrane receptor protein tyrosine kinase activity gene sets with the modulation of memory strength by negative emotional arousal, and of the L1 cell adhesion molecule (L1CAM) interactions gene set with the repetition-based memory improvement. Furthermore, in a large functional MRI sample of 795 subjects we found that the association between L1CAM interactions and memory maintenance revealed large clusters of differences in brain activity in frontal cortical areas. Our findings provide converging evidence that distinct genetic profiles underlie specific mental processes of human episodic memory. They also provide empirical support to previous theoretical and neurobiological studies linking specific neuromodulators to the learning rate and linking neural cell adhesion molecules to memory maintenance. Furthermore, our study suggests additional memory-related genetic pathways, which may contribute to a better understanding of the neurobiology of human memory. PMID:26261317

  20. Computational dissection of human episodic memory reveals mental process-specific genetic profiles.

    Science.gov (United States)

    Luksys, Gediminas; Fastenrath, Matthias; Coynel, David; Freytag, Virginie; Gschwind, Leo; Heck, Angela; Jessen, Frank; Maier, Wolfgang; Milnik, Annette; Riedel-Heller, Steffi G; Scherer, Martin; Spalek, Klara; Vogler, Christian; Wagner, Michael; Wolfsgruber, Steffen; Papassotiropoulos, Andreas; de Quervain, Dominique J-F

    2015-09-01

    Episodic memory performance is the result of distinct mental processes, such as learning, memory maintenance, and emotional modulation of memory strength. Such processes can be effectively dissociated using computational models. Here we performed gene set enrichment analyses of model parameters estimated from the episodic memory performance of 1,765 healthy young adults. We report robust and replicated associations of the amine compound SLC (solute-carrier) transporters gene set with the learning rate, of the collagen formation and transmembrane receptor protein tyrosine kinase activity gene sets with the modulation of memory strength by negative emotional arousal, and of the L1 cell adhesion molecule (L1CAM) interactions gene set with the repetition-based memory improvement. Furthermore, in a large functional MRI sample of 795 subjects we found that the association between L1CAM interactions and memory maintenance revealed large clusters of differences in brain activity in frontal cortical areas. Our findings provide converging evidence that distinct genetic profiles underlie specific mental processes of human episodic memory. They also provide empirical support to previous theoretical and neurobiological studies linking specific neuromodulators to the learning rate and linking neural cell adhesion molecules to memory maintenance. Furthermore, our study suggests additional memory-related genetic pathways, which may contribute to a better understanding of the neurobiology of human memory.

  1. Perspectives on distributed computing : thirty people, four user types, and the distributed computing user experience.

    Energy Technology Data Exchange (ETDEWEB)

    Childers, L.; Liming, L.; Foster, I.; Mathematics and Computer Science; Univ. of Chicago

    2008-10-15

    This report summarizes the methodology and results of a user perspectives study conducted by the Community Driven Improvement of Globus Software (CDIGS) project. The purpose of the study was to document the work-related goals and challenges facing today's scientific technology users, to record their perspectives on Globus software and the distributed-computing ecosystem, and to provide recommendations to the Globus community based on the observations. Globus is a set of open source software components intended to provide a framework for collaborative computational science activities. Rather than attempting to characterize all users or potential users of Globus software, our strategy has been to speak in detail with a small group of individuals in the scientific community whose work appears to be the kind that could benefit from Globus software, learn as much as possible about their work goals and the challenges they face, and describe what we found. The result is a set of statements about specific individuals experiences. We do not claim that these are representative of a potential user community, but we do claim to have found commonalities and differences among the interviewees that may be reflected in the user community as a whole. We present these as a series of hypotheses that can be tested by subsequent studies, and we offer recommendations to Globus developers based on the assumption that these hypotheses are representative. Specifically, we conducted interviews with thirty technology users in the scientific community. We included both people who have used Globus software and those who have not. We made a point of including individuals who represent a variety of roles in scientific projects, for example, scientists, software developers, engineers, and infrastructure providers. The following material is included in this report: (1) A summary of the reported work-related goals, significant issues, and points of satisfaction with the use of Globus software

  2. 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

  3. Administrator of 9/11 victim compensation fund to administer Hokie Spirit Memorial Fund distributions

    OpenAIRE

    Hincker, Lawrence

    2007-01-01

    Virginia Tech President Charles Steger has asked Kenneth R. Feinberg, who served as "Special Master of the federal September 11th Victim Compensation Fund of 2001," to administer distributions of the university Hokie Spirit Memorial Fund (HSMF).

  4. Arcade: A Web-Java Based Framework for Distributed Computing

    Science.gov (United States)

    Chen, Zhikai; Maly, Kurt; Mehrotra, Piyush; Zubair, Mohammad; Bushnell, Dennis M. (Technical Monitor)

    2000-01-01

    Distributed heterogeneous environments are being increasingly used to execute a variety of large size simulations and computational problems. We are developing Arcade, a web-based environment to design, execute, monitor, and control distributed applications. These targeted applications consist of independent heterogeneous modules which can be executed on a distributed heterogeneous environment. In this paper we describe the overall design of the system and discuss the prototype implementation of the core functionalities required to support such a framework.

  5. MSAProbs-MPI: parallel multiple sequence aligner for distributed-memory systems.

    Science.gov (United States)

    González-Domínguez, Jorge; Liu, Yongchao; Touriño, Juan; Schmidt, Bertil

    2016-12-15

    MSAProbs is a state-of-the-art protein multiple sequence alignment tool based on hidden Markov models. It can achieve high alignment accuracy at the expense of relatively long runtimes for large-scale input datasets. In this work we present MSAProbs-MPI, a distributed-memory parallel version of the multithreaded MSAProbs tool that is able to reduce runtimes by exploiting the compute capabilities of common multicore CPU clusters. Our performance evaluation on a cluster with 32 nodes (each containing two Intel Haswell processors) shows reductions in execution time of over one order of magnitude for typical input datasets. Furthermore, MSAProbs-MPI using eight nodes is faster than the GPU-accelerated QuickProbs running on a Tesla K20. Another strong point is that MSAProbs-MPI can deal with large datasets for which MSAProbs and QuickProbs might fail due to time and memory constraints, respectively. Source code in C ++ and MPI running on Linux systems as well as a reference manual are available at http://msaprobs.sourceforge.net CONTACT: jgonzalezd@udc.esSupplementary information: Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

  6. 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.

  7. Childhood amnesia in the making: different distributions of autobiographical memories in children and adults.

    Science.gov (United States)

    Bauer, Patricia J; Larkina, Marina

    2014-04-01

    Within the memory literature, a robust finding is of childhood amnesia: a relative paucity among adults for autobiographical or personal memories from the first 3 to 4 years of life, and from the first 7 years, a smaller number of memories than would be expected based on normal forgetting. Childhood amnesia is observed in spite of strong evidence that during the period eventually obscured by the amnesia, children construct and preserve autobiographical memories. Why early memories seemingly are lost to recollection is an unanswered question. In the present research, we examined the issue by using the cue word technique to chart the distributions of autobiographical memories in samples of children ages 7 to 11 years and samples of young and middle-aged adults. Among adults, the distributions were best fit by the power function, whereas among children, the exponential function provided a better fit to the distributions of memories. The findings suggest that a major source of childhood amnesia is a constant rate of forgetting in childhood, seemingly resulting from failed consolidation, the outcome of which is a smaller pool of memories available for later retrieval.

  8. 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...

  9. 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...

  10. Efficient Numeric and Geometric Computations using Heterogeneous Shared Memory Architectures

    Science.gov (United States)

    2017-10-04

    to the memory architectures of CPUs and GPUs to obtain good performance and result in good memory performance using cache management. These methods ...Accomplishments: The PI and students has developed new methods for path and ray tracing and their Report Date: 14-Oct-2017 INVESTIGATOR(S): Phone...The efficiency of our method makes it a good candidate for forming hybrid schemes with wave-based models. One possibility is to couple the ray curve

  11. Projection multiplex recording of computer-synthesised one-dimensional Fourier holograms for holographic memory systems: mathematical and experimental modelling

    Energy Technology Data Exchange (ETDEWEB)

    Betin, A Yu; Bobrinev, V I; Verenikina, N M; Donchenko, S S; Odinokov, S B [Research Institute ' Radiotronics and Laser Engineering' , Bauman Moscow State Technical University, Moscow (Russian Federation); Evtikhiev, N N; Zlokazov, E Yu; Starikov, S N; Starikov, R S [National Reseach Nuclear University MEPhI (Moscow Engineering Physics Institute), Moscow (Russian Federation)

    2015-08-31

    A multiplex method of recording computer-synthesised one-dimensional Fourier holograms intended for holographic memory devices is proposed. The method potentially allows increasing the recording density in the previously proposed holographic memory system based on the computer synthesis and projection recording of data page holograms. (holographic memory)

  12. Computer Game Play Reduces Intrusive Memories of Experimental Trauma via Reconsolidation-Update Mechanisms.

    Science.gov (United States)

    James, Ella L; Bonsall, Michael B; Hoppitt, Laura; Tunbridge, Elizabeth M; Geddes, John R; Milton, Amy L; Holmes, Emily A

    2015-08-01

    Memory of a traumatic event becomes consolidated within hours. Intrusive memories can then flash back repeatedly into the mind's eye and cause distress. We investigated whether reconsolidation-the process during which memories become malleable when recalled-can be blocked using a cognitive task and whether such an approach can reduce these unbidden intrusions. We predicted that reconsolidation of a reactivated visual memory of experimental trauma could be disrupted by engaging in a visuospatial task that would compete for visual working memory resources. We showed that intrusive memories were virtually abolished by playing the computer game Tetris following a memory-reactivation task 24 hr after initial exposure to experimental trauma. Furthermore, both memory reactivation and playing Tetris were required to reduce subsequent intrusions (Experiment 2), consistent with reconsolidation-update mechanisms. A simple, noninvasive cognitive-task procedure administered after emotional memory has already consolidated (i.e., > 24 hours after exposure to experimental trauma) may prevent the recurrence of intrusive memories of those emotional events. © The Author(s) 2015.

  13. Computer Generation of Fourier Transform Libraries for Distributed Memory Architectures

    Science.gov (United States)

    2010-12-01

    tractions used in quantum chemistry . It too performs algebraic transformations tominimize the operations count, and then optimizes code based on...existing parallel DFT algorithms, including their strengths and weaknesses. Four-stepFFT.The four-step algorithm [Hegland, 1994;Norton and Silberger , 1987...Sadayappan, and Alexander Sibiryakov. Synthesis of high-performance parallel programs for a class of ab initio quan- tum chemistry models. Proc. of

  14. High speed vision processor with reconfigurable processing element array based on full-custom distributed memory

    Science.gov (United States)

    Chen, Zhe; Yang, Jie; Shi, Cong; Qin, Qi; Liu, Liyuan; Wu, Nanjian

    2016-04-01

    In this paper, a hybrid vision processor based on a compact full-custom distributed memory for near-sensor high-speed image processing is proposed. The proposed processor consists of a reconfigurable processing element (PE) array, a row processor (RP) array, and a dual-core microprocessor. The PE array includes two-dimensional processing elements with a compact full-custom distributed memory. It supports real-time reconfiguration between the PE array and the self-organized map (SOM) neural network. The vision processor is fabricated using a 0.18 µm CMOS technology. The circuit area of the distributed memory is reduced markedly into 1/3 of that of the conventional memory so that the circuit area of the vision processor is reduced by 44.2%. Experimental results demonstrate that the proposed design achieves correct functions.

  15. 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.

  16. Method of computer generation and projection recording of microholograms for holographic memory systems: mathematical modelling and experimental implementation

    International Nuclear Information System (INIS)

    Betin, A Yu; Bobrinev, V I; Evtikhiev, N N; Zherdev, A Yu; Zlokazov, E Yu; Lushnikov, D S; Markin, V V; Odinokov, S B; Starikov, S N; Starikov, R S

    2013-01-01

    A method of computer generation and projection recording of microholograms for holographic memory systems is presented; the results of mathematical modelling and experimental implementation of the method are demonstrated. (holographic memory)

  17. Memory-assisted quantum key distribution resilient against multiple-excitation effects

    Science.gov (United States)

    Lo Piparo, Nicolò; Sinclair, Neil; Razavi, Mohsen

    2018-01-01

    Memory-assisted measurement-device-independent quantum key distribution (MA-MDI-QKD) has recently been proposed as a technique to improve the rate-versus-distance behavior of QKD systems by using existing, or nearly-achievable, quantum technologies. The promise is that MA-MDI-QKD would require less demanding quantum memories than the ones needed for probabilistic quantum repeaters. Nevertheless, early investigations suggest that, in order to beat the conventional memory-less QKD schemes, the quantum memories used in the MA-MDI-QKD protocols must have high bandwidth-storage products and short interaction times. Among different types of quantum memories, ensemble-based memories offer some of the required specifications, but they typically suffer from multiple excitation effects. To avoid the latter issue, in this paper, we propose two new variants of MA-MDI-QKD both relying on single-photon sources for entangling purposes. One is based on known techniques for entanglement distribution in quantum repeaters. This scheme turns out to offer no advantage even if one uses ideal single-photon sources. By finding the root cause of the problem, we then propose another setup, which can outperform single memory-less setups even if we allow for some imperfections in our single-photon sources. For such a scheme, we compare the key rate for different types of ensemble-based memories and show that certain classes of atomic ensembles can improve the rate-versus-distance behavior.

  18. 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

  19. PCI bus content-addressable-memory (CAM) implementation on FPGA for pattern recognition/image retrieval in a distributed environment

    Science.gov (United States)

    Megherbi, Dalila B.; Yan, Yin; Tanmay, Parikh; Khoury, Jed; Woods, C. L.

    2004-11-01

    Recently surveillance and Automatic Target Recognition (ATR) applications are increasing as the cost of computing power needed to process the massive amount of information continues to fall. This computing power has been made possible partly by the latest advances in FPGAs and SOPCs. In particular, to design and implement state-of-the-Art electro-optical imaging systems to provide advanced surveillance capabilities, there is a need to integrate several technologies (e.g. telescope, precise optics, cameras, image/compute vision algorithms, which can be geographically distributed or sharing distributed resources) into a programmable system and DSP systems. Additionally, pattern recognition techniques and fast information retrieval, are often important components of intelligent systems. The aim of this work is using embedded FPGA as a fast, configurable and synthesizable search engine in fast image pattern recognition/retrieval in a distributed hardware/software co-design environment. In particular, we propose and show a low cost Content Addressable Memory (CAM)-based distributed embedded FPGA hardware architecture solution with real time recognition capabilities and computing for pattern look-up, pattern recognition, and image retrieval. We show how the distributed CAM-based architecture offers a performance advantage of an order-of-magnitude over RAM-based architecture (Random Access Memory) search for implementing high speed pattern recognition for image retrieval. The methods of designing, implementing, and analyzing the proposed CAM based embedded architecture are described here. Other SOPC solutions/design issues are covered. Finally, experimental results, hardware verification, and performance evaluations using both the Xilinx Virtex-II and the Altera Apex20k are provided to show the potential and power of the proposed method for low cost reconfigurable fast image pattern recognition/retrieval at the hardware/software co-design level.

  20. Efficient calculation of open quantum system dynamics and time-resolved spectroscopy with distributed memory HEOM (DM-HEOM).

    Science.gov (United States)

    Kramer, Tobias; Noack, Matthias; Reinefeld, Alexander; Rodríguez, Mirta; Zelinskyy, Yaroslav

    2018-06-11

    Time- and frequency-resolved optical signals provide insights into the properties of light-harvesting molecular complexes, including excitation energies, dipole strengths and orientations, as well as in the exciton energy flow through the complex. The hierarchical equations of motion (HEOM) provide a unifying theory, which allows one to study the combined effects of system-environment dissipation and non-Markovian memory without making restrictive assumptions about weak or strong couplings or separability of vibrational and electronic degrees of freedom. With increasing system size the exact solution of the open quantum system dynamics requires memory and compute resources beyond a single compute node. To overcome this barrier, we developed a scalable variant of HEOM. Our distributed memory HEOM, DM-HEOM, is a universal tool for open quantum system dynamics. It is used to accurately compute all experimentally accessible time- and frequency-resolved processes in light-harvesting molecular complexes with arbitrary system-environment couplings for a wide range of temperatures and complex sizes. © 2018 Wiley Periodicals, Inc. © 2018 Wiley Periodicals, Inc.

  1. CMS Distributed Computing Integration in the LHC sustained operations era

    International Nuclear Information System (INIS)

    Grandi, C; Bonacorsi, D; Bockelman, B; Fisk, I

    2011-01-01

    After many years of preparation the CMS computing system has reached a situation where stability in operations limits the possibility to introduce innovative features. Nevertheless it is the same need of stability and smooth operations that requires the introduction of features that were considered not strategic in the previous phases. Examples are: adequate authorization to control and prioritize the access to storage and computing resources; improved monitoring to investigate problems and identify bottlenecks on the infrastructure; increased automation to reduce the manpower needed for operations; effective process to deploy in production new releases of the software tools. We present the work of the CMS Distributed Computing Integration Activity that is responsible for providing a liaison between the CMS distributed computing infrastructure and the software providers, both internal and external to CMS. In particular we describe the introduction of new middleware features during the last 18 months as well as the requirements to Grid and Cloud software developers for the future.

  2. Cloud manufacturing distributed computing technologies for global and sustainable manufacturing

    CERN Document Server

    Mehnen, Jörn

    2013-01-01

    Global networks, which are the primary pillars of the modern manufacturing industry and supply chains, can only cope with the new challenges, requirements and demands when supported by new computing and Internet-based technologies. Cloud Manufacturing: Distributed Computing Technologies for Global and Sustainable Manufacturing introduces a new paradigm for scalable service-oriented sustainable and globally distributed manufacturing systems.   The eleven chapters in this book provide an updated overview of the latest technological development and applications in relevant research areas.  Following an introduction to the essential features of Cloud Computing, chapters cover a range of methods and applications such as the factors that actually affect adoption of the Cloud Computing technology in manufacturing companies and new geometrical simplification method to stream 3-Dimensional design and manufacturing data via the Internet. This is further supported case studies and real life data for Waste Electrical ...

  3. Computer-Presented Organizational/Memory Aids as Instruction for Solving Pico-Fomi Problems.

    Science.gov (United States)

    Steinberg, Esther R.; And Others

    1985-01-01

    Describes investigation of effectiveness of computer-presented organizational/memory aids (matrix and verbal charts controlled by computer or learner) as instructional technique for solving Pico-Fomi problems, and the acquisition of deductive inference rules when such aids are present. Results indicate chart use control should be adapted to…

  4. Single-Chip Computers With Microelectromechanical Systems-Based Magnetic Memory

    NARCIS (Netherlands)

    Carley, L. Richard; Bain, James A.; Fedder, Gary K.; Greve, David W.; Guillou, David F.; Lu, Michael S.C.; Mukherjee, Tamal; Santhanam, Suresh; Abelmann, Leon; Min, Seungook

    This article describes an approach for implementing a complete computer system (CPU, RAM, I/O, and nonvolatile mass memory) on a single integrated-circuit substrate (a chip)—hence, the name "single-chip computer." The approach presented combines advances in the field of microelectromechanical

  5. 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.

  6. First Experiences with LHC Grid Computing and Distributed Analysis

    CERN Document Server

    Fisk, Ian

    2010-01-01

    In this presentation the experiences of the LHC experiments using grid computing were presented with a focus on experience with distributed analysis. After many years of development, preparation, exercises, and validation the LHC (Large Hadron Collider) experiments are in operations. The computing infrastructure has been heavily utilized in the first 6 months of data collection. The general experience of exploiting the grid infrastructure for organized processing and preparation is described, as well as the successes employing the infrastructure for distributed analysis. At the end the expected evolution and future plans are outlined.

  7. Distributed Computing and Artificial Intelligence, 12th International Conference

    CERN Document Server

    Malluhi, Qutaibah; Gonzalez, Sara; Bocewicz, Grzegorz; Bucciarelli, Edgardo; Giulioni, Gianfranco; Iqba, Farkhund

    2015-01-01

    The 12th International Symposium on Distributed Computing and Artificial Intelligence 2015 (DCAI 2015) is a forum to present applications of innovative techniques for studying and solving complex problems. The exchange of ideas between scientists and technicians from both the academic and industrial sector is essential to facilitate the development of systems that can meet the ever-increasing demands of today’s society. The present edition brings together past experience, current work and promising future trends associated with distributed computing, artificial intelligence and their application in order to provide efficient solutions to real problems. This symposium is organized by the Osaka Institute of Technology, Qatar University and the University of Salamanca.

  8. 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

  9. 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.

  10. Proceedings: Distributed digital systems, plant process computers, and networks

    International Nuclear Information System (INIS)

    1995-03-01

    These are the proceedings of a workshop on Distributed Digital Systems, Plant Process Computers, and Networks held in Charlotte, North Carolina on August 16--18, 1994. The purpose of the workshop was to provide a forum for technology transfer, technical information exchange, and education. The workshop was attended by more than 100 representatives of electric utilities, equipment manufacturers, engineering service organizations, and government agencies. The workshop consisted of three days of presentations, exhibitions, a panel discussion and attendee interactions. Original plant process computers at the nuclear power plants are becoming obsolete resulting in increasing difficulties in their effectiveness to support plant operations and maintenance. Some utilities have already replaced their plant process computers by more powerful modern computers while many other utilities intend to replace their aging plant process computers in the future. Information on recent and planned implementations are presented. Choosing an appropriate communications and computing network architecture facilitates integrating new systems and provides functional modularity for both hardware and software. Control room improvements such as CRT-based distributed monitoring and control, as well as digital decision and diagnostic aids, can improve plant operations. Commercially available digital products connected to the plant communications system are now readily available to provide distributed processing where needed. Plant operations, maintenance activities, and engineering analyses can be supported in a cost-effective manner. Selected papers are indexed separately for inclusion in the Energy Science and Technology Database

  11. STADIC: a computer code for combining probability distributions

    International Nuclear Information System (INIS)

    Cairns, J.J.; Fleming, K.N.

    1977-03-01

    The STADIC computer code uses a Monte Carlo simulation technique for combining probability distributions. The specific function for combination of the input distribution is defined by the user by introducing the appropriate FORTRAN statements to the appropriate subroutine. The code generates a Monte Carlo sampling from each of the input distributions and combines these according to the user-supplied function to provide, in essence, a random sampling of the combined distribution. When the desired number of samples is obtained, the output routine calculates the mean, standard deviation, and confidence limits for the resultant distribution. This method of combining probability distributions is particularly useful in cases where analytical approaches are either too difficult or undefined

  12. 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.

  13. Visuospatial memory computations during whole-body rotations in roll

    NARCIS (Netherlands)

    Pelt, S. van; Gisbergen, J.A.M. van; Medendorp, W.P.

    2005-01-01

    We used a memory-saccade task to test whether the location of a target, briefly presented before a whole-body rotation in roll, is stored in egocentric or in allocentric coordinates. To make this distinction, we exploited the fact that subjects, when tilted sideways in darkness, make systematic

  14. Secure Computation, I/O-Efficient Algorithms and Distributed Signatures

    DEFF Research Database (Denmark)

    Damgård, Ivan Bjerre; Kölker, Jonas; Toft, Tomas

    2012-01-01

    values of form r, gr for random secret-shared r ∈ ℤq and gr in a group of order q. This costs a constant number of exponentiation per player per value generated, even if less than n/3 players are malicious. This can be used for efficient distributed computing of Schnorr signatures. We further develop...... the technique so we can sign secret data in a distributed fashion at essentially the same cost....

  15. 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.

  16. Distributed Problem Solving: Adaptive Networks with a Computer Intermediary Resource. Intelligent Executive Computer Communication

    Science.gov (United States)

    1991-06-01

    Proceedings of The National Conference on Artificial Intelligence , pages 181-184, The American Association for Aritificial Intelligence , Pittsburgh...Intermediary Resource: Intelligent Executive Computer Communication John Lyman and Carla J. Conaway University of California at Los Angeles for Contracting...Include Security Classification) Interim Report: Distributed Problem Solving: Adaptive Networks With a Computer Intermediary Resource: Intelligent

  17. 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.

  18. 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.

  19. The future of PanDA in ATLAS distributed computing

    Science.gov (United States)

    De, K.; Klimentov, A.; Maeno, T.; Nilsson, P.; Oleynik, D.; Panitkin, S.; Petrosyan, A.; Schovancova, J.; Vaniachine, A.; Wenaus, T.

    2015-12-01

    Experiments at the Large Hadron Collider (LHC) face unprecedented computing challenges. Heterogeneous resources are distributed worldwide at hundreds of sites, thousands of physicists analyse the data remotely, the volume of processed data is beyond the exabyte scale, while data processing requires more than a few billion hours of computing usage per year. The PanDA (Production and Distributed Analysis) system was developed to meet the scale and complexity of LHC distributed computing for the ATLAS experiment. In the process, the old batch job paradigm of locally managed computing in HEP was discarded in favour of a far more automated, flexible and scalable model. The success of PanDA in ATLAS is leading to widespread adoption and testing by other experiments. PanDA is the first exascale workload management system in HEP, already operating at more than a million computing jobs per day, and processing over an exabyte of data in 2013. There are many new challenges that PanDA will face in the near future, in addition to new challenges of scale, heterogeneity and increasing user base. PanDA will need to handle rapidly changing computing infrastructure, will require factorization of code for easier deployment, will need to incorporate additional information sources including network metrics in decision making, be able to control network circuits, handle dynamically sized workload processing, provide improved visualization, and face many other challenges. In this talk we will focus on the new features, planned or recently implemented, that are relevant to the next decade of distributed computing workload management using PanDA.

  20. Two alternate proofs of Wang's lune formula for sparse distributed memory and an integral approximation

    Science.gov (United States)

    Jaeckel, Louis A.

    1988-01-01

    In Kanerva's Sparse Distributed Memory, writing to and reading from the memory are done in relation to spheres in an n-dimensional binary vector space. Thus it is important to know how many points are in the intersection of two spheres in this space. Two proofs are given of Wang's formula for spheres of unequal radii, and an integral approximation for the intersection in this case.

  1. How are rescaled range analyses affected by different memory and distributional properties? A Monte Carlo study

    Czech Academy of Sciences Publication Activity Database

    Krištoufek, Ladislav

    2012-01-01

    Roč. 391, č. 17 (2012), s. 4252-4260 ISSN 0378-4371 R&D Projects: GA ČR GA402/09/0965 Grant - others:GA UK(CZ) 118310; SVV(CZ) 261 501 Institutional support: RVO:67985556 Keywords : Rescaled range analysis * Modified rescaled range analysis * Hurst exponent * Long - term memory * Short- term memory Subject RIV: AH - Economics Impact factor: 1.676, year: 2012 http://library.utia.cas.cz/separaty/2012/E/kristoufek-how are rescaled range analyses affected by different memory and distributional properties.pdf

  2. Efficient packing of patterns in sparse distributed memory by selective weighting of input bits

    Science.gov (United States)

    Kanerva, Pentti

    1991-01-01

    When a set of patterns is stored in a distributed memory, any given storage location participates in the storage of many patterns. From the perspective of any one stored pattern, the other patterns act as noise, and such noise limits the memory's storage capacity. The more similar the retrieval cues for two patterns are, the more the patterns interfere with each other in memory, and the harder it is to separate them on retrieval. A method is described of weighting the retrieval cues to reduce such interference and thus to improve the separability of patterns that have similar cues.

  3. A database for on-line event analysis on a distributed memory machine

    CERN Document Server

    Argante, E; Van der Stok, P D V; Willers, Ian Malcolm

    1995-01-01

    Parallel in-memory databases can enhance the structuring and parallelization of programs used in High Energy Physics (HEP). Efficient database access routines are used as communication primitives which hide the communication topology in contrast to the more explicit communications like PVM or MPI. A parallel in-memory database, called SPIDER, has been implemented on a 32 node Meiko CS-2 distributed memory machine. The spider primitives generate a lower overhead than the one generated by PVM or PMI. The event reconstruction program, CPREAD of the CPLEAR experiment, has been used as a test case. Performance measurerate generated by CPLEAR.

  4. 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.

  5. Computed tomography of surface related radionuclide distributions ('BONN'-tomography)

    International Nuclear Information System (INIS)

    Bockisch, A.; Koenig, R.

    1989-01-01

    A method called the 'BONN' tomography is described to produce planar projections of circular activity distributions using standard single photon emission computed tomography. The clinical value of the method is demonstrated for bone scans of the jaw, thorax, and pelvis. Numerical or projection-related problems are discussed. (orig.) [de

  6. Distributed Computing with Centralized Support Works at Brigham Young.

    Science.gov (United States)

    McDonald, Kelly; Stone, Brad

    1992-01-01

    Brigham Young University (Utah) has addressed the need for maintenance and support of distributed computing systems on campus by implementing a program patterned after a national business franchise, providing the support and training of a centralized administration but allowing each unit to operate much as an independent small business.…

  7. The Future of PanDA in ATLAS Distributed Computing

    CERN Document Server

    De, Kaushik; The ATLAS collaboration; Maeno, Tadashi; Nilsson, Paul; Oleynik, Danila; Panitkin, Sergey; Petrosyan, Artem; Schovancova, Jaroslava; Vaniachine, Alexandre; Wenaus, Torre

    2015-01-01

    Experiments at the Large Hadron Collider (LHC) face unprecedented computing challenges. Heterogeneous resources are distributed worldwide at hundreds of sites, thousands of physicists analyze the data remotely, the volume of processed data is beyond the exabyte scale, while data processing requires more than a few billion hours of computing usage per year. The PanDA (Production and Distributed Analysis) system was developed to meet the scale and complexity of LHC distributed computing for the ATLAS experiment. In the process, the old batch job paradigm of locally managed computing in HEP was discarded in favor of a far more automated, flexible and scalable model. The success of PanDA in ATLAS is leading to widespread adoption and testing by other experiments. PanDA is the first exascale workload management system in HEP, already operating at more than a million computing jobs per day, and processing over an exabyte of data in 2013. There are many new challenges that PanDA will face in the near future, in addi...

  8. Portable memory consistency for software managed distributed memory in many-core SoC

    NARCIS (Netherlands)

    Rutgers, J.H.; Bekooij, Marco Jan Gerrit; Smit, Gerardus Johannes Maria

    2013-01-01

    Porting software to different platforms can require modifications of the application. One of the issues is that the targeted hardware supports another memory consistency model. As a consequence, the completion order of reads and writes in a multi-threaded application can change, which may result in

  9. Attention and visual memory in visualization and computer graphics.

    Science.gov (United States)

    Healey, Christopher G; Enns, James T

    2012-07-01

    A fundamental goal of visualization is to produce images of data that support visual analysis, exploration, and discovery of novel insights. An important consideration during visualization design is the role of human visual perception. How we "see" details in an image can directly impact a viewer's efficiency and effectiveness. This paper surveys research on attention and visual perception, with a specific focus on results that have direct relevance to visualization and visual analytics. We discuss theories of low-level visual perception, then show how these findings form a foundation for more recent work on visual memory and visual attention. We conclude with a brief overview of how knowledge of visual attention and visual memory is being applied in visualization and graphics. We also discuss how challenges in visualization are motivating research in psychophysics.

  10. Optical interconnection network for parallel access to multi-rank memory in future computing systems.

    Science.gov (United States)

    Wang, Kang; Gu, Huaxi; Yang, Yintang; Wang, Kun

    2015-08-10

    With the number of cores increasing, there is an emerging need for a high-bandwidth low-latency interconnection network, serving core-to-memory communication. In this paper, aiming at the goal of simultaneous access to multi-rank memory, we propose an optical interconnection network for core-to-memory communication. In the proposed network, the wavelength usage is delicately arranged so that cores can communicate with different ranks at the same time and broadcast for flow control can be achieved. A distributed memory controller architecture that works in a pipeline mode is also designed for efficient optical communication and transaction address processes. The scaling method and wavelength assignment for the proposed network are investigated. Compared with traditional electronic bus-based core-to-memory communication, the simulation results based on the PARSEC benchmark show that the bandwidth enhancement and latency reduction are apparent.

  11. ATLAS Distributed Computing Monitoring tools during the LHC Run I

    CERN Document Server

    Schovancova, J; The ATLAS collaboration; Di Girolamo, A; Jezequel, S; Ueda, I; Wenaus, T

    2013-01-01

    This contribution summarizes evolution of the ATLAS Distributed Computing (ADC) Monitoring project during the LHC Run I. The ADC Monitoring targets at the three groups of customers: ADC Operations team to early identify malfunctions and escalate issues to an activity or a service expert, ATLAS national contacts and sites for the real-time monitoring and long-term measurement of the performance of the provided computing resources, and the ATLAS Management for long-term trends and accounting information about the ATLAS Distributed Computing resources.\\\\ During the LHC Run I a significant development effort has been invested in standardization of the monitoring and accounting applications in order to provide extensive monitoring and accounting suite. ADC Monitoring applications separate the data layer and the visualization layer. The data layer exposes data in a predefined format. The visualization layer is designed bearing in mind visual identity of the provided graphical elements, and re-usability of the visua...

  12. ATLAS Distributed Computing Monitoring tools during the LHC Run I

    CERN Document Server

    Schovancova, J; The ATLAS collaboration; Di Girolamo, A; Jezequel, S; Ueda, I; Wenaus, T

    2014-01-01

    This contribution summarizes evolution of the ATLAS Distributed Computing (ADC) Monitoring project during the LHC Run I. The ADC Monitoring targets at the three groups of customers: ADC Operations team to early identify malfunctions and escalate issues to an activity or a service expert, ATLAS national contacts and sites for the real-time monitoring and long-term measurement of the performance of the provided computing resources, and the ATLAS Management for long-term trends and accounting information about the ATLAS Distributed Computing resources.\\\\ During the LHC Run I a significant development effort has been invested in standardization of the monitoring and accounting applications in order to provide extensive monitoring and accounting suite. ADC Monitoring applications separate the data layer and the visualization layer. The data layer exposes data in a predefined format. The visualization layer is designed bearing in mind visual identity of the provided graphical elements, and re-usability of the visua...

  13. Vertical Load Distribution for Cloud Computing via Multiple Implementation Options

    Science.gov (United States)

    Phan, Thomas; Li, Wen-Syan

    Cloud computing looks to deliver software as a provisioned service to end users, but the underlying infrastructure must be sufficiently scalable and robust. In our work, we focus on large-scale enterprise cloud systems and examine how enterprises may use a service-oriented architecture (SOA) to provide a streamlined interface to their business processes. To scale up the business processes, each SOA tier usually deploys multiple servers for load distribution and fault tolerance, a scenario which we term horizontal load distribution. One limitation of this approach is that load cannot be distributed further when all servers in the same tier are loaded. In complex multi-tiered SOA systems, a single business process may actually be implemented by multiple different computation pathways among the tiers, each with different components, in order to provide resilience and scalability. Such multiple implementation options gives opportunities for vertical load distribution across tiers. In this chapter, we look at a novel request routing framework for SOA-based enterprise computing with multiple implementation options that takes into account the options of both horizontal and vertical load distribution.

  14. 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

  15. SuperLU{_}DIST: A scalable distributed-memory sparse direct solver for unsymmetric linear systems

    Energy Technology Data Exchange (ETDEWEB)

    Li, Xiaoye S.; Demmel, James W.

    2002-03-27

    In this paper, we present the main algorithmic features in the software package SuperLU{_}DIST, a distributed-memory sparse direct solver for large sets of linear equations. We give in detail our parallelization strategies, with focus on scalability issues, and demonstrate the parallel performance and scalability on current machines. The solver is based on sparse Gaussian elimination, with an innovative static pivoting strategy proposed earlier by the authors. The main advantage of static pivoting over classical partial pivoting is that it permits a priori determination of data structures and communication pattern for sparse Gaussian elimination, which makes it more scalable on distributed memory machines. Based on this a priori knowledge, we designed highly parallel and scalable algorithms for both LU decomposition and triangular solve and we show that they are suitable for large-scale distributed memory machines.

  16. Computation of distribution of minimum resolution for log-normal distribution of chromatographic peak heights.

    Science.gov (United States)

    Davis, Joe M

    2011-10-28

    General equations are derived for the distribution of minimum resolution between two chromatographic peaks, when peak heights in a multi-component chromatogram follow a continuous statistical distribution. The derivation draws on published theory by relating the area under the distribution of minimum resolution to the area under the distribution of the ratio of peak heights, which in turn is derived from the peak-height distribution. Two procedures are proposed for the equations' numerical solution. The procedures are applied to the log-normal distribution, which recently was reported to describe the distribution of component concentrations in three complex natural mixtures. For published statistical parameters of these mixtures, the distribution of minimum resolution is similar to that for the commonly assumed exponential distribution of peak heights used in statistical-overlap theory. However, these two distributions of minimum resolution can differ markedly, depending on the scale parameter of the log-normal distribution. Theory for the computation of the distribution of minimum resolution is extended to other cases of interest. With the log-normal distribution of peak heights as an example, the distribution of minimum resolution is computed when small peaks are lost due to noise or detection limits, and when the height of at least one peak is less than an upper limit. The distribution of minimum resolution shifts slightly to lower resolution values in the first case and to markedly larger resolution values in the second one. The theory and numerical procedure are confirmed by Monte Carlo simulation. Copyright © 2011 Elsevier B.V. All rights reserved.

  17. AGIS: Evolution of Distributed Computing information system for ATLAS

    Science.gov (United States)

    Anisenkov, A.; Di Girolamo, A.; Alandes, M.; Karavakis, E.

    2015-12-01

    ATLAS, a particle physics experiment at the Large Hadron Collider at CERN, produces petabytes of data annually through simulation production and tens of petabytes of data per year from the detector itself. The ATLAS computing model embraces the Grid paradigm and a high degree of decentralization of computing resources in order to meet the ATLAS requirements of petabytes scale data operations. It has been evolved after the first period of LHC data taking (Run-1) in order to cope with new challenges of the upcoming Run- 2. In this paper we describe the evolution and recent developments of the ATLAS Grid Information System (AGIS), developed in order to integrate configuration and status information about resources, services and topology of the computing infrastructure used by the ATLAS Distributed Computing applications and services.

  18. 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

  19. Forms of memory: Investigating the computational basis of semantic-episodic memory interactions

    NARCIS (Netherlands)

    Neville, D.A.

    2015-01-01

    The present thesis investigated how the memory systems related to the processing of semantic and episodic information combine to generate behavioural performance as measured in standard laboratory tasks. Across a series of behavioural experiment I looked at different types of interactions between

  20. A Parallel Distributed-Memory Particle Method Enables Acquisition-Rate Segmentation of Large Fluorescence Microscopy Images.

    Directory of Open Access Journals (Sweden)

    Yaser Afshar

    Full Text Available Modern fluorescence microscopy modalities, such as light-sheet microscopy, are capable of acquiring large three-dimensional images at high data rate. This creates a bottleneck in computational processing and analysis of the acquired images, as the rate of acquisition outpaces the speed of processing. Moreover, images can be so large that they do not fit the main memory of a single computer. We address both issues by developing a distributed parallel algorithm for segmentation of large fluorescence microscopy images. The method is based on the versatile Discrete Region Competition algorithm, which has previously proven useful in microscopy image segmentation. The present distributed implementation decomposes the input image into smaller sub-images that are distributed across multiple computers. Using network communication, the computers orchestrate the collectively solving of the global segmentation problem. This not only enables segmentation of large images (we test images of up to 10(10 pixels, but also accelerates segmentation to match the time scale of image acquisition. Such acquisition-rate image segmentation is a prerequisite for the smart microscopes of the future and enables online data compression and interactive experiments.

  1. A Parallel Distributed-Memory Particle Method Enables Acquisition-Rate Segmentation of Large Fluorescence Microscopy Images.

    Science.gov (United States)

    Afshar, Yaser; Sbalzarini, Ivo F

    2016-01-01

    Modern fluorescence microscopy modalities, such as light-sheet microscopy, are capable of acquiring large three-dimensional images at high data rate. This creates a bottleneck in computational processing and analysis of the acquired images, as the rate of acquisition outpaces the speed of processing. Moreover, images can be so large that they do not fit the main memory of a single computer. We address both issues by developing a distributed parallel algorithm for segmentation of large fluorescence microscopy images. The method is based on the versatile Discrete Region Competition algorithm, which has previously proven useful in microscopy image segmentation. The present distributed implementation decomposes the input image into smaller sub-images that are distributed across multiple computers. Using network communication, the computers orchestrate the collectively solving of the global segmentation problem. This not only enables segmentation of large images (we test images of up to 10(10) pixels), but also accelerates segmentation to match the time scale of image acquisition. Such acquisition-rate image segmentation is a prerequisite for the smart microscopes of the future and enables online data compression and interactive experiments.

  2. A Parallel Distributed-Memory Particle Method Enables Acquisition-Rate Segmentation of Large Fluorescence Microscopy Images

    Science.gov (United States)

    Afshar, Yaser; Sbalzarini, Ivo F.

    2016-01-01

    Modern fluorescence microscopy modalities, such as light-sheet microscopy, are capable of acquiring large three-dimensional images at high data rate. This creates a bottleneck in computational processing and analysis of the acquired images, as the rate of acquisition outpaces the speed of processing. Moreover, images can be so large that they do not fit the main memory of a single computer. We address both issues by developing a distributed parallel algorithm for segmentation of large fluorescence microscopy images. The method is based on the versatile Discrete Region Competition algorithm, which has previously proven useful in microscopy image segmentation. The present distributed implementation decomposes the input image into smaller sub-images that are distributed across multiple computers. Using network communication, the computers orchestrate the collectively solving of the global segmentation problem. This not only enables segmentation of large images (we test images of up to 1010 pixels), but also accelerates segmentation to match the time scale of image acquisition. Such acquisition-rate image segmentation is a prerequisite for the smart microscopes of the future and enables online data compression and interactive experiments. PMID:27046144

  3. A homotopy method for solving Riccati equations on a shared memory parallel computer

    International Nuclear Information System (INIS)

    Zigic, D.; Watson, L.T.; Collins, E.G. Jr.; Davis, L.D.

    1993-01-01

    Although there are numerous algorithms for solving Riccati equations, there still remains a need for algorithms which can operate efficiently on large problems and on parallel machines. This paper gives a new homotopy-based algorithm for solving Riccati equations on a shared memory parallel computer. The central part of the algorithm is the computation of the kernel of the Jacobian matrix, which is essential for the corrector iterations along the homotopy zero curve. Using a Schur decomposition the tensor product structure of various matrices can be efficiently exploited. The algorithm allows for efficient parallelization on shared memory machines

  4. Distributed parallel computing in stochastic modeling of groundwater systems.

    Science.gov (United States)

    Dong, Yanhui; Li, Guomin; Xu, Haizhen

    2013-03-01

    Stochastic modeling is a rapidly evolving, popular approach to the study of the uncertainty and heterogeneity of groundwater systems. However, the use of Monte Carlo-type simulations to solve practical groundwater problems often encounters computational bottlenecks that hinder the acquisition of meaningful results. To improve the computational efficiency, a system that combines stochastic model generation with MODFLOW-related programs and distributed parallel processing is investigated. The distributed computing framework, called the Java Parallel Processing Framework, is integrated into the system to allow the batch processing of stochastic models in distributed and parallel systems. As an example, the system is applied to the stochastic delineation of well capture zones in the Pinggu Basin in Beijing. Through the use of 50 processing threads on a cluster with 10 multicore nodes, the execution times of 500 realizations are reduced to 3% compared with those of a serial execution. Through this application, the system demonstrates its potential in solving difficult computational problems in practical stochastic modeling. © 2012, The Author(s). Groundwater © 2012, National Ground Water Association.

  5. Software for Distributed Computation on Medical Databases: A Demonstration Project

    Directory of Open Access Journals (Sweden)

    Balasubramanian Narasimhan

    2017-05-01

    Full Text Available Bringing together the information latent in distributed medical databases promises to personalize medical care by enabling reliable, stable modeling of outcomes with rich feature sets (including patient characteristics and treatments received. However, there are barriers to aggregation of medical data, due to lack of standardization of ontologies, privacy concerns, proprietary attitudes toward data, and a reluctance to give up control over end use. Aggregation of data is not always necessary for model fitting. In models based on maximizing a likelihood, the computations can be distributed, with aggregation limited to the intermediate results of calculations on local data, rather than raw data. Distributed fitting is also possible for singular value decomposition. There has been work on the technical aspects of shared computation for particular applications, but little has been published on the software needed to support the "social networking" aspect of shared computing, to reduce the barriers to collaboration. We describe a set of software tools that allow the rapid assembly of a collaborative computational project, based on the flexible and extensible R statistical software and other open source packages, that can work across a heterogeneous collection of database environments, with full transparency to allow local officials concerned with privacy protections to validate the safety of the method. We describe the principles, architecture, and successful test results for the site-stratified Cox model and rank-k singular value decomposition.

  6. 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...

  7. 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.

  8. Improving flow distribution in influent channels using computational fluid dynamics.

    Science.gov (United States)

    Park, No-Suk; Yoon, Sukmin; Jeong, Woochang; Lee, Seungjae

    2016-10-01

    Although the flow distribution in an influent channel where the inflow is split into each treatment process in a wastewater treatment plant greatly affects the efficiency of the process, and a weir is the typical structure for the flow distribution, to the authors' knowledge, there is a paucity of research on the flow distribution in an open channel with a weir. In this study, the influent channel of a real-scale wastewater treatment plant was used, installing a suppressed rectangular weir that has a horizontal crest to cross the full channel width. The flow distribution in the influent channel was analyzed using a validated computational fluid dynamics model to investigate (1) the comparison of single-phase and two-phase simulation, (2) the improved procedure of the prototype channel, and (3) the effect of the inflow rate on flow distribution. The results show that two-phase simulation is more reliable due to the description of the free-surface fluctuations. It should first be considered for improving flow distribution to prevent a short-circuit flow, and the difference in the kinetic energy with the inflow rate makes flow distribution trends different. The authors believe that this case study is helpful for improving flow distribution in an influent channel.

  9. 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.

  10. Computational strategies for three-dimensional flow simulations on distributed computer systems

    Science.gov (United States)

    Sankar, Lakshmi N.; Weed, Richard A.

    1995-08-01

    This research effort is directed towards an examination of issues involved in porting large computational fluid dynamics codes in use within the industry to a distributed computing environment. This effort addresses strategies for implementing the distributed computing in a device independent fashion and load balancing. A flow solver called TEAM presently in use at Lockheed Aeronautical Systems Company was acquired to start this effort. The following tasks were completed: (1) The TEAM code was ported to a number of distributed computing platforms including a cluster of HP workstations located in the School of Aerospace Engineering at Georgia Tech; a cluster of DEC Alpha Workstations in the Graphics visualization lab located at Georgia Tech; a cluster of SGI workstations located at NASA Ames Research Center; and an IBM SP-2 system located at NASA ARC. (2) A number of communication strategies were implemented. Specifically, the manager-worker strategy and the worker-worker strategy were tested. (3) A variety of load balancing strategies were investigated. Specifically, the static load balancing, task queue balancing and the Crutchfield algorithm were coded and evaluated. (4) The classical explicit Runge-Kutta scheme in the TEAM solver was replaced with an LU implicit scheme. And (5) the implicit TEAM-PVM solver was extensively validated through studies of unsteady transonic flow over an F-5 wing, undergoing combined bending and torsional motion. These investigations are documented in extensive detail in the dissertation, 'Computational Strategies for Three-Dimensional Flow Simulations on Distributed Computing Systems', enclosed as an appendix.

  11. Computational strategies for three-dimensional flow simulations on distributed computer systems

    Science.gov (United States)

    Sankar, Lakshmi N.; Weed, Richard A.

    1995-01-01

    This research effort is directed towards an examination of issues involved in porting large computational fluid dynamics codes in use within the industry to a distributed computing environment. This effort addresses strategies for implementing the distributed computing in a device independent fashion and load balancing. A flow solver called TEAM presently in use at Lockheed Aeronautical Systems Company was acquired to start this effort. The following tasks were completed: (1) The TEAM code was ported to a number of distributed computing platforms including a cluster of HP workstations located in the School of Aerospace Engineering at Georgia Tech; a cluster of DEC Alpha Workstations in the Graphics visualization lab located at Georgia Tech; a cluster of SGI workstations located at NASA Ames Research Center; and an IBM SP-2 system located at NASA ARC. (2) A number of communication strategies were implemented. Specifically, the manager-worker strategy and the worker-worker strategy were tested. (3) A variety of load balancing strategies were investigated. Specifically, the static load balancing, task queue balancing and the Crutchfield algorithm were coded and evaluated. (4) The classical explicit Runge-Kutta scheme in the TEAM solver was replaced with an LU implicit scheme. And (5) the implicit TEAM-PVM solver was extensively validated through studies of unsteady transonic flow over an F-5 wing, undergoing combined bending and torsional motion. These investigations are documented in extensive detail in the dissertation, 'Computational Strategies for Three-Dimensional Flow Simulations on Distributed Computing Systems', enclosed as an appendix.

  12. Pulmonary blood flow distribution measured by radionuclide computed tomography

    International Nuclear Information System (INIS)

    Maeda, H.; Itoh, H.; Ishii, Y.

    1982-01-01

    Distributions of pulmonary blood flow per unit lung volume were measured in sitting patients with a radionuclide computed tomography (RCT) by intravenously administered Tc-99m macroaggregates of human serum albumin (MAA). Four different types of distribution were distinguished, among which a group referred as type 2 had a three zonal blood flow distribution as previously reported (West and co-workers, 1964). The pulmonary arterial pressure (Pa) and the venous pressure (Pv) were determined in this group of distribution. These values showed satifactory agreements with the pulmonary artery pressure (Par) and the capillary wedged pressure (Pcw) measured by Swan-Ganz catheter in eighteen supine patients. Those good correlations enable to establish a noninvasive methodology for measurement of pulmonary vascular pressures

  13. Common accounting system for monitoring the ATLAS distributed computing resources

    International Nuclear Information System (INIS)

    Karavakis, E; Andreeva, J; Campana, S; Saiz, P; Gayazov, S; Jezequel, S; Sargsyan, L; Schovancova, J; Ueda, I

    2014-01-01

    This paper covers in detail a variety of accounting tools used to monitor the utilisation of the available computational and storage resources within the ATLAS Distributed Computing during the first three years of Large Hadron Collider data taking. The Experiment Dashboard provides a set of common accounting tools that combine monitoring information originating from many different information sources; either generic or ATLAS specific. This set of tools provides quality and scalable solutions that are flexible enough to support the constantly evolving requirements of the ATLAS user community.

  14. Memory

    Science.gov (United States)

    ... it has to decide what is worth remembering. Memory is the process of storing and then remembering this information. There are different types of memory. Short-term memory stores information for a few ...

  15. Distributed Database Access in the LHC Computing Grid with CORAL

    CERN Document Server

    Molnár, Z; Düllmann, D; Giacomo, G; Kalkhof, A; Valassi, A; CERN. Geneva. IT Department

    2009-01-01

    The CORAL package is the LCG Persistency Framework foundation for accessing relational databases. From the start CORAL has been designed to facilitate the deployment of the LHC experiment database applications in a distributed computing environment. In particular we cover - improvements to database service scalability by client connection management - platform-independent, multi-tier scalable database access by connection multiplexing, caching - a secure authentication and authorisation scheme integrated with existing grid services. We will summarize the deployment experience from several experiment productions using the distributed database infrastructure, which is now available in LCG. Finally, we present perspectives for future developments in this area.

  16. On the computation of momentum distributions within wavepacket propagation calculations

    International Nuclear Information System (INIS)

    Feuerstein, Bernold; Thumm, Uwe

    2003-01-01

    We present a new method to extract momentum distributions from time-dependent wavepacket calculations. In contrast to established Fourier transformation of the spatial wavepacket at a fixed time, the proposed 'virtual detector' method examines the time dependence of the wavepacket at a fixed position. In first applications to the ionization of model atoms and the dissociation of H 2 + , we find a significant reduction of computing time and are able to extract reliable fragment momentum distributions by using a comparatively small spatial numerical grid for the time-dependent wavefunction

  17. Radar data processing using a distributed computational system

    Science.gov (United States)

    Mota, Gilberto F.

    1992-06-01

    This research specifies and validates a new concurrent decomposition scheme, called Confined Space Search Decomposition (CSSD), to exploit parallelism of Radar Data Processing algorithms using a Distributed Computational System. To formalize the specification, we propose and apply an object-oriented methodology called Decomposition Cost Evaluation Model (DCEM). To reduce the penalties of load imbalance, we propose a distributed dynamic load balance heuristic called Object Reincarnation (OR). To validate the research, we first compare our decomposition with an identified alternative using the proposed DCEM model and then develop a theoretical prediction of selected parameters. We also develop a simulation to check the Object Reincarnation Concept.

  18. A highly efficient parallel algorithm for solving the neutron diffusion nodal equations on shared-memory computers

    International Nuclear Information System (INIS)

    Azmy, Y.Y.; Kirk, B.L.

    1990-01-01

    Modern parallel computer architectures offer an enormous potential for reducing CPU and wall-clock execution times of large-scale computations commonly performed in various applications in science and engineering. Recently, several authors have reported their efforts in developing and implementing parallel algorithms for solving the neutron diffusion equation on a variety of shared- and distributed-memory parallel computers. Testing of these algorithms for a variety of two- and three-dimensional meshes showed significant speedup of the computation. Even for very large problems (i.e., three-dimensional fine meshes) executed concurrently on a few nodes in serial (nonvector) mode, however, the measured computational efficiency is very low (40 to 86%). In this paper, the authors present a highly efficient (∼85 to 99.9%) algorithm for solving the two-dimensional nodal diffusion equations on the Sequent Balance 8000 parallel computer. Also presented is a model for the performance, represented by the efficiency, as a function of problem size and the number of participating processors. The model is validated through several tests and then extrapolated to larger problems and more processors to predict the performance of the algorithm in more computationally demanding situations

  19. ParBiBit: Parallel tool for binary biclustering on modern distributed-memory systems.

    Science.gov (United States)

    González-Domínguez, Jorge; Expósito, Roberto R

    2018-01-01

    Biclustering techniques are gaining attention in the analysis of large-scale datasets as they identify two-dimensional submatrices where both rows and columns are correlated. In this work we present ParBiBit, a parallel tool to accelerate the search of interesting biclusters on binary datasets, which are very popular on different fields such as genetics, marketing or text mining. It is based on the state-of-the-art sequential Java tool BiBit, which has been proved accurate by several studies, especially on scenarios that result on many large biclusters. ParBiBit uses the same methodology as BiBit (grouping the binary information into patterns) and provides the same results. Nevertheless, our tool significantly improves performance thanks to an efficient implementation based on C++11 that includes support for threads and MPI processes in order to exploit the compute capabilities of modern distributed-memory systems, which provide several multicore CPU nodes interconnected through a network. Our performance evaluation with 18 representative input datasets on two different eight-node systems shows that our tool is significantly faster than the original BiBit. Source code in C++ and MPI running on Linux systems as well as a reference manual are available at https://sourceforge.net/projects/parbibit/.

  20. 11th International Conference on Distributed Computing and Artificial Intelligence

    CERN Document Server

    Bersini, Hugues; Corchado, Juan; Rodríguez, Sara; Pawlewski, Paweł; Bucciarelli, Edgardo

    2014-01-01

    The 11th International Symposium on Distributed Computing and Artificial Intelligence 2014 (DCAI 2014) is a forum to present applications of innovative techniques for studying and solving complex problems. The exchange of ideas between scientists and technicians from both the academic and industrial sector is essential to facilitate the development of systems that can meet the ever-increasing demands of today’s society. The present edition brings together past experience, current work and promising future trends associated with distributed computing, artificial intelligence and their application in order to provide efficient solutions to real problems. This year’s technical program presents both high quality and diversity, with contributions in well-established and evolving areas of research (Algeria, Brazil, China, Croatia, Czech Republic, Denmark, France, Germany, Ireland, Italy, Japan, Malaysia, Mexico, Poland, Portugal, Republic of Korea, Spain, Taiwan, Tunisia, Ukraine, United Kingdom), representing ...

  1. The BaBar experiment's distributed computing model

    International Nuclear Information System (INIS)

    Boutigny, D.

    2001-01-01

    In order to face the expected increase in statistics between now and 2005, the BaBar experiment at SLAC is evolving its computing model toward a distributed multitier system. It is foreseen that data will be spread among Tier-A centers and deleted from the SLAC center. A uniform computing environment is being deployed in the centers, the network bandwidth is continuously increased and data distribution tools has been designed in order to reach a transfer rate of ∼100 TB of data per year. In parallel, smaller Tier-B and C sites receive subsets of data, presently in Kanga-ROOT format and later in Objectivity format. GRID tools will be used for remote job submission

  2. The BaBar Experiment's Distributed Computing Model

    International Nuclear Information System (INIS)

    Gowdy, Stephen J.

    2002-01-01

    In order to face the expected increase in statistics between now and 2005, the BaBar experiment at SLAC is evolving its computing model toward a distributed multi-tier system. It is foreseen that data will be spread among Tier-A centers and deleted from the SLAC center. A uniform computing environment is being deployed in the centers, the network bandwidth is continuously increased and data distribution tools has been designed in order to reach a transfer rate of ∼100 TB of data per year. In parallel, smaller Tier-B and C sites receive subsets of data, presently in Kanga-ROOT[1] format and later in Objectivity[2] format. GRID tools will be used for remote job submission

  3. Integrating Xgrid into the HENP distributed computing model

    International Nuclear Information System (INIS)

    Hajdu, L; Lauret, J; Kocoloski, A; Miller, M

    2008-01-01

    Modern Macintosh computers feature Xgrid, a distributed computing architecture built directly into Apple's OS X operating system. While the approach is radically different from those generally expected by the Unix based Grid infrastructures (Open Science Grid, TeraGrid, EGEE), opportunistic computing on Xgrid is nonetheless a tempting and novel way to assemble a computing cluster with a minimum of additional configuration. In fact, it requires only the default operating system and authentication to a central controller from each node. OS X also implements arbitrarily extensible metadata, allowing an instantly updated file catalog to be stored as part of the filesystem itself. The low barrier to entry allows an Xgrid cluster to grow quickly and organically. This paper and presentation will detail the steps that can be taken to make such a cluster a viable resource for HENP research computing. We will further show how to provide to users a unified job submission framework by integrating Xgrid through the STAR Unified Meta-Scheduler (SUMS), making tasks and jobs submission effortlessly at reach for those users already using the tool for traditional Grid or local cluster job submission. We will discuss additional steps that can be taken to make an Xgrid cluster a full partner in grid computing initiatives, focusing on Open Science Grid integration. MIT's Xgrid system currently supports the work of multiple research groups in the Laboratory for Nuclear Science, and has become an important tool for generating simulations and conducting data analyses at the Massachusetts Institute of Technology

  4. Integrating Xgrid into the HENP distributed computing model

    Science.gov (United States)

    Hajdu, L.; Kocoloski, A.; Lauret, J.; Miller, M.

    2008-07-01

    Modern Macintosh computers feature Xgrid, a distributed computing architecture built directly into Apple's OS X operating system. While the approach is radically different from those generally expected by the Unix based Grid infrastructures (Open Science Grid, TeraGrid, EGEE), opportunistic computing on Xgrid is nonetheless a tempting and novel way to assemble a computing cluster with a minimum of additional configuration. In fact, it requires only the default operating system and authentication to a central controller from each node. OS X also implements arbitrarily extensible metadata, allowing an instantly updated file catalog to be stored as part of the filesystem itself. The low barrier to entry allows an Xgrid cluster to grow quickly and organically. This paper and presentation will detail the steps that can be taken to make such a cluster a viable resource for HENP research computing. We will further show how to provide to users a unified job submission framework by integrating Xgrid through the STAR Unified Meta-Scheduler (SUMS), making tasks and jobs submission effortlessly at reach for those users already using the tool for traditional Grid or local cluster job submission. We will discuss additional steps that can be taken to make an Xgrid cluster a full partner in grid computing initiatives, focusing on Open Science Grid integration. MIT's Xgrid system currently supports the work of multiple research groups in the Laboratory for Nuclear Science, and has become an important tool for generating simulations and conducting data analyses at the Massachusetts Institute of Technology.

  5. Development of distributed computer systems for future nuclear power plants

    International Nuclear Information System (INIS)

    Yan, G.; L'Archeveque, J.V.R.

    1978-01-01

    Dual computers have been used for direct digital control in CANDU power reactors since 1963. However, as reactor plants have grown in size and complexity, some drawbacks to centralized control appear such as, for example, the surprisingly large amount of cabling required for information transmission. Dramatic changes in costs of components and a desire to improve system performance have stimulated a broad-based research and development effort in distribution systems. This paper outlines work in this area

  6. Brookhaven Reactor Experiment Control Facility, a distributed function computer network

    International Nuclear Information System (INIS)

    Dimmler, D.G.; Greenlaw, N.; Kelley, M.A.; Potter, D.W.; Rankowitz, S.; Stubblefield, F.W.

    1975-11-01

    A computer network for real-time data acquisition, monitoring and control of a series of experiments at the Brookhaven High Flux Beam Reactor has been developed and has been set into routine operation. This reactor experiment control facility presently services nine neutron spectrometers and one x-ray diffractometer. Several additional experiment connections are in progress. The architecture of the facility is based on a distributed function network concept. A statement of implementation and results is presented

  7. 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

  8. Distributed user interfaces for clinical ubiquitous computing applications.

    Science.gov (United States)

    Bång, Magnus; Larsson, Anders; Berglund, Erik; Eriksson, Henrik

    2005-08-01

    Ubiquitous computing with multiple interaction devices requires new interface models that support user-specific modifications to applications and facilitate the fast development of active workspaces. We have developed NOSTOS, a computer-augmented work environment for clinical personnel to explore new user interface paradigms for ubiquitous computing. NOSTOS uses several devices such as digital pens, an active desk, and walk-up displays that allow the system to track documents and activities in the workplace. We present the distributed user interface (DUI) model that allows standalone applications to distribute their user interface components to several devices dynamically at run-time. This mechanism permit clinicians to develop their own user interfaces and forms to clinical information systems to match their specific needs. We discuss the underlying technical concepts of DUIs and show how service discovery, component distribution, events and layout management are dealt with in the NOSTOS system. Our results suggest that DUIs--and similar network-based user interfaces--will be a prerequisite of future mobile user interfaces and essential to develop clinical multi-device environments.

  9. Computationally intensive econometrics using a distributed matrix-programming language.

    Science.gov (United States)

    Doornik, Jurgen A; Hendry, David F; Shephard, Neil

    2002-06-15

    This paper reviews the need for powerful computing facilities in econometrics, focusing on concrete problems which arise in financial economics and in macroeconomics. We argue that the profession is being held back by the lack of easy-to-use generic software which is able to exploit the availability of cheap clusters of distributed computers. Our response is to extend, in a number of directions, the well-known matrix-programming interpreted language Ox developed by the first author. We note three possible levels of extensions: (i) Ox with parallelization explicit in the Ox code; (ii) Ox with a parallelized run-time library; and (iii) Ox with a parallelized interpreter. This paper studies and implements the first case, emphasizing the need for deterministic computing in science. We give examples in the context of financial economics and time-series modelling.

  10. A Parallel and Distributed Surrogate Model Implementation for Computational Steering

    KAUST Repository

    Butnaru, Daniel

    2012-06-01

    Understanding the influence of multiple parameters in a complex simulation setting is a difficult task. In the ideal case, the scientist can freely steer such a simulation and is immediately presented with the results for a certain configuration of the input parameters. Such an exploration process is however not possible if the simulation is computationally too expensive. For these cases we present in this paper a scalable computational steering approach utilizing a fast surrogate model as substitute for the time-consuming simulation. The surrogate model we propose is based on the sparse grid technique, and we identify the main computational tasks associated with its evaluation and its extension. We further show how distributed data management combined with the specific use of accelerators allows us to approximate and deliver simulation results to a high-resolution visualization system in real-time. This significantly enhances the steering workflow and facilitates the interactive exploration of large datasets. © 2012 IEEE.

  11. Data Provenance for Agent-Based Models in a Distributed Memory

    Directory of Open Access Journals (Sweden)

    Delmar B. Davis

    2018-04-01

    Full Text Available Agent-Based Models (ABMs assist with studying emergent collective behavior of individual entities in social, biological, economic, network, and physical systems. Data provenance can support ABM by explaining individual agent behavior. However, there is no provenance support for ABMs in a distributed setting. The Multi-Agent Spatial Simulation (MASS library provides a framework for simulating ABMs at fine granularity, where agents and spatial data are shared application resources in a distributed memory. We introduce a novel approach to capture ABM provenance in a distributed memory, called ProvMASS. We evaluate our technique with traditional data provenance queries and performance measures. Our results indicate that a configurable approach can capture provenance that explains coordination of distributed shared resources, simulation logic, and agent behavior while limiting performance overhead. We also show the ability to support practical analyses (e.g., agent tracking and storage requirements for different capture configurations.

  12. Power profiling of Cholesky and QR factorizations on distributed memory systems

    KAUST Repository

    Bosilca, George

    2012-08-30

    This paper presents the power profile of two high performance dense linear algebra libraries on distributed memory systems, ScaLAPACK and DPLASMA. From the algorithmic perspective, their methodologies are opposite. The former is based on block algorithms and relies on multithreaded BLAS and a two-dimensional block cyclic data distribution to achieve high parallel performance. The latter is based on tile algorithms running on top of a tile data layout and uses fine-grained task parallelism combined with a dynamic distributed scheduler (DAGuE) to leverage distributed memory systems. We present performance results (Gflop/s) as well as the power profile (Watts) of two common dense factorizations needed to solve linear systems of equations, namely Cholesky and QR. The reported numbers show that DPLASMA surpasses ScaLAPACK not only in terms of performance (up to 2X speedup) but also in terms of energy efficiency (up to 62 %). © 2012 Springer-Verlag (outside the USA).

  13. Effects of Violent and Non-Violent Computer Game Content on Memory Performance in Adolescents

    Science.gov (United States)

    Maass, Asja; Kollhorster, Kirsten; Riediger, Annemarie; MacDonald, Vanessa; Lohaus, Arnold

    2011-01-01

    The present study focuses on the short-term effects of electronic entertainment media on memory and learning processes. It compares the effects of violent versus non-violent computer game content in a condition of playing and in another condition of watching the same game. The participants consisted of 83 female and 94 male adolescents with a mean…

  14. Computer Simulations of Developmental Change: The Contributions of Working Memory Capacity and Long-Term Knowledge

    Science.gov (United States)

    Jones, Gary; Gobet, Fernand; Pine, Julian M.

    2008-01-01

    Increasing working memory (WM) capacity is often cited as a major influence on children's development and yet WM capacity is difficult to examine independently of long-term knowledge. A computational model of children's nonword repetition (NWR) performance is presented that independently manipulates long-term knowledge and WM capacity to determine…

  15. The Effects of 3D Computer Simulation on Biology Students' Achievement and Memory Retention

    Science.gov (United States)

    Elangovan, Tavasuria; Ismail, Zurida

    2014-01-01

    A quasi experimental study was conducted for six weeks to determine the effectiveness of two different 3D computer simulation based teaching methods, that is, realistic simulation and non-realistic simulation on Form Four Biology students' achievement and memory retention in Perak, Malaysia. A sample of 136 Form Four Biology students in Perak,…

  16. Explicit time integration of finite element models on a vectorized, concurrent computer with shared memory

    Science.gov (United States)

    Gilbertsen, Noreen D.; Belytschko, Ted

    1990-01-01

    The implementation of a nonlinear explicit program on a vectorized, concurrent computer with shared memory is described and studied. The conflict between vectorization and concurrency is described and some guidelines are given for optimal block sizes. Several example problems are summarized to illustrate the types of speed-ups which can be achieved by reprogramming as compared to compiler optimization.

  17. Effect of Computer-Presented Organizational/Memory Aids on Problem Solving Behavior.

    Science.gov (United States)

    Steinberg, Esther R.; And Others

    This research studied the effects of computer-presented organizational/memory aids on problem solving behavior. The aids were either matrix or verbal charts shown on the display screen next to the problem. The 104 college student subjects were randomly assigned to one of the four conditions: type of chart (matrix or verbal chart) and use of charts…

  18. From shoebox to performative agent: the computer as personal memory machine

    NARCIS (Netherlands)

    van Dijck, J.

    2005-01-01

    Digital technologies offer new opportunities in the everyday lives of people: with still expanding memory capacities, the computer is rapidly becoming a giant storage and processing facility for recording and retrieving ‘bits of life’. Software engineers and companies promise not only to expand the

  19. Distributed computing testbed for a remote experimental environment

    International Nuclear Information System (INIS)

    Butner, D.N.; Casper, T.A.; Howard, B.C.; Henline, P.A.; Davis, S.L.; Barnes, D.

    1995-01-01

    Collaboration is increasing as physics research becomes concentrated on a few large, expensive facilities, particularly in magnetic fusion energy research, with national and international participation. These facilities are designed for steady state operation and interactive, real-time experimentation. We are developing tools to provide for the establishment of geographically distant centers for interactive operations; such centers would allow scientists to participate in experiments from their home institutions. A testbed is being developed for a Remote Experimental Environment (REE), a ''Collaboratory.'' The testbed will be used to evaluate the ability of a remotely located group of scientists to conduct research on the DIII-D Tokamak at General Atomics. The REE will serve as a testing environment for advanced control and collaboration concepts applicable to future experiments. Process-to-process communications over high speed wide area networks provide real-time synchronization and exchange of data among multiple computer networks, while the ability to conduct research is enhanced by adding audio/video communication capabilities. The Open Software Foundation's Distributed Computing Environment is being used to test concepts in distributed control, security, naming, remote procedure calls and distributed file access using the Distributed File Services. We are exploring the technology and sociology of remotely participating in the operation of a large scale experimental facility

  20. Extending and implementing the Self-adaptive Virtual Processor for distributed memory architectures

    NARCIS (Netherlands)

    van Tol, M.W.; Koivisto, J.

    2011-01-01

    Many-core architectures of the future are likely to have distributed memory organizations and need fine grained concurrency management to be used effectively. The Self-adaptive Virtual Processor (SVP) is an abstract concurrent programming model which can provide this, but the model and its current

  1. Learning to read aloud: A neural network approach using sparse distributed memory

    Science.gov (United States)

    Joglekar, Umesh Dwarkanath

    1989-01-01

    An attempt to solve a problem of text-to-phoneme mapping is described which does not appear amenable to solution by use of standard algorithmic procedures. Experiments based on a model of distributed processing are also described. This model (sparse distributed memory (SDM)) can be used in an iterative supervised learning mode to solve the problem. Additional improvements aimed at obtaining better performance are suggested.

  2. Multigrid solution of diffusion equations on distributed memory multiprocessor systems

    International Nuclear Information System (INIS)

    Finnemann, H.

    1988-01-01

    The subject is the solution of partial differential equations for simulation of the reactor core on high-performance computers. The parallelization and implementation of nodal multigrid diffusion algorithms on array and ring configurations of the DIRMU multiprocessor system is outlined. The particular iteration scheme employed in the nodal expansion method appears similarly efficient in serial and parallel environments. The combination of modern multi-level techniques with innovative hardware (vector-multiprocessor systems) provides powerful tools needed for real time simulation of physical systems. The parallel efficiencies range from 70 to 90%. The same performance is estimated for large problems on large multiprocessor systems being designed at present. (orig.) [de

  3. The use of fractal dimension calculation algorithm to determine the nature of autobiographical memories distribution across the life span

    Science.gov (United States)

    Mitina, Olga V.; Nourkova, Veronica V.

    In the given research we offer the technique for the calculation of the density of events which people retrieve from autobiographical memory. We wanted to prove a non-uniformity nature of memories distribution in the course of time and were interested with the law of distribution of these events during life course.

  4. Successful initiation of and management through a distributed computer upgrade

    International Nuclear Information System (INIS)

    Barich, F.T.; Crawford, T.H.

    1995-01-01

    Processing capacity, the lack of data analysis tools, obsolescence, and spare parts issues are forcing utilities to upgrade or replace their plant computer systems with newer, larger systems. As a result, the utility faces an increasing number of new technologies, such as fiber optics and communication standards (FDDI, ATM, etc.), Graphic User Interface using X-Windows, and distributed architectures that eliminate the host based computer. Technologies such as these, if properly applied, can greatly enhance the capabilities and functions of the existing system. Besides this, the utility also faces funtionality previously not available through the plant computer, such as integrated plant monitoring and digital controls, voice, imaging, etc. With computing technology vastly changing from traditional host systems, the utility confronts the question, open-quotes what are my needs (now and for the future), and what new system can meet those needs most effectively?close quotes. This paper describes the management process necessary to define the needs and then carry out a successful computer replacement project

  5. An ATLAS distributed computing architecture for HL-LHC

    CERN Document Server

    Campana, Simone; The ATLAS collaboration

    2017-01-01

    The ATLAS collaboration started a process to understand the computing needs for the High Luminosity LHC era. Based on our best understanding of the computing model input parameters for the HL-LHC data taking conditions, results indicate the need for a larger amount of computational and storage resources with respect of the projection of constant yearly budget for computing in 2026. Filling the gap between the projection and the needs will be one of the challenges in preparation for LHC Run-4. While the gains from improvements in offline software will play a crucial role in this process, a different model for data processing, management, access and bookkeeping should also be envisaged to optimise resource usage. In this contribution we will describe a straw man of this model, founded on basic principles such as single event level granularity for data processing and virtual data. We will explain how the current architecture will evolve adiabatically into the future distributed computing system, through the prot...

  6. Feature-Based Visual Short-Term Memory Is Widely Distributed and Hierarchically Organized.

    Science.gov (United States)

    Dotson, Nicholas M; Hoffman, Steven J; Goodell, Baldwin; Gray, Charles M

    2018-06-15

    Feature-based visual short-term memory is known to engage both sensory and association cortices. However, the extent of the participating circuit and the neural mechanisms underlying memory maintenance is still a matter of vigorous debate. To address these questions, we recorded neuronal activity from 42 cortical areas in monkeys performing a feature-based visual short-term memory task and an interleaved fixation task. We find that task-dependent differences in firing rates are widely distributed throughout the cortex, while stimulus-specific changes in firing rates are more restricted and hierarchically organized. We also show that microsaccades during the memory delay encode the stimuli held in memory and that units modulated by microsaccades are more likely to exhibit stimulus specificity, suggesting that eye movements contribute to visual short-term memory processes. These results support a framework in which most cortical areas, within a modality, contribute to mnemonic representations at timescales that increase along the cortical hierarchy. Copyright © 2018 Elsevier Inc. All rights reserved.

  7. Immigration, language proficiency, and autobiographical memories: Lifespan distribution and second-language access.

    Science.gov (United States)

    Esposito, Alena G; Baker-Ward, Lynne

    2016-08-01

    This investigation examined two controversies in the autobiographical literature: how cross-language immigration affects the distribution of autobiographical memories across the lifespan and under what circumstances language-dependent recall is observed. Both Spanish/English bilingual immigrants and English monolingual non-immigrants participated in a cue word study, with the bilingual sample taking part in a within-subject language manipulation. The expected bump in the number of memories from early life was observed for non-immigrants but not immigrants, who reported more memories for events surrounding immigration. Aspects of the methodology addressed possible reasons for past discrepant findings. Language-dependent recall was influenced by second-language proficiency. Results were interpreted as evidence that bilinguals with high second-language proficiency, in contrast to those with lower second-language proficiency, access a single conceptual store through either language. The final multi-level model predicting language-dependent recall, including second-language proficiency, age of immigration, internal language, and cue word language, explained ¾ of the between-person variance and (1)/5 of the within-person variance. We arrive at two conclusions. First, major life transitions influence the distribution of memories. Second, concept representation across multiple languages follows a developmental model. In addition, the results underscore the importance of considering language experience in research involving memory reports.

  8. Spin-wave interference patterns created by spin-torque nano-oscillators for memory and computation

    International Nuclear Information System (INIS)

    Macia, Ferran; Kent, Andrew D; Hoppensteadt, Frank C

    2011-01-01

    Magnetization dynamics in nanomagnets has attracted broad interest since it was predicted that a dc current flowing through a thin magnetic layer can create spin-wave excitations. These excitations are due to spin momentum transfer, a transfer of spin angular momentum between conduction electrons and the background magnetization, that enables new types of information processing. Here we show how arrays of spin-torque nano-oscillators can create propagating spin-wave interference patterns of use for memory and computation. Memristic transponders distributed on the thin film respond to threshold tunnel magnetoresistance values, thereby allowing spin-wave detection and creating new excitation patterns. We show how groups of transponders create resonant (reverberating) spin-wave interference patterns that may be used for polychronous wave computation and information storage.

  9. Mnemonic transmission, social contagion, and emergence of collective memory: Influence of emotional valence, group structure, and information distribution.

    Science.gov (United States)

    Choi, Hae-Yoon; Kensinger, Elizabeth A; Rajaram, Suparna

    2017-09-01

    Social transmission of memory and its consequence on collective memory have generated enduring interdisciplinary interest because of their widespread significance in interpersonal, sociocultural, and political arenas. We tested the influence of 3 key factors-emotional salience of information, group structure, and information distribution-on mnemonic transmission, social contagion, and collective memory. Participants individually studied emotionally salient (negative or positive) and nonemotional (neutral) picture-word pairs that were completely shared, partially shared, or unshared within participant triads, and then completed 3 consecutive recalls in 1 of 3 conditions: individual-individual-individual (control), collaborative-collaborative (identical group; insular structure)-individual, and collaborative-collaborative (reconfigured group; diverse structure)-individual. Collaboration enhanced negative memories especially in insular group structure and especially for shared information, and promoted collective forgetting of positive memories. Diverse group structure reduced this negativity effect. Unequally distributed information led to social contagion that creates false memories; diverse structure propagated a greater variety of false memories whereas insular structure promoted confidence in false recognition and false collective memory. A simultaneous assessment of network structure, information distribution, and emotional valence breaks new ground to specify how network structure shapes the spread of negative memories and false memories, and the emergence of collective memory. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  10. Optimizing NEURON Simulation Environment Using Remote Memory Access with Recursive Doubling on Distributed Memory Systems

    OpenAIRE

    Shehzad, Danish; Bozkuş, Zeki

    2016-01-01

    Increase in complexity of neuronal network models escalated the efforts to make NEURON simulation environment efficient. The computational neuroscientists divided the equations into subnets amongst multiple processors for achieving better hardware performance. On parallel machines for neuronal networks, interprocessor spikes exchange consumes large section of overall simulation time. In NEURON for communication between processors Message Passing Interface (MPI) is used. MPI_Allgather collecti...

  11. 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.

  12. Improving CMS data transfers among its distributed computing facilities

    CERN Document Server

    Flix, J; Sartirana, A

    2001-01-01

    CMS computing needs reliable, stable and fast connections among multi-tiered computing infrastructures. For data distribution, the CMS experiment relies on a data placement and transfer system, PhEDEx, managing replication operations at each site in the distribution network. PhEDEx uses the File Transfer Service (FTS), a low level data movement service responsible for moving sets of files from one site to another, while allowing participating sites to control the network resource usage. FTS servers are provided by Tier-0 and Tier-1 centres and are used by all computing sites in CMS, according to the established policy. FTS needs to be set up according to the Grid site's policies, and properly configured to satisfy the requirements of all Virtual Organizations making use of the Grid resources at the site. Managing the service efficiently requires good knowledge of the CMS needs for all kinds of transfer workflows. This contribution deals with a revision of FTS servers used by CMS, collecting statistics on thei...

  13. Improving CMS data transfers among its distributed computing facilities

    CERN Document Server

    Flix, Jose

    2010-01-01

    CMS computing needs reliable, stable and fast connections among multi-tiered computing infrastructures. For data distribution, the CMS experiment relies on a data placement and transfer system, PhEDEx, managing replication operations at each site in the distribution network. PhEDEx uses the File Transfer Service (FTS), a low level data movement service responsible for moving sets of files from one site to another, while allowing participating sites to control the network resource usage. FTS servers are provided by Tier-0 and Tier-1 centres and are used by all computing sites in CMS, according to the established policy. FTS needs to be set up according to the Grid site's policies, and properly configured to satisfy the requirements of all Virtual Organizations making use of the Grid resources at the site. Managing the service efficiently requires good knowledge of the CMS needs for all kinds of transfer workflows. This contribution deals with a revision of FTS servers used by CMS, collecting statistics on the...

  14. Improving CMS data transfers among its distributed computing facilities

    International Nuclear Information System (INIS)

    Flix, J; Magini, N; Sartirana, A

    2011-01-01

    CMS computing needs reliable, stable and fast connections among multi-tiered computing infrastructures. For data distribution, the CMS experiment relies on a data placement and transfer system, PhEDEx, managing replication operations at each site in the distribution network. PhEDEx uses the File Transfer Service (FTS), a low level data movement service responsible for moving sets of files from one site to another, while allowing participating sites to control the network resource usage. FTS servers are provided by Tier-0 and Tier-1 centres and are used by all computing sites in CMS, according to the established policy. FTS needs to be set up according to the Grid site's policies, and properly configured to satisfy the requirements of all Virtual Organizations making use of the Grid resources at the site. Managing the service efficiently requires good knowledge of the CMS needs for all kinds of transfer workflows. This contribution deals with a revision of FTS servers used by CMS, collecting statistics on their usage, customizing the topologies and improving their setup in order to keep CMS transferring data at the desired levels in a reliable and robust way.

  15. ATLAS Distributed Computing Monitoring tools during the LHC Run I

    Science.gov (United States)

    Schovancová, J.; Campana, S.; Di Girolamo, A.; Jézéquel, S.; Ueda, I.; Wenaus, T.; Atlas Collaboration

    2014-06-01

    This contribution summarizes evolution of the ATLAS Distributed Computing (ADC) Monitoring project during the LHC Run I. The ADC Monitoring targets at the three groups of customers: ADC Operations team to early identify malfunctions and escalate issues to an activity or a service expert, ATLAS national contacts and sites for the real-time monitoring and long-term measurement of the performance of the provided computing resources, and the ATLAS Management for long-term trends and accounting information about the ATLAS Distributed Computing resources. During the LHC Run I a significant development effort has been invested in standardization of the monitoring and accounting applications in order to provide extensive monitoring and accounting suite. ADC Monitoring applications separate the data layer and the visualization layer. The data layer exposes data in a predefined format. The visualization layer is designed bearing in mind visual identity of the provided graphical elements, and re-usability of the visualization bits across the different tools. A rich family of various filtering and searching options enhancing available user interfaces comes naturally with the data and visualization layer separation. With a variety of reliable monitoring data accessible through standardized interfaces, the possibility of automating actions under well defined conditions correlating multiple data sources has become feasible. In this contribution we discuss also about the automated exclusion of degraded resources and their automated recovery in various activities.

  16. Memory allocation and computations for Laplace’s equation of 3-D arbitrary boundary problems

    Directory of Open Access Journals (Sweden)

    Tsay Tswn-Syau

    2017-01-01

    Full Text Available Computation iteration schemes and memory allocation technique for finite difference method were presented in this paper. The transformed form of a groundwater flow problem in the generalized curvilinear coordinates was taken to be the illustrating example and a 3-dimensional second order accurate 19-point scheme was presented. Traditional element-by-element methods (e.g. SOR are preferred since it is simple and memory efficient but time consuming in computation. For efficient memory allocation, an index method was presented to store the sparse non-symmetric matrix of the problem. For computations, conjugate-gradient-like methods were reported to be computationally efficient. Among them, using incomplete Choleski decomposition as preconditioner was reported to be good method for iteration convergence. In general, the developed index method in this paper has the following advantages: (1 adaptable to various governing and boundary conditions, (2 flexible for higher order approximation, (3 independence of problem dimension, (4 efficient for complex problems when global matrix is not symmetric, (5 convenience for general sparse matrices, (6 computationally efficient in the most time consuming procedure of matrix multiplication, and (7 applicable to any developed matrix solver.

  17. Increasing efficiency of job execution with resource co-allocation in distributed computer systems

    OpenAIRE

    Cankar, Matija

    2014-01-01

    The field of distributed computer systems, while not new in computer science, is still the subject of a lot of interest in both industry and academia. More powerful computers, faster and more ubiquitous networks, and complex distributed applications are accelerating the growth of distributed computing. Large numbers of computers interconnected in a single network provide additional computing power to users whenever required. Such systems are, however, expensive and complex to manage, which ca...

  18. Integrating Xgrid into the HENP distributed computing model

    Energy Technology Data Exchange (ETDEWEB)

    Hajdu, L; Lauret, J [Brookhaven National Laboratory, Upton, NY 11973 (United States); Kocoloski, A; Miller, M [Department of Physics, Massachusetts Institute of Technology, Cambridge, MA 02139 (United States)], E-mail: kocolosk@mit.edu

    2008-07-15

    Modern Macintosh computers feature Xgrid, a distributed computing architecture built directly into Apple's OS X operating system. While the approach is radically different from those generally expected by the Unix based Grid infrastructures (Open Science Grid, TeraGrid, EGEE), opportunistic computing on Xgrid is nonetheless a tempting and novel way to assemble a computing cluster with a minimum of additional configuration. In fact, it requires only the default operating system and authentication to a central controller from each node. OS X also implements arbitrarily extensible metadata, allowing an instantly updated file catalog to be stored as part of the filesystem itself. The low barrier to entry allows an Xgrid cluster to grow quickly and organically. This paper and presentation will detail the steps that can be taken to make such a cluster a viable resource for HENP research computing. We will further show how to provide to users a unified job submission framework by integrating Xgrid through the STAR Unified Meta-Scheduler (SUMS), making tasks and jobs submission effortlessly at reach for those users already using the tool for traditional Grid or local cluster job submission. We will discuss additional steps that can be taken to make an Xgrid cluster a full partner in grid computing initiatives, focusing on Open Science Grid integration. MIT's Xgrid system currently supports the work of multiple research groups in the Laboratory for Nuclear Science, and has become an important tool for generating simulations and conducting data analyses at the Massachusetts Institute of Technology.

  19. Computational Fluid Dynamics (CFD) Computations With Zonal Navier-Stokes Flow Solver (ZNSFLOW) Common High Performance Computing Scalable Software Initiative (CHSSI) Software

    National Research Council Canada - National Science Library

    Edge, Harris

    1999-01-01

    ...), computational fluid dynamics (CFD) 6 project. Under the project, a proven zonal Navier-Stokes solver was rewritten for scalable parallel performance on both shared memory and distributed memory high performance computers...

  20. 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

  1. Computational scheme for transient temperature distribution in PWR vessel wall

    International Nuclear Information System (INIS)

    Dedovic, S.; Ristic, P.

    1980-01-01

    Computer code TEMPNES is a part of joint effort made in Gosa Industries in achieving the technique for structural analysis of heavy pressure vessels. Transient heat conduction problems analysis is based on finite element discretization of structures non-linear transient matrix formulation and time integration scheme as developed by Wilson (step-by-step procedure). Convection boundary conditions and the effect of heat generation due to radioactive radiation are both considered. The computation of transient temperature distributions in reactor vessel wall when the water temperature suddenly drops as a consequence of reactor cooling pump failure is presented. The vessel is treated as as axisymmetric body of revolution. The program has two finite time element options a) fixed predetermined increment and; b) an automatically optimized time increment for each step dependent on the rate of change of the nodal temperatures. (author)

  2. Storm blueprints patterns for distributed real-time computation

    CERN Document Server

    Goetz, P Taylor

    2014-01-01

    A blueprints book with 10 different projects built in 10 different chapters which demonstrate the various use cases of storm for both beginner and intermediate users, grounded in real-world example applications.Although the book focuses primarily on Java development with Storm, the patterns are more broadly applicable and the tips, techniques, and approaches described in the book apply to architects, developers, and operations.Additionally, the book should provoke and inspire applications of distributed computing to other industries and domains. Hadoop enthusiasts will also find this book a go

  3. Scalable error correction in distributed ion trap computers

    International Nuclear Information System (INIS)

    Oi, Daniel K. L.; Devitt, Simon J.; Hollenberg, Lloyd C. L.

    2006-01-01

    A major challenge for quantum computation in ion trap systems is scalable integration of error correction and fault tolerance. We analyze a distributed architecture with rapid high-fidelity local control within nodes and entangled links between nodes alleviating long-distance transport. We demonstrate fault-tolerant operator measurements which are used for error correction and nonlocal gates. This scheme is readily applied to linear ion traps which cannot be scaled up beyond a few ions per individual trap but which have access to a probabilistic entanglement mechanism. A proof-of-concept system is presented which is within the reach of current experiment

  4. Job monitoring on DIRAC for Belle II distributed computing

    Science.gov (United States)

    Kato, Yuji; Hayasaka, Kiyoshi; Hara, Takanori; Miyake, Hideki; Ueda, Ikuo

    2015-12-01

    We developed a monitoring system for Belle II distributed computing, which consists of active and passive methods. In this paper we describe the passive monitoring system, where information stored in the DIRAC database is processed and visualized. We divide the DIRAC workload management flow into steps and store characteristic variables which indicate issues. These variables are chosen carefully based on our experiences, then visualized. As a result, we are able to effectively detect issues. Finally, we discuss the future development for automating log analysis, notification of issues, and disabling problematic sites.

  5. Enabling Computational Dynamics in Distributed Computing Environments Using a Heterogeneous Computing Template

    Science.gov (United States)

    2011-08-09

    heterogeneous computing concept advertised recently as the paradigm capable of delivering exascale flop rates by the end of the decade. In this framework...and Lamb. Page 10 of 10 UNCLASSIFIED [3] Skaugen, K., Petascale to Exascale : Extending Intel’s HPC Commitment: http://download.intel.com

  6. A data base for on-line event analysis on a distributed memory machine

    International Nuclear Information System (INIS)

    Argante, E.; Meesters, M.R.J.; Willers, I.; Stok, P. van der

    1996-01-01

    Parallel in-memory databases can enhance the structuring and parallelization of programs used in High Energy Physics (HEP). Efficient database access routines are used as communication primitives which hide the communication topology in contrast to the more explicit communications like PVM or MPI. A parallel in-memory database, called SPIDER, has been implemented on a 32 node Meiko CS-2 distributed memory machine. The SPIDER primitives generate a lower overhead than the one generated by PVM or MPI. The even reconstruction program, CPREAD, of the CLEAR experiment, has been used as test case. Performance measurements showed that CPREAD interfaced to SPIDER can easily cope with the event rate generated by CPLEAR. (author)

  7. Investigating Solution Convergence in a Global Ocean Model Using a 2048-Processor Cluster of Distributed Shared Memory Machines

    Directory of Open Access Journals (Sweden)

    Chris Hill

    2007-01-01

    Full Text Available Up to 1920 processors of a cluster of distributed shared memory machines at the NASA Ames Research Center are being used to simulate ocean circulation globally at horizontal resolutions of 1/4, 1/8, and 1/16-degree with the Massachusetts Institute of Technology General Circulation Model, a finite volume code that can scale to large numbers of processors. The study aims to understand physical processes responsible for skill improvements as resolution is increased and to gain insight into what resolution is sufficient for particular purposes. This paper focuses on the computational aspects of reaching the technical objective of efficiently performing these global eddy-resolving ocean simulations. At 1/16-degree resolution the model grid contains 1.2 billion cells. At this resolution it is possible to simulate approximately one month of ocean dynamics in about 17 hours of wallclock time with a model timestep of two minutes on a cluster of four 512-way NUMA Altix systems. The Altix systems' large main memory and I/O subsystems allow computation and disk storage of rich sets of diagnostics during each integration, supporting the scientific objective to develop a better understanding of global ocean circulation model solution convergence as model resolution is increased.

  8. Fencing direct memory access data transfers in a parallel active messaging interface of a parallel computer

    Science.gov (United States)

    Blocksome, Michael A.; Mamidala, Amith R.

    2013-09-03

    Fencing direct memory access (`DMA`) data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including specifications of a client, a context, and a task, the endpoints coupled for data communications through the PAMI and through DMA controllers operatively coupled to segments of shared random access memory through which the DMA controllers deliver data communications deterministically, including initiating execution through the PAMI of an ordered sequence of active DMA instructions for DMA data transfers between two endpoints, effecting deterministic DMA data transfers through a DMA controller and a segment of shared memory; and executing through the PAMI, with no FENCE accounting for DMA data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all DMA instructions initiated prior to execution of the FENCE instruction for DMA data transfers between the two endpoints.

  9. KeyWare: an open wireless distributed computing environment

    Science.gov (United States)

    Shpantzer, Isaac; Schoenfeld, Larry; Grindahl, Merv; Kelman, Vladimir

    1995-12-01

    Deployment of distributed applications in the wireless domain lack equivalent tools, methodologies, architectures, and network management that exist in LAN based applications. A wireless distributed computing environment (KeyWareTM) based on intelligent agents within a multiple client multiple server scheme was developed to resolve this problem. KeyWare renders concurrent application services to wireline and wireless client nodes encapsulated in multiple paradigms such as message delivery, database access, e-mail, and file transfer. These services and paradigms are optimized to cope with temporal and spatial radio coverage, high latency, limited throughput and transmission costs. A unified network management paradigm for both wireless and wireline facilitates seamless extensions of LAN- based management tools to include wireless nodes. A set of object oriented tools and methodologies enables direct asynchronous invocation of agent-based services supplemented by tool-sets matched to supported KeyWare paradigms. The open architecture embodiment of KeyWare enables a wide selection of client node computing platforms, operating systems, transport protocols, radio modems and infrastructures while maintaining application portability.

  10. DISTRIBUTED GENERATION OF COMPUTER MUSIC IN THE INTERNET OF THINGS

    Directory of Open Access Journals (Sweden)

    G. G. Rogozinsky

    2015-07-01

    Full Text Available Problem Statement. The paper deals with distributed intelligent multi-agent system for computer music generation. A mathematical model for data extraction from the environment and their application in the music generation process is proposed. Methods. We use Resource Description Framework for representation of timbre data. A special musical programming language Csound is used for subsystem of synthesis and sound processing. Sound generation occurs according to the parameters of compositional model, getting data from the outworld. Results. We propose architecture of a potential distributed system for computer music generation. An example of core sound synthesis is presented. We also propose a method for mapping real world parameters to the plane of compositional model, in an attempt to imitate elements and aspects of creative inspiration. Music generation system has been represented as an artifact in the Central Museum of Communication n.a. A.S. Popov in the framework of «Night of Museums» action. In the course of public experiment it was stated that, in the whole, the system tends to a quick settling of neutral state with no musical events generation. This proves the necessity of algorithms design for active condition support of agents’ network, in the whole. Practical Relevance. Realization of the proposed system will give the possibility for creation of a technological platform for a whole new class of applications, including augmented acoustic reality and algorithmic composition.

  11. 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.

  12. The reminiscence bump without memories: The distribution of imagined word-cued and important autobiographical memories in a hypothetical 70-year-old.

    Science.gov (United States)

    Koppel, Jonathan; Berntsen, Dorthe

    2016-08-01

    The reminiscence bump is the disproportionate number of autobiographical memories dating from adolescence and early adulthood. It has often been ascribed to a consolidation of the mature self in the period covered by the bump. Here we stripped away factors relating to the characteristics of autobiographical memories per se, most notably factors that aid in their encoding or retention, by asking students to generate imagined word-cued and imagined 'most important' autobiographical memories of a hypothetical, prototypical 70-year-old of their own culture and gender. We compared the distribution of these fictional memories with the distributions of actual word-cued and most important autobiographical memories in a sample of 61-70-year-olds. We found a striking similarity between the temporal distributions of the imagined memories and the actual memories. These results suggest that the reminiscence bump is largely driven by constructive, schematic factors at retrieval, thereby challenging most existing theoretical accounts. Copyright © 2016 Elsevier Inc. All rights reserved.

  13. Computational cost estimates for parallel shared memory isogeometric multi-frontal solvers

    KAUST Repository

    Woźniak, Maciej

    2014-06-01

    In this paper we present computational cost estimates for parallel shared memory isogeometric multi-frontal solvers. The estimates show that the ideal isogeometric shared memory parallel direct solver scales as O( p2log(N/p)) for one dimensional problems, O(Np2) for two dimensional problems, and O(N4/3p2) for three dimensional problems, where N is the number of degrees of freedom, and p is the polynomial order of approximation. The computational costs of the shared memory parallel isogeometric direct solver are compared with those corresponding to the sequential isogeometric direct solver, being the latest equal to O(N p2) for the one dimensional case, O(N1.5p3) for the two dimensional case, and O(N2p3) for the three dimensional case. The shared memory version significantly reduces both the scalability in terms of N and p. Theoretical estimates are compared with numerical experiments performed with linear, quadratic, cubic, quartic, and quintic B-splines, in one and two spatial dimensions. © 2014 Elsevier Ltd. All rights reserved.

  14. Computational cost estimates for parallel shared memory isogeometric multi-frontal solvers

    KAUST Repository

    Woźniak, Maciej; Kuźnik, Krzysztof M.; Paszyński, Maciej R.; Calo, Victor M.; Pardo, D.

    2014-01-01

    In this paper we present computational cost estimates for parallel shared memory isogeometric multi-frontal solvers. The estimates show that the ideal isogeometric shared memory parallel direct solver scales as O( p2log(N/p)) for one dimensional problems, O(Np2) for two dimensional problems, and O(N4/3p2) for three dimensional problems, where N is the number of degrees of freedom, and p is the polynomial order of approximation. The computational costs of the shared memory parallel isogeometric direct solver are compared with those corresponding to the sequential isogeometric direct solver, being the latest equal to O(N p2) for the one dimensional case, O(N1.5p3) for the two dimensional case, and O(N2p3) for the three dimensional case. The shared memory version significantly reduces both the scalability in terms of N and p. Theoretical estimates are compared with numerical experiments performed with linear, quadratic, cubic, quartic, and quintic B-splines, in one and two spatial dimensions. © 2014 Elsevier Ltd. All rights reserved.

  15. Distributing the computation in combinatorial optimization experiments over the cloud

    Directory of Open Access Journals (Sweden)

    Mario Brcic

    2017-12-01

    Full Text Available Combinatorial optimization is an area of great importance since many of the real-world problems have discrete parameters which are part of the objective function to be optimized. Development of combinatorial optimization algorithms is guided by the empirical study of the candidate ideas and their performance over a wide range of settings or scenarios to infer general conclusions. Number of scenarios can be overwhelming, especially when modeling uncertainty in some of the problem’s parameters. Since the process is also iterative and many ideas and hypotheses may be tested, execution time of each experiment has an important role in the efficiency and successfulness. Structure of such experiments allows for significant execution time improvement by distributing the computation. We focus on the cloud computing as a cost-efficient solution in these circumstances. In this paper we present a system for validating and comparing stochastic combinatorial optimization algorithms. The system also deals with selection of the optimal settings for computational nodes and number of nodes in terms of performance-cost tradeoff. We present applications of the system on a new class of project scheduling problem. We show that we can optimize the selection over cloud service providers as one of the settings and, according to the model, it resulted in a substantial cost-savings while meeting the deadline.

  16. A QDWH-Based SVD Software Framework on Distributed-Memory Manycore Systems

    KAUST Repository

    Sukkari, Dalal; Ltaief, Hatem; Esposito, Aniello; Keyes, David E.

    2017-01-01

    , the inherent high level of concurrency associated with Level 3 BLAS compute-bound kernels ultimately compensates for the arithmetic complexity overhead. Using the ScaLAPACK two-dimensional block cyclic data distribution with a rectangular processor topology

  17. Exploiting short-term memory in soft body dynamics as a computational resource.

    Science.gov (United States)

    Nakajima, K; Li, T; Hauser, H; Pfeifer, R

    2014-11-06

    Soft materials are not only highly deformable, but they also possess rich and diverse body dynamics. Soft body dynamics exhibit a variety of properties, including nonlinearity, elasticity and potentially infinitely many degrees of freedom. Here, we demonstrate that such soft body dynamics can be employed to conduct certain types of computation. Using body dynamics generated from a soft silicone arm, we show that they can be exploited to emulate functions that require memory and to embed robust closed-loop control into the arm. Our results suggest that soft body dynamics have a short-term memory and can serve as a computational resource. This finding paves the way towards exploiting passive body dynamics for control of a large class of underactuated systems. © 2014 The Author(s) Published by the Royal Society. All rights reserved.

  18. Pervasive Computing, Privacy and Distribution of the Self

    Directory of Open Access Journals (Sweden)

    Soraj Hongladarom

    2011-05-01

    Full Text Available The emergence of what is commonly known as “ambient intelligence” or “ubiquitous computing” means that our conception of privacy and trust needs to be reconsidered. Many have voiced their concerns about the threat to privacy and the more prominent role of trust that have been brought about by emerging technologies. In this paper, I will present an investigation of what this means for the self and identity in our ambient intelligence environment. Since information about oneself can be actively distributed and processed, it is proposed that in a significant sense it is the self itself that is distributed throughout a pervasive or ubiquitous computing network when information pertaining to the self of the individual travels through the network. Hence privacy protection needs to be extended to all types of information distributed. It is also recommended that appropriately strong legislation on privacy and data protection regarding this pervasive network is necessary, but at present not sufficient, to ensure public trust. What is needed is a campaign on public awareness and positive perception of the technology.

  19. Capacity for patterns and sequences in Kanerva's SDM as compared to other associative memory models. [Sparse, Distributed Memory

    Science.gov (United States)

    Keeler, James D.

    1988-01-01

    The information capacity of Kanerva's Sparse Distributed Memory (SDM) and Hopfield-type neural networks is investigated. Under the approximations used here, it is shown that the total information stored in these systems is proportional to the number connections in the network. The proportionality constant is the same for the SDM and Hopfield-type models independent of the particular model, or the order of the model. The approximations are checked numerically. This same analysis can be used to show that the SDM can store sequences of spatiotemporal patterns, and the addition of time-delayed connections allows the retrieval of context dependent temporal patterns. A minor modification of the SDM can be used to store correlated patterns.

  20. Immigration, Language Proficiency, and Autobiographical Memories: Lifespan Distribution and Second-Language Access

    OpenAIRE

    Esposito, Alena G.; Baker-Ward, Lynne

    2015-01-01

    This investigation examined two controversies in the autobiographical literature: how cross-language immigration affects the distribution of autobiographical memories across the lifespan and under what circumstances language-dependent recall is observed. Both Spanish/English bilingual immigrants and English monolingual non-immigrants participated in a cue word study, with the bilingual sample taking part in a within-subject language manipulation. The expected bump in the num...

  1. Classification of bacterial contamination using image processing and distributed computing.

    Science.gov (United States)

    Ahmed, W M; Bayraktar, B; Bhunia, A; Hirleman, E D; Robinson, J P; Rajwa, B

    2013-01-01

    Disease outbreaks due to contaminated food are a major concern not only for the food-processing industry but also for the public at large. Techniques for automated detection and classification of microorganisms can be a great help in preventing outbreaks and maintaining the safety of the nations food supply. Identification and classification of foodborne pathogens using colony scatter patterns is a promising new label-free technique that utilizes image-analysis and machine-learning tools. However, the feature-extraction tools employed for this approach are computationally complex, and choosing the right combination of scatter-related features requires extensive testing with different feature combinations. In the presented work we used computer clusters to speed up the feature-extraction process, which enables us to analyze the contribution of different scatter-based features to the overall classification accuracy. A set of 1000 scatter patterns representing ten different bacterial strains was used. Zernike and Chebyshev moments as well as Haralick texture features were computed from the available light-scatter patterns. The most promising features were first selected using Fishers discriminant analysis, and subsequently a support-vector-machine (SVM) classifier with a linear kernel was used. With extensive testing we were able to identify a small subset of features that produced the desired results in terms of classification accuracy and execution speed. The use of distributed computing for scatter-pattern analysis, feature extraction, and selection provides a feasible mechanism for large-scale deployment of a light scatter-based approach to bacterial classification.

  2. Computational Modeling of Shape Memory Polymer Origami that Responds to Light

    Science.gov (United States)

    Mailen, Russell William

    Shape memory polymers (SMPs) transform in response to external stimuli, such as infrared (IR) light. Although SMPs have many applications, this investigation focuses on their use as actuators in self-folding origami structures. Ink patterned on the surface of the SMP sheet absorbs thermal energy from the IR light, which produces localized heating. The material shrinks wherever the activation temperature is exceeded and can produce out-of-plane deformation. The time and temperature dependent response of these SMPs provides unique opportunities for developing complex three-dimensional (3D) structures from initially flat sheets through self-folding origami, but the application of this technique requires predicting accurately the final folded or deformed shape. Furthermore, current computational approaches for SMPs do not fully couple the thermo-mechanical response of the material. Hence, a proposed nonlinear, 3D, thermo-viscoelastic finite element framework was formulated to predict deformed shapes for different self-folding systems and compared to experimental results for self-folding origami structures. A detailed understanding of the shape memory response and the effect of controllable design parameters, such as the ink pattern, pre-strain conditions, and applied thermal and mechanical fields, allows for a predictive understanding and design of functional, 3D structures. The proposed modeling framework was used to obtain a fundamental understanding of the thermo-mechanical behavior of SMPs and the impact of the material behavior on hinged self-folding. These predictions indicated how the thermal and mechanical conditions during pre-strain significantly affect the shrinking and folding response of the SMP. Additionally, the externally applied thermal loads significantly influenced the folding rate and maximum bending angle. The computational framework was also adapted to understand the effects of fully coupling the thermal and mechanical response of the material

  3. Novel spintronics devices for memory and logic: prospects and challenges for room temperature all spin computing

    Science.gov (United States)

    Wang, Jian-Ping

    An energy efficient memory and logic device for the post-CMOS era has been the goal of a variety of research fields. The limits of scaling, which we expect to reach by the year 2025, demand that future advances in computational power will not be realized from ever-shrinking device sizes, but rather by innovative designs and new materials and physics. Magnetoresistive based devices have been a promising candidate for future integrated magnetic computation because of its unique non-volatility and functionalities. The application of perpendicular magnetic anisotropy for potential STT-RAM application was demonstrated and later has been intensively investigated by both academia and industry groups, but there is no clear path way how scaling will eventually work for both memory and logic applications. One of main reasons is that there is no demonstrated material stack candidate that could lead to a scaling scheme down to sub 10 nm. Another challenge for the usage of magnetoresistive based devices for logic application is its available switching speed and writing energy. Although a good progress has been made to demonstrate the fast switching of a thermally stable magnetic tunnel junction (MTJ) down to 165 ps, it is still several times slower than its CMOS counterpart. In this talk, I will review the recent progress by my research group and my C-SPIN colleagues, then discuss the opportunities, challenges and some potential path ways for magnetoresitive based devices for memory and logic applications and their integration for room temperature all spin computing system.

  4. PREFACE: Special section on Computational Fluid Dynamics—in memory of Professor Kunio Kuwahara Special section on Computational Fluid Dynamics—in memory of Professor Kunio Kuwahara

    Science.gov (United States)

    Ishii, Katsuya

    2011-08-01

    This issue includes a special section on computational fluid dynamics (CFD) in memory of the late Professor Kunio Kuwahara, who passed away on 15 September 2008, at the age of 66. In this special section, five articles are included that are based on the lectures and discussions at `The 7th International Nobeyama Workshop on CFD: To the Memory of Professor Kuwahara' held in Tokyo on 23 and 24 September 2009. Professor Kuwahara started his research in fluid dynamics under Professor Imai at the University of Tokyo. His first paper was published in 1969 with the title 'Steady Viscous Flow within Circular Boundary', with Professor Imai. In this paper, he combined theoretical and numerical methods in fluid dynamics. Since that time, he made significant and seminal contributions to computational fluid dynamics. He undertook pioneering numerical studies on the vortex method in 1970s. From then to the early nineties, he developed numerical analyses on a variety of three-dimensional unsteady phenomena of incompressible and compressible fluid flows and/or complex fluid flows using his own supercomputers with academic and industrial co-workers and members of his private research institute, ICFD in Tokyo. In addition, a number of senior and young researchers of fluid mechanics around the world were invited to ICFD and the Nobeyama workshops, which were held near his villa, and they intensively discussed new frontier problems of fluid physics and fluid engineering at Professor Kuwahara's kind hospitality. At the memorial Nobeyama workshop held in 2009, 24 overseas speakers presented their papers, including the talks of Dr J P Boris (Naval Research Laboratory), Dr E S Oran (Naval Research Laboratory), Professor Z J Wang (Iowa State University), Dr M Meinke (RWTH Aachen), Professor K Ghia (University of Cincinnati), Professor U Ghia (University of Cincinnati), Professor F Hussain (University of Houston), Professor M Farge (École Normale Superieure), Professor J Y Yong (National

  5. System of common usage on the base of external memory devices and the SM-3 computer

    International Nuclear Information System (INIS)

    Baluka, G.; Vasin, A.Yu.; Ermakov, V.A.; Zhukov, G.P.; Zimin, G.N.; Namsraj, Yu.; Ostrovnoj, A.I.; Savvateev, A.S.; Salamatin, I.M.; Yanovskij, G.Ya.

    1980-01-01

    An easily modified system of common usage on the base of external memories and a SM-3 minicomputer replacing some pulse analysers is described. The system has merits of PA and is more advantageous with regard to effectiveness of equipment using, the possibility of changing configuration and functions, the data protection against losses due to user errors and some failures, price of one registration channel, place occupied. The system of common usage is intended for the IBR-2 pulse reactor computing centre. It is designed using the SANPO system means for SM-3 computer [ru

  6. 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

  7. More than a filter: Feature-based attention regulates the distribution of visual working memory resources.

    Science.gov (United States)

    Dube, Blaire; Emrich, Stephen M; Al-Aidroos, Naseem

    2017-10-01

    Across 2 experiments we revisited the filter account of how feature-based attention regulates visual working memory (VWM). Originally drawing from discrete-capacity ("slot") models, the filter account proposes that attention operates like the "bouncer in the brain," preventing distracting information from being encoded so that VWM resources are reserved for relevant information. Given recent challenges to the assumptions of discrete-capacity models, we investigated whether feature-based attention plays a broader role in regulating memory. Both experiments used partial report tasks in which participants memorized the colors of circle and square stimuli, and we provided a feature-based goal by manipulating the likelihood that 1 shape would be probed over the other across a range of probabilities. By decomposing participants' responses using mixture and variable-precision models, we estimated the contributions of guesses, nontarget responses, and imprecise memory representations to their errors. Consistent with the filter account, participants were less likely to guess when the probed memory item matched the feature-based goal. Interestingly, this effect varied with goal strength, even across high probabilities where goal-matching information should always be prioritized, demonstrating strategic control over filter strength. Beyond this effect of attention on which stimuli were encoded, we also observed effects on how they were encoded: Estimates of both memory precision and nontarget errors varied continuously with feature-based attention. The results offer support for an extension to the filter account, where feature-based attention dynamically regulates the distribution of resources within working memory so that the most relevant items are encoded with the greatest precision. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

  8. Global asymptotic stability analysis of bidirectional associative memory neural networks with distributed delays and impulse

    International Nuclear Information System (INIS)

    Huang Zaitang; Luo Xiaoshu; Yang Qigui

    2007-01-01

    Many systems existing in physics, chemistry, biology, engineering and information science can be characterized by impulsive dynamics caused by abrupt jumps at certain instants during the process. These complex dynamical behaviors can be model by impulsive differential system or impulsive neural networks. This paper formulates and studies a new model of impulsive bidirectional associative memory (BAM) networks with finite distributed delays. Several fundamental issues, such as global asymptotic stability and existence and uniqueness of such BAM neural networks with impulse and distributed delays, are established

  9. A learnable parallel processing architecture towards unity of memory and computing.

    Science.gov (United States)

    Li, H; Gao, B; Chen, Z; Zhao, Y; Huang, P; Ye, H; Liu, L; Liu, X; Kang, J

    2015-08-14

    Developing energy-efficient parallel information processing systems beyond von Neumann architecture is a long-standing goal of modern information technologies. The widely used von Neumann computer architecture separates memory and computing units, which leads to energy-hungry data movement when computers work. In order to meet the need of efficient information processing for the data-driven applications such as big data and Internet of Things, an energy-efficient processing architecture beyond von Neumann is critical for the information society. Here we show a non-von Neumann architecture built of resistive switching (RS) devices named "iMemComp", where memory and logic are unified with single-type devices. Leveraging nonvolatile nature and structural parallelism of crossbar RS arrays, we have equipped "iMemComp" with capabilities of computing in parallel and learning user-defined logic functions for large-scale information processing tasks. Such architecture eliminates the energy-hungry data movement in von Neumann computers. Compared with contemporary silicon technology, adder circuits based on "iMemComp" can improve the speed by 76.8% and the power dissipation by 60.3%, together with a 700 times aggressive reduction in the circuit area.

  10. A learnable parallel processing architecture towards unity of memory and computing

    Science.gov (United States)

    Li, H.; Gao, B.; Chen, Z.; Zhao, Y.; Huang, P.; Ye, H.; Liu, L.; Liu, X.; Kang, J.

    2015-08-01

    Developing energy-efficient parallel information processing systems beyond von Neumann architecture is a long-standing goal of modern information technologies. The widely used von Neumann computer architecture separates memory and computing units, which leads to energy-hungry data movement when computers work. In order to meet the need of efficient information processing for the data-driven applications such as big data and Internet of Things, an energy-efficient processing architecture beyond von Neumann is critical for the information society. Here we show a non-von Neumann architecture built of resistive switching (RS) devices named “iMemComp”, where memory and logic are unified with single-type devices. Leveraging nonvolatile nature and structural parallelism of crossbar RS arrays, we have equipped “iMemComp” with capabilities of computing in parallel and learning user-defined logic functions for large-scale information processing tasks. Such architecture eliminates the energy-hungry data movement in von Neumann computers. Compared with contemporary silicon technology, adder circuits based on “iMemComp” can improve the speed by 76.8% and the power dissipation by 60.3%, together with a 700 times aggressive reduction in the circuit area.

  11. Patterns of particle distribution in multiparticle systems by random walks with memory enhancement and decay

    Science.gov (United States)

    Tan, Zhi-Jie; Zou, Xian-Wu; Huang, Sheng-You; Zhang, Wei; Jin, Zhun-Zhi

    2002-07-01

    We investigate the pattern of particle distribution and its evolution with time in multiparticle systems using the model of random walks with memory enhancement and decay. This model describes some biological intelligent walks. With decrease in the memory decay exponent α, the distribution of particles changes from a random dispersive pattern to a locally dense one, and then returns to the random one. Correspondingly, the fractal dimension Df,p characterizing the distribution of particle positions increases from a low value to a maximum and then decreases to the low one again. This is determined by the degree of overlap of regions consisting of sites with remanent information. The second moment of the density ρ(2) was introduced to investigate the inhomogeneity of the particle distribution. The dependence of ρ(2) on α is similar to that of Df,p on α. ρ(2) increases with time as a power law in the process of adjusting the particle distribution, and then ρ(2) tends to a stable equilibrium value.

  12. Distributed Monitoring Infrastructure for Worldwide LHC Computing Grid

    CERN Document Server

    Andrade, Pedro; Bhatt, Kislay; Chand, Phool; Collados, David; Duggal, Vibhuti; Fuente, Paloma; Hayashi, Soichi; Imamagic, Emir; Joshi, Pradyumna; Kalmady, Rajesh; Karnani, Urvashi; Kumar, Vaibhav; Lapka, Wojciech; Quick, Robert; Tarragon, Jacobo; Teige, Scott; Triantafyllidis, Christos

    2012-01-01

    The journey of a monitoring probe from its development phase to the moment its execution result is presented in an availability report is a complex process. It goes through multiple phases such as development, testing, integration, release, deployment, execution, data aggregation, computation, and reporting. Further, it involves people with different roles (developers, site managers, VO managers, service managers, management), from different middleware providers (ARC, dCache, gLite, UNICORE and VDT), consortiums (WLCG, EMI, EGI, OSG), and operational teams (GOC, OMB, OTAG, CSIRT). The seamless harmonization of these distributed actors is in daily use for monitoring of the WLCG infrastructure. In this paper we describe the monitoring of the WLCG infrastructure from the operational perspective. We explain the complexity of the journey of a monitoring probe from its execution on a grid node to the visualization on the MyWLCG portal where it is exposed to other clients. This monitoring workflow profits from the i...

  13. 13th International Conference on Distributed Computing and Artificial Intelligence

    CERN Document Server

    Silvestri, Marcello; González, Sara

    2016-01-01

    The special session Decision Economics (DECON) 2016 is a scientific forum by which to share ideas, projects, researches results, models and experiences associated with the complexity of behavioral decision processes aiming at explaining socio-economic phenomena. DECON 2016 held in the University of Seville, Spain, as part of the 13th International Conference on Distributed Computing and Artificial Intelligence (DCAI) 2016. In the tradition of Herbert A. Simon’s interdisciplinary legacy, this book dedicates itself to the interdisciplinary study of decision-making in the recognition that relevant decision-making takes place in a range of critical subject areas and research fields, including economics, finance, information systems, small and international business, management, operations, and production. Decision-making issues are of crucial importance in economics. Not surprisingly, the study of decision-making has received a growing empirical research efforts in the applied economic literature over the last ...

  14. Evaluation of Secure Computation in a Distributed Healthcare Setting.

    Science.gov (United States)

    Kimura, Eizen; Hamada, Koki; Kikuchi, Ryo; Chida, Koji; Okamoto, Kazuya; Manabe, Shirou; Kuroda, Tomohiko; Matsumura, Yasushi; Takeda, Toshihiro; Mihara, Naoki

    2016-01-01

    Issues related to ensuring patient privacy and data ownership in clinical repositories prevent the growth of translational research. Previous studies have used an aggregator agent to obscure clinical repositories from the data user, and to ensure the privacy of output using statistical disclosure control. However, there remain several issues that must be considered. One such issue is that a data breach may occur when multiple nodes conspire. Another is that the agent may eavesdrop on or leak a user's queries and their results. We have implemented a secure computing method so that the data used by each party can be kept confidential even if all of the other parties conspire to crack the data. We deployed our implementation at three geographically distributed nodes connected to a high-speed layer two network. The performance of our method, with respect to processing times, suggests suitability for practical use.

  15. Distributed and multi-core computation of 2-loop integrals

    International Nuclear Information System (INIS)

    De Doncker, E; Yuasa, F

    2014-01-01

    For an automatic computation of Feynman loop integrals in the physical region we rely on an extrapolation technique where the integrals of the sequence are obtained with iterated/repeated adaptive methods from the QUADPACK 1D quadrature package. The integration rule evaluations in the outer level, corresponding to independent inner integral approximations, are assigned to threads dynamically via the OpenMP runtime in the parallel implementation. Furthermore, multi-level (nested) parallelism enables an efficient utilization of hyperthreading or larger numbers of cores. For a class of loop integrals in the unphysical region, which do not suffer from singularities in the interior of the integration domain, we find that the distributed adaptive integration methods in the multivariate PARINT package are highly efficient and accurate. We apply these techniques without resorting to integral transformations and report on the capabilities of the algorithms and the parallel performance for a test set including various types of two-loop integrals

  16. 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.

  17. Power Consumption Evaluation of Distributed Computing Network Considering Traffic Locality

    Science.gov (United States)

    Ogawa, Yukio; Hasegawa, Go; Murata, Masayuki

    When computing resources are consolidated in a few huge data centers, a massive amount of data is transferred to each data center over a wide area network (WAN). This results in increased power consumption in the WAN. A distributed computing network (DCN), such as a content delivery network, can reduce the traffic from/to the data center, thereby decreasing the power consumed in the WAN. In this paper, we focus on the energy-saving aspect of the DCN and evaluate its effectiveness, especially considering traffic locality, i.e., the amount of traffic related to the geographical vicinity. We first formulate the problem of optimizing the DCN power consumption and describe the DCN in detail. Then, numerical evaluations show that, when there is strong traffic locality and the router has ideal energy proportionality, the system's power consumption is reduced to about 50% of the power consumed in the case where a DCN is not used; moreover, this advantage becomes even larger (up to about 30%) when the data center is located farthest from the center of the network topology.

  18. Distribution of return point memory states for systems with stochastic inputs

    International Nuclear Information System (INIS)

    Amann, A; Brokate, M; Rachinskii, D; Temnov, G

    2011-01-01

    We consider the long term effect of stochastic inputs on the state of an open loop system which exhibits the so-called return point memory. An example of such a system is the Preisach model; more generally, systems with the Preisach type input-state relationship, such as in spin-interaction models, are considered. We focus on the characterisation of the expected memory configuration after the system has been effected by the input for sufficiently long period of time. In the case where the input is given by a discrete time random walk process, or the Wiener process, simple closed form expressions for the probability density of the vector of the main input extrema recorded by the memory state, and scaling laws for the dimension of this vector, are derived. If the input is given by a general continuous Markov process, we show that the distribution of previous memory elements can be obtained from a Markov chain scheme which is derived from the solution of an associated one-dimensional escape type problem. Formulas for transition probabilities defining this Markov chain scheme are presented. Moreover, explicit formulas for the conditional probability densities of previous main extrema are obtained for the Ornstein-Uhlenbeck input process. The analytical results are confirmed by numerical experiments.

  19. Metal oxide resistive random access memory based synaptic devices for brain-inspired computing

    Science.gov (United States)

    Gao, Bin; Kang, Jinfeng; Zhou, Zheng; Chen, Zhe; Huang, Peng; Liu, Lifeng; Liu, Xiaoyan

    2016-04-01

    The traditional Boolean computing paradigm based on the von Neumann architecture is facing great challenges for future information technology applications such as big data, the Internet of Things (IoT), and wearable devices, due to the limited processing capability issues such as binary data storage and computing, non-parallel data processing, and the buses requirement between memory units and logic units. The brain-inspired neuromorphic computing paradigm is believed to be one of the promising solutions for realizing more complex functions with a lower cost. To perform such brain-inspired computing with a low cost and low power consumption, novel devices for use as electronic synapses are needed. Metal oxide resistive random access memory (ReRAM) devices have emerged as the leading candidate for electronic synapses. This paper comprehensively addresses the recent work on the design and optimization of metal oxide ReRAM-based synaptic devices. A performance enhancement methodology and optimized operation scheme to achieve analog resistive switching and low-energy training behavior are provided. A three-dimensional vertical synapse network architecture is proposed for high-density integration and low-cost fabrication. The impacts of the ReRAM synaptic device features on the performances of neuromorphic systems are also discussed on the basis of a constructed neuromorphic visual system with a pattern recognition function. Possible solutions to achieve the high recognition accuracy and efficiency of neuromorphic systems are presented.

  20. Energy Scaling Advantages of Resistive Memory Crossbar Based Computation and its Application to Sparse Coding

    Directory of Open Access Journals (Sweden)

    Sapan eAgarwal

    2016-01-01

    Full Text Available The exponential increase in data over the last decade presents a significant challenge to analytics efforts that seek to process and interpret such data for various applications. Neural-inspired computing approaches are being developed in order to leverage the computational advantages of the analog, low-power data processing observed in biological systems. Analog resistive memory crossbars can perform a parallel read or a vector-matrix multiplication as well as a parallel write or a rank-1 update with high computational efficiency. For an NxN crossbar, these two kernels are at a minimum O(N more energy efficient than a digital memory-based architecture. If the read operation is noise limited, the energy to read a column can be independent of the crossbar size (O(1. These two kernels form the basis of many neuromorphic algorithms such as image, text, and speech recognition. For instance, these kernels can be applied to a neural sparse coding algorithm to give an O(N reduction in energy for the entire algorithm. Sparse coding is a rich problem with a host of applications including computer vision, object tracking, and more generally unsupervised learning.

  1. 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.

  2. 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.

  3. 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

  4. Soft-error tolerance and energy consumption evaluation of embedded computer with magnetic random access memory in practical systems using computer simulations

    Science.gov (United States)

    Nebashi, Ryusuke; Sakimura, Noboru; Sugibayashi, Tadahiko

    2017-08-01

    We evaluated the soft-error tolerance and energy consumption of an embedded computer with magnetic random access memory (MRAM) using two computer simulators. One is a central processing unit (CPU) simulator of a typical embedded computer system. We simulated the radiation-induced single-event-upset (SEU) probability in a spin-transfer-torque MRAM cell and also the failure rate of a typical embedded computer due to its main memory SEU error. The other is a delay tolerant network (DTN) system simulator. It simulates the power dissipation of wireless sensor network nodes of the system using a revised CPU simulator and a network simulator. We demonstrated that the SEU effect on the embedded computer with 1 Gbit MRAM-based working memory is less than 1 failure in time (FIT). We also demonstrated that the energy consumption of the DTN sensor node with MRAM-based working memory can be reduced to 1/11. These results indicate that MRAM-based working memory enhances the disaster tolerance of embedded computers.

  5. Logic computation in phase change materials by threshold and memory switching.

    Science.gov (United States)

    Cassinerio, M; Ciocchini, N; Ielmini, D

    2013-11-06

    Memristors, namely hysteretic devices capable of changing their resistance in response to applied electrical stimuli, may provide new opportunities for future memory and computation, thanks to their scalable size, low switching energy and nonvolatile nature. We have developed a functionally complete set of logic functions including NOR, NAND and NOT gates, each utilizing a single phase-change memristor (PCM) where resistance switching is due to the phase transformation of an active chalcogenide material. The logic operations are enabled by the high functionality of nanoscale phase change, featuring voltage comparison, additive crystallization and pulse-induced amorphization. The nonvolatile nature of memristive states provides the basis for developing reconfigurable hybrid logic/memory circuits featuring low-power and high-speed switching. © 2013 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

  6. EBR-II Cover Gas Cleanup System upgrade distributed control and front end computer systems

    International Nuclear Information System (INIS)

    Carlson, R.B.

    1992-01-01

    The Experimental Breeder Reactor II (EBR-II) Cover Gas Cleanup System (CGCS) control system was upgraded in 1991 to improve control and provide a graphical operator interface. The upgrade consisted of a main control computer, a distributed control computer, a front end input/output computer, a main graphics interface terminal, and a remote graphics interface terminal. This paper briefly describes the Cover Gas Cleanup System and the overall control system; gives reasons behind the computer system structure; and then gives a detailed description of the distributed control computer, the front end computer, and how these computers interact with the main control computer. The descriptions cover both hardware and software

  7. PHENIX On-Line Distributed Computing System Architecture

    International Nuclear Information System (INIS)

    Desmond, Edmond; Haggerty, John; Kehayias, Hyon Joo; Purschke, Martin L.; Witzig, Chris; Kozlowski, Thomas

    1997-01-01

    PHENIX is one of the two large experiments at the Relativistic Heavy Ion Collider (RHIC) currently under construction at Brookhaven National Laboratory. The detector consists of 11 sub-detectors, that are further subdivided into 29 units (''granules'') that can be operated independently, which includes simultaneous data taking with independent data streams and independent triggers. The detector has 250,000 channels and is read out by front end modules, where the data is buffered in a pipeline while awaiting the level trigger decision. Zero suppression and calibration is done after the level accept in custom built data collection modules (DCMs) with DSPs before the data is sent to an event builder (design throughput of 2 Gb/sec) and higher level triggers. The On-line Computing Systems Group (ONCS) has two responsibilities. Firstly it is responsible for receiving the data from the event builder, routing it through a network of workstations to consumer processes and archiving it at a data rate of 20 MB/sec. Secondly it is also responsible for the overall configuration, control and operation of the detector and data acquisition chain, which comprises the software integration for several thousand custom built hardware modules. The software must furthermore support the independent operation of the above mentioned granules, which includes the coordination of processes that run in 60-100 VME processors and workstations. ONOS has adapted the Shlaer- Mellor Object Oriented Methodology for the design of the top layer software. CORBA is used as communication layer between the distributed objects, which are implemented as asynchronous finite state machines. We will give an overview of the PHENIX online system with the main focus on the system architecture, software components and integration tasks of the On-line Computing group ONCS and report on the status of the current prototypes

  8. 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.

  9. Maintaining Traceability in an Evolving Distributed Computing Environment

    Science.gov (United States)

    Collier, I.; Wartel, R.

    2015-12-01

    The management of risk is fundamental to the operation of any distributed computing infrastructure. Identifying the cause of incidents is essential to prevent them from re-occurring. In addition, it is a goal to contain the impact of an incident while keeping services operational. For response to incidents to be acceptable this needs to be commensurate with the scale of the problem. The minimum level of traceability for distributed computing infrastructure usage is to be able to identify the source of all actions (executables, file transfers, pilot jobs, portal jobs, etc.) and the individual who initiated them. In addition, sufficiently fine-grained controls, such as blocking the originating user and monitoring to detect abnormal behaviour, are necessary for keeping services operational. It is essential to be able to understand the cause and to fix any problems before re-enabling access for the user. The aim is to be able to answer the basic questions who, what, where, and when concerning any incident. This requires retaining all relevant information, including timestamps and the digital identity of the user, sufficient to identify, for each service instance, and for every security event including at least the following: connect, authenticate, authorize (including identity changes) and disconnect. In traditional grid infrastructures (WLCG, EGI, OSG etc.) best practices and procedures for gathering and maintaining the information required to maintain traceability are well established. In particular, sites collect and store information required to ensure traceability of events at their sites. With the increased use of virtualisation and private and public clouds for HEP workloads established procedures, which are unable to see 'inside' running virtual machines no longer capture all the information required. Maintaining traceability will at least involve a shift of responsibility from sites to Virtual Organisations (VOs) bringing with it new requirements for their

  10. Using distributed processing on a local area network to increase available computing power

    International Nuclear Information System (INIS)

    Capps, K.S.; Sherry, K.J.

    1996-01-01

    The migration from central computers to desktop computers distributed the total computing horsepower of a system over many different machines. A typical engineering office may have several networked desktop computers that are sometimes idle, especially after work hours and when people are absent. Users would benefit if applications were able to use these networked computers collectively. This paper describes a method of distributing the workload of an application on one desktop system to otherwise idle systems on the network. The authors present this discussion from a developer's viewpoint, because the developer must modify an application before the user can realize any benefit of distributed computing on available systems

  11. Las Vegas is better than determinism in VLSI and distributed computing

    DEFF Research Database (Denmark)

    Mehlhorn, Kurt; Schmidt, Erik Meineche

    1982-01-01

    In this paper we describe a new method for proving lower bounds on the complexity of VLSI - computations and more generally distributed computations. Lipton and Sedgewick observed that the crossing sequence arguments used to prove lower bounds in VLSI (or TM or distributed computing) apply to (ac...

  12. Computational Aspects of Sensor Network Protocols (Distributed Sensor Network Simulator

    Directory of Open Access Journals (Sweden)

    Vasanth Iyer

    2009-08-01

    Full Text Available In this work, we model the sensor networks as an unsupervised learning and clustering process. We classify nodes according to its static distribution to form known class densities (CCPD. These densities are chosen from specific cross-layer features which maximizes lifetime of power-aware routing algorithms. To circumvent computational complexities of a power-ware communication STACK we introduce path-loss models at the nodes only for high density deployments. We study the cluster heads and formulate the data handling capacity for an expected deployment and use localized probability models to fuse the data with its side information before transmission. So each cluster head has a unique Pmax but not all cluster heads have the same measured value. In a lossless mode if there are no faults in the sensor network then we can show that the highest probability given by Pmax is ambiguous if its frequency is ≤ n/2 otherwise it can be determined by a local function. We further show that the event detection at the cluster heads can be modelled with a pattern 2m and m, the number of bits can be a correlated pattern of 2 bits and for a tight lower bound we use 3-bit Huffman codes which have entropy < 1. These local algorithms are further studied to optimize on power, fault detection and to maximize on the distributed routing algorithm used at the higher layers. From these bounds in large network, it is observed that the power dissipation is network size invariant. The performance of the routing algorithms solely based on success of finding healthy nodes in a large distribution. It is also observed that if the network size is kept constant and the density of the nodes is kept closer then the local pathloss model effects the performance of the routing algorithms. We also obtain the maximum intensity of transmitting nodes for a given category of routing algorithms for an outage constraint, i.e., the lifetime of sensor network.

  13. Above the cloud computing orbital services distributed data model

    Science.gov (United States)

    Straub, Jeremy

    2014-05-01

    Technology miniaturization and system architecture advancements have created an opportunity to significantly lower the cost of many types of space missions by sharing capabilities between multiple spacecraft. Historically, most spacecraft have been atomic entities that (aside from their communications with and tasking by ground controllers) operate in isolation. Several notable example exist; however, these are purpose-designed systems that collaborate to perform a single goal. The above the cloud computing (ATCC) concept aims to create ad-hoc collaboration between service provider and consumer craft. Consumer craft can procure processing, data transmission, storage, imaging and other capabilities from provider craft. Because of onboard storage limitations, communications link capability limitations and limited windows of communication, data relevant to or required for various operations may span multiple craft. This paper presents a model for the identification, storage and accessing of this data. This model includes appropriate identification features for this highly distributed environment. It also deals with business model constraints such as data ownership, retention and the rights of the storing craft to access, resell, transmit or discard the data in its possession. The model ensures data integrity and confidentiality (to the extent applicable to a given data item), deals with unique constraints of the orbital environment and tags data with business model (contractual) obligation data.

  14. Client/server models for transparent, distributed computational resources

    International Nuclear Information System (INIS)

    Hammer, K.E.; Gilman, T.L.

    1991-01-01

    Client/server models are proposed to address issues of shared resources in a distributed, heterogeneous UNIX environment. Recent development of automated Remote Procedure Call (RPC) interface generator has simplified the development of client/server models. Previously, implementation of the models was only possible at the UNIX socket level. An overview of RPCs and the interface generator will be presented and will include a discussion of generation and installation of remote services, the RPC paradigm, and the three levels of RPC programming. Two applications, the Nuclear Plant Analyzer (NPA) and a fluids simulation using molecular modelling, will be presented to demonstrate how client/server models using RPCs and External Data Representations (XDR) have been used production/computation situations. The NPA incorporates a client/server interface for transferring/translation of TRAC or RELAP results from the UNICOS Cray to a UNIX workstation. The fluids simulation program utilizes the client/server model to access the Cray via a single function allowing it to become a shared co-processor to the workstation application. 5 refs., 6 figs

  15. Evaluating Emulation-based Models of Distributed Computing Systems

    Energy Technology Data Exchange (ETDEWEB)

    Jones, Stephen T. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Cyber Initiatives; Gabert, Kasimir G. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Cyber Initiatives; Tarman, Thomas D. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States). Emulytics Initiatives

    2017-08-01

    Emulation-based models of distributed computing systems are collections of virtual ma- chines, virtual networks, and other emulation components configured to stand in for oper- ational systems when performing experimental science, training, analysis of design alterna- tives, test and evaluation, or idea generation. As with any tool, we should carefully evaluate whether our uses of emulation-based models are appropriate and justified. Otherwise, we run the risk of using a model incorrectly and creating meaningless results. The variety of uses of emulation-based models each have their own goals and deserve thoughtful evaluation. In this paper, we enumerate some of these uses and describe approaches that one can take to build an evidence-based case that a use of an emulation-based model is credible. Predictive uses of emulation-based models, where we expect a model to tell us something true about the real world, set the bar especially high and the principal evaluation method, called validation , is comensurately rigorous. We spend the majority of our time describing and demonstrating the validation of a simple predictive model using a well-established methodology inherited from decades of development in the compuational science and engineering community.

  16. HAlign-II: efficient ultra-large multiple sequence alignment and phylogenetic tree reconstruction with distributed and parallel computing.

    Science.gov (United States)

    Wan, Shixiang; Zou, Quan

    2017-01-01

    Multiple sequence alignment (MSA) plays a key role in biological sequence analyses, especially in phylogenetic tree construction. Extreme increase in next-generation sequencing results in shortage of efficient ultra-large biological sequence alignment approaches for coping with different sequence types. Distributed and parallel computing represents a crucial technique for accelerating ultra-large (e.g. files more than 1 GB) sequence analyses. Based on HAlign and Spark distributed computing system, we implement a highly cost-efficient and time-efficient HAlign-II tool to address ultra-large multiple biological sequence alignment and phylogenetic tree construction. The experiments in the DNA and protein large scale data sets, which are more than 1GB files, showed that HAlign II could save time and space. It outperformed the current software tools. HAlign-II can efficiently carry out MSA and construct phylogenetic trees with ultra-large numbers of biological sequences. HAlign-II shows extremely high memory efficiency and scales well with increases in computing resource. THAlign-II provides a user-friendly web server based on our distributed computing infrastructure. HAlign-II with open-source codes and datasets was established at http://lab.malab.cn/soft/halign.

  17. The Cortex Transform as an image preprocessor for sparse distributed memory: An initial study

    Science.gov (United States)

    Olshausen, Bruno; Watson, Andrew

    1990-01-01

    An experiment is described which was designed to evaluate the use of the Cortex Transform as an image processor for Sparse Distributed Memory (SDM). In the experiment, a set of images were injected with Gaussian noise, preprocessed with the Cortex Transform, and then encoded into bit patterns. The various spatial frequency bands of the Cortex Transform were encoded separately so that they could be evaluated based on their ability to properly cluster patterns belonging to the same class. The results of this study indicate that by simply encoding the low pass band of the Cortex Transform, a very suitable input representation for the SDM can be achieved.

  18. Convergence dynamics of hybrid bidirectional associative memory neural networks with distributed delays

    International Nuclear Information System (INIS)

    Liao Xiaofeng; Wong, K.-W.; Yang Shizhong

    2003-01-01

    In this Letter, the characteristics of the convergence dynamics of hybrid bidirectional associative memory neural networks with distributed transmission delays are studied. Without assuming the symmetry of synaptic connection weights and the monotonicity and differentiability of activation functions, the Lyapunov functionals are constructed and the generalized Halanay-type inequalities are employed to derive the delay-independent sufficient conditions under which the networks converge exponentially to the equilibria associated with temporally uniform external inputs. Some examples are given to illustrate the correctness of our results

  19. WRF4G project: Adaptation of WRF Model to Distributed Computing Infrastructures

    Science.gov (United States)

    Cofino, Antonio S.; Fernández Quiruelas, Valvanuz; García Díez, Markel; Blanco Real, Jose C.; Fernández, Jesús

    2013-04-01

    Nowadays Grid Computing is powerful computational tool which is ready to be used for scientific community in different areas (such as biomedicine, astrophysics, climate, etc.). However, the use of this distributed computing infrastructures (DCI) is not yet common practice in climate research, and only a few teams and applications in this area take advantage of this infrastructure. Thus, the first objective of this project is to popularize the use of this technology in the atmospheric sciences area. In order to achieve this objective, one of the most used applications has been taken (WRF; a limited- area model, successor of the MM5 model), that has a user community formed by more than 8000 researchers worldwide. This community develop its research activity on different areas and could benefit from the advantages of Grid resources (case study simulations, regional hind-cast/forecast, sensitivity studies, etc.). The WRF model is been used as input by many energy and natural hazards community, therefore those community will also benefit. However, Grid infrastructures have some drawbacks for the execution of applications that make an intensive use of CPU and memory for a long period of time. This makes necessary to develop a specific framework (middleware). This middleware encapsulates the application and provides appropriate services for the monitoring and management of the jobs and the data. Thus, the second objective of the project consists on the development of a generic adaptation of WRF for Grid (WRF4G), to be distributed as open-source and to be integrated in the official WRF development cycle. The use of this WRF adaptation should be transparent and useful to face any of the previously described studies, and avoid any of the problems of the Grid infrastructure. Moreover it should simplify the access to the Grid infrastructures for the research teams, and also to free them from the technical and computational aspects of the use of the Grid. Finally, in order to

  20. Iterative schemes for parallel Sn algorithms in a shared-memory computing environment

    International Nuclear Information System (INIS)

    Haghighat, A.; Hunter, M.A.; Mattis, R.E.

    1995-01-01

    Several two-dimensional spatial domain partitioning S n transport theory algorithms are developed on the basis of different iterative schemes. These algorithms are incorporated into TWOTRAN-II and tested on the shared-memory CRAY Y-MP C90 computer. For a series of fixed-source r-z geometry homogeneous problems, it is demonstrated that the concurrent red-black algorithms may result in large parallel efficiencies (>60%) on C90. It is also demonstrated that for a realistic shielding problem, the use of the negative flux fixup causes high load imbalance, which results in a significant loss of parallel efficiency

  1. Disentangling the Relationship Between the Adoption of In-Memory Computing and Firm Performance

    DEFF Research Database (Denmark)

    Fay, Marua; Müller, Oliver; vom Brocke, Jan

    2016-01-01

    Recent growth in data volume, variety, and velocity led to an increased demand for high-performance data processing and analytics solutions. In-memory computing (IMC) enables organizations to boost their information processing capacity, and is widely acknowledged to be one of the leading strategic...... at explaining the relationship between the adoption of IMC solutions and firm performance. In this research-in-progress paper we discuss the theoretical background of our work, describe the proposed research design, and develop five hypotheses for later testing. Our work aims at contributing to the research...

  2. Memory

    OpenAIRE

    Wager, Nadia

    2017-01-01

    This chapter will explore a response to traumatic victimisation which has divided the opinions of psychologists at an exponential rate. We will be examining amnesia for memories of childhood sexual abuse and the potential to recover these memories in adulthood. Whilst this phenomenon is generally accepted in clinical circles, it is seen as highly contentious amongst research psychologists, particularly experimental cognitive psychologists. The chapter will begin with a real case study of a wo...

  3. A Parallel and Distributed Surrogate Model Implementation for Computational Steering

    KAUST Repository

    Butnaru, Daniel; Buse, Gerrit; Pfluger, Dirk

    2012-01-01

    of the input parameters. Such an exploration process is however not possible if the simulation is computationally too expensive. For these cases we present in this paper a scalable computational steering approach utilizing a fast surrogate model as substitute

  4. SiGe epitaxial memory for neuromorphic computing with reproducible high performance based on engineered dislocations

    Science.gov (United States)

    Choi, Shinhyun; Tan, Scott H.; Li, Zefan; Kim, Yunjo; Choi, Chanyeol; Chen, Pai-Yu; Yeon, Hanwool; Yu, Shimeng; Kim, Jeehwan

    2018-01-01

    Although several types of architecture combining memory cells and transistors have been used to demonstrate artificial synaptic arrays, they usually present limited scalability and high power consumption. Transistor-free analog switching devices may overcome these limitations, yet the typical switching process they rely on—formation of filaments in an amorphous medium—is not easily controlled and hence hampers the spatial and temporal reproducibility of the performance. Here, we demonstrate analog resistive switching devices that possess desired characteristics for neuromorphic computing networks with minimal performance variations using a single-crystalline SiGe layer epitaxially grown on Si as a switching medium. Such epitaxial random access memories utilize threading dislocations in SiGe to confine metal filaments in a defined, one-dimensional channel. This confinement results in drastically enhanced switching uniformity and long retention/high endurance with a high analog on/off ratio. Simulations using the MNIST handwritten recognition data set prove that epitaxial random access memories can operate with an online learning accuracy of 95.1%.

  5. Results from the First Two Flights of the Static Computer Memory Integrity Testing Experiment

    Science.gov (United States)

    Hancock, Thomas M., III

    1999-01-01

    This paper details the scientific objectives, experiment design, data collection method, and post flight analysis following the first two flights of the Static Computer Memory Integrity Testing (SCMIT) experiment. SCMIT is designed to detect soft-event upsets in passive magnetic memory. A soft-event upset is a change in the logic state of active or passive forms of magnetic memory, commonly referred to as a "Bitflip". In its mildest form a soft-event upset can cause software exceptions, unexpected events, start spacecraft safeing (ending data collection) or corrupted fault protection and error recovery capabilities. In it's most severe form loss of mission or spacecraft can occur. Analysis after the first flight (in 1991 during STS-40) identified possible soft-event upsets to 25% of the experiment detectors. Post flight analysis after the second flight (in 1997 on STS-87) failed to find any evidence of soft-event upsets. The SCMIT experiment is currently scheduled for a third flight in December 1999 on STS-101.

  6. Massive calculations of electrostatic potentials and structure maps of biopolymers in a distributed computing environment

    International Nuclear Information System (INIS)

    Akishina, T.P.; Ivanov, V.V.; Stepanenko, V.A.

    2013-01-01

    Among the key factors determining the processes of transcription and translation are the distributions of the electrostatic potentials of DNA, RNA and proteins. Calculations of electrostatic distributions and structure maps of biopolymers on computers are time consuming and require large computational resources. We developed the procedures for organization of massive calculations of electrostatic potentials and structure maps for biopolymers in a distributed computing environment (several thousands of cores).

  7. Discrete Ziggurat: A time-memory trade-off for sampling from a Gaussian distribution over the integers

    NARCIS (Netherlands)

    Buchmann, J.; Cabarcas, D.; Göpfert, F.; Hülsing, A.T.; Weiden, P.; Lange, T.; Lauter, K.; Lisonek, P.

    2014-01-01

    Several lattice-based cryptosystems require to sample from a discrete Gaussian distribution over the integers. Existing methods to sample from such a distribution either need large amounts of memory or they are very slow. In this paper we explore a different method that allows for a flexible

  8. Modified stretched exponential model of computer system resources management limitations-The case of cache memory

    Science.gov (United States)

    Strzałka, Dominik; Dymora, Paweł; Mazurek, Mirosław

    2018-02-01

    In this paper we present some preliminary results in the field of computer systems management with relation to Tsallis thermostatistics and the ubiquitous problem of hardware limited resources. In the case of systems with non-deterministic behaviour, management of their resources is a key point that guarantees theirs acceptable performance and proper working. This is very wide problem that stands for many challenges in financial, transport, water and food, health, etc. areas. We focus on computer systems with attention paid to cache memory and propose to use an analytical model that is able to connect non-extensive entropy formalism, long-range dependencies, management of system resources and queuing theory. Obtained analytical results are related to the practical experiment showing interesting and valuable results.

  9. Raster Scan Computer Image Generation (CIG) System Based On Refresh Memory

    Science.gov (United States)

    Dichter, W.; Doris, K.; Conkling, C.

    1982-06-01

    A full color, Computer Image Generation (CIG) raster visual system has been developed which provides a high level of training sophistication by utilizing advanced semiconductor technology and innovative hardware and firmware techniques. Double buffered refresh memory and efficient algorithms eliminate the problem of conventional raster line ordering by allowing the generated image to be stored in a random fashion. Modular design techniques and simplified architecture provide significant advantages in reduced system cost, standardization of parts, and high reliability. The major system components are a general purpose computer to perform interfacing and data base functions; a geometric processor to define the instantaneous scene image; a display generator to convert the image to a video signal; an illumination control unit which provides final image processing; and a CRT monitor for display of the completed image. Additional optional enhancements include texture generators, increased edge and occultation capability, curved surface shading, and data base extensions.

  10. Photon echo quantum random access memory integration in a quantum computer

    International Nuclear Information System (INIS)

    Moiseev, Sergey A; Andrianov, Sergey N

    2012-01-01

    We have analysed an efficient integration of multi-qubit echo quantum memory (QM) into the quantum computer scheme based on squids, quantum dots or atomic resonant ensembles in a quantum electrodynamics cavity. Here, one atomic ensemble with controllable inhomogeneous broadening is used for the QM node and other nodes characterized by the homogeneously broadened resonant line are used for processing. We have found the optimal conditions for the efficient integration of the multi-qubit QM modified for the analysed scheme, and we have determined the self-temporal modes providing a perfect reversible transfer of the photon qubits between the QM node and arbitrary processing nodes. The obtained results open the way for realization of a full-scale solid state quantum computing based on the efficient multi-qubit QM. (paper)

  11. Evaluation of DEC`s GIGAswitch for distributed parallel computing

    Energy Technology Data Exchange (ETDEWEB)

    Chen, H.; Hutchins, J.; Brandt, J.

    1993-10-01

    One of Sandia`s research efforts is to reduce the end-to-end communication delay in a parallel-distributed computing environment. GIGAswitch is DEC`s implementation of a gigabit local area network based on switched FDDI technology. Using the GIGAswitch, the authors intend to minimize the medium access latency suffered by shared-medium FDDI technology. Experimental results show that the GIGAswitch adds 16.5 microseconds of switching and bridging delay to an end-to-end communication. Although the added latency causes a 1.8% throughput degradation and a 5% line efficiency degradation, the availability of dedicated bandwidth is much more than what is available to a workstation on a shared medium. For example, ten directly connected workstations each would have a dedicated bandwidth of 95 Mbps, but if they were sharing the FDDI bandwidth, each would have 10% of the total bandwidth, i.e., less than 10 Mbps. In addition, they have found that when there is no output port contention, the switch`s aggregate bandwidth will scale up to multiples of its port bandwidth. However, with output port contention, the throughput and latency performance suffered significantly. Their mathematical and simulation models indicate that the GIGAswitch line efficiency could be as low as 63% when there are nine input ports contending for the same output port. The data indicate that the delay introduced by contention at the server workstation is 50 times that introduced by the GIGAswitch. The authors conclude that the GIGAswitch meets the performance requirements of today`s high-end workstations and that the switched FDDI technology provides an alternative that utilizes existing workstation interfaces while increasing the aggregate bandwidth. However, because the speed of workstations is increasing by a factor of 2 every 1.5 years, the switched FDDI technology is only good as an interim solution.

  12. Accelerated Cyclic Reduction: A Distributed-Memory Fast Solver for Structured Linear Systems

    KAUST Repository

    Chávez, Gustavo

    2017-12-15

    We present Accelerated Cyclic Reduction (ACR), a distributed-memory fast solver for rank-compressible block tridiagonal linear systems arising from the discretization of elliptic operators, developed here for three dimensions. Algorithmic synergies between Cyclic Reduction and hierarchical matrix arithmetic operations result in a solver that has O(kNlogN(logN+k2)) arithmetic complexity and O(k Nlog N) memory footprint, where N is the number of degrees of freedom and k is the rank of a block in the hierarchical approximation, and which exhibits substantial concurrency. We provide a baseline for performance and applicability by comparing with the multifrontal method with and without hierarchical semi-separable matrices, with algebraic multigrid and with the classic cyclic reduction method. Over a set of large-scale elliptic systems with features of nonsymmetry and indefiniteness, the robustness of the direct solvers extends beyond that of the multigrid solver, and relative to the multifrontal approach ACR has lower or comparable execution time and size of the factors, with substantially lower numerical ranks. ACR exhibits good strong and weak scaling in a distributed context and, as with any direct solver, is advantageous for problems that require the solution of multiple right-hand sides. Numerical experiments show that the rank k patterns are of O(1) for the Poisson equation and of O(n) for the indefinite Helmholtz equation. The solver is ideal in situations where low-accuracy solutions are sufficient, or otherwise as a preconditioner within an iterative method.

  13. Accelerated Cyclic Reduction: A Distributed-Memory Fast Solver for Structured Linear Systems

    KAUST Repository

    Chá vez, Gustavo; Turkiyyah, George; Zampini, Stefano; Ltaief, Hatem; Keyes, David E.

    2017-01-01

    We present Accelerated Cyclic Reduction (ACR), a distributed-memory fast solver for rank-compressible block tridiagonal linear systems arising from the discretization of elliptic operators, developed here for three dimensions. Algorithmic synergies between Cyclic Reduction and hierarchical matrix arithmetic operations result in a solver that has O(kNlogN(logN+k2)) arithmetic complexity and O(k Nlog N) memory footprint, where N is the number of degrees of freedom and k is the rank of a block in the hierarchical approximation, and which exhibits substantial concurrency. We provide a baseline for performance and applicability by comparing with the multifrontal method with and without hierarchical semi-separable matrices, with algebraic multigrid and with the classic cyclic reduction method. Over a set of large-scale elliptic systems with features of nonsymmetry and indefiniteness, the robustness of the direct solvers extends beyond that of the multigrid solver, and relative to the multifrontal approach ACR has lower or comparable execution time and size of the factors, with substantially lower numerical ranks. ACR exhibits good strong and weak scaling in a distributed context and, as with any direct solver, is advantageous for problems that require the solution of multiple right-hand sides. Numerical experiments show that the rank k patterns are of O(1) for the Poisson equation and of O(n) for the indefinite Helmholtz equation. The solver is ideal in situations where low-accuracy solutions are sufficient, or otherwise as a preconditioner within an iterative method.

  14. Approach to Accelerating Dissolved Vector Buffer Generation in Distributed In-Memory Cluster Architecture

    Directory of Open Access Journals (Sweden)

    Jinxin Shen

    2018-01-01

    Full Text Available The buffer generation algorithm is a fundamental function in GIS, identifying areas of a given distance surrounding geographic features. Past research largely focused on buffer generation algorithms generated in a stand-alone environment. Moreover, dissolved buffer generation is data- and computing-intensive. In this scenario, the improvement in the stand-alone environment is limited when considering large-scale mass vector data. Nevertheless, recent parallel dissolved vector buffer algorithms suffer from scalability problems, leaving room for further optimization. At present, the prevailing in-memory cluster-computing framework—Spark—provides promising efficiency for computing-intensive analysis; however, it has seldom been researched for buffer analysis. On this basis, we propose a cluster-computing-oriented parallel dissolved vector buffer generating algorithm, called the HPBM, that contains a Hilbert-space-filling-curve-based data partition method, a data skew and cross-boundary objects processing strategy, and a depth-given tree-like merging method. Experiments are conducted in both stand-alone and cluster environments using real-world vector data that include points and roads. Compared with some existing parallel buffer algorithms, as well as various popular GIS software, the HPBM achieves a performance gain of more than 50%.

  15. A multiprocessor computer simulation model employing a feedback scheduler/allocator for memory space and bandwidth matching and TMR processing

    Science.gov (United States)

    Bradley, D. B.; Irwin, J. D.

    1974-01-01

    A computer simulation model for a multiprocessor computer is developed that is useful for studying the problem of matching multiprocessor's memory space, memory bandwidth and numbers and speeds of processors with aggregate job set characteristics. The model assumes an input work load of a set of recurrent jobs. The model includes a feedback scheduler/allocator which attempts to improve system performance through higher memory bandwidth utilization by matching individual job requirements for space and bandwidth with space availability and estimates of bandwidth availability at the times of memory allocation. The simulation model includes provisions for specifying precedence relations among the jobs in a job set, and provisions for specifying precedence execution of TMR (Triple Modular Redundant and SIMPLEX (non redundant) jobs.

  16. Microdot - A Four-Bit Microcontroller Designed for Distributed Low-End Computing in Satellites

    National Research Council Canada - National Science Library

    2002-01-01

    .... An alternative design approach is a distributed network of small and low power microcontrollers designed for space that handle the computing requirements of each individual sensor and actuator...

  17. A wireless computational platform for distributed computing based traffic monitoring involving mixed Eulerian-Lagrangian sensing

    KAUST Repository

    Jiang, Jiming

    2013-06-01

    This paper presents a new wireless platform designed for an integrated traffic monitoring system based on combined Lagrangian (mobile) and Eulerian (fixed) sensing. The sensor platform is built around a 32-bit ARM Cortex M4 micro-controller and a 2.4GHz 802.15.4 ISM compliant radio module, and can be interfaced with fixed traffic sensors, or receive data from vehicle transponders. The platform is specially designed and optimized to be integrated in a solar-powered wireless sensor network in which traffic flow maps are computed by the nodes directly using distributed computing. A MPPT circuitry is proposed to increase the power output of the attached solar panel. A self-recovering unit is designed to increase reliability and allow periodic hard resets, an essential requirement for sensor networks. A radio monitoring circuitry is proposed to monitor incoming and outgoing transmissions, simplifying software debug. An ongoing implementation is briefly discussed, and compared with existing platforms used in wireless sensor networks. © 2013 IEEE.

  18. Linking Working Memory and Long-Term Memory: A Computational Model of the Learning of New Words

    Science.gov (United States)

    Jones, Gary; Gobet, Fernand; Pine, Julian M.

    2007-01-01

    The nonword repetition (NWR) test has been shown to be a good predictor of children's vocabulary size. NWR performance has been explained using phonological working memory, which is seen as a critical component in the learning of new words. However, no detailed specification of the link between phonological working memory and long-term memory…

  19. Read-only-memory-based quantum computation: Experimental explorations using nuclear magnetic resonance and future prospects

    International Nuclear Information System (INIS)

    Sypher, D.R.; Brereton, I.M.; Wiseman, H.M.; Hollis, B.L.; Travaglione, B.C.

    2002-01-01

    Read-only-memory-based (ROM-based) quantum computation (QC) is an alternative to oracle-based QC. It has the advantages of being less 'magical', and being more suited to implementing space-efficient computation (i.e., computation using the minimum number of writable qubits). Here we consider a number of small (one- and two-qubit) quantum algorithms illustrating different aspects of ROM-based QC. They are: (a) a one-qubit algorithm to solve the Deutsch problem; (b) a one-qubit binary multiplication algorithm; (c) a two-qubit controlled binary multiplication algorithm; and (d) a two-qubit ROM-based version of the Deutsch-Jozsa algorithm. For each algorithm we present experimental verification using nuclear magnetic resonance ensemble QC. The average fidelities for the implementation were in the ranges 0.9-0.97 for the one-qubit algorithms, and 0.84-0.94 for the two-qubit algorithms. We conclude with a discussion of future prospects for ROM-based quantum computation. We propose a four-qubit algorithm, using Grover's iterate, for solving a miniature 'real-world' problem relating to the lengths of paths in a network

  20. Distributed Computing on Gadgetron: A new paradigm for MRI reconstruction

    DEFF Research Database (Denmark)

    Xue, Hui; Kelmann, Peter; Inati, Souheil

    cloud computing. With this extension (named GT-Plus), any number of Gadgetron processes can run cooperatively across multiple computers. GT-Plus framework was deployed on Amazon EC2 cloud and NIH’s Biowulf system. We demonstrate that with the GT-Plus cloud, a multi-slice free-breathing myocardial cine...

  1. Memories.

    Science.gov (United States)

    Brand, Judith, Ed.

    1998-01-01

    This theme issue of the journal "Exploring" covers the topic of "memories" and describes an exhibition at San Francisco's Exploratorium that ran from May 22, 1998 through January 1999 and that contained over 40 hands-on exhibits, demonstrations, artworks, images, sounds, smells, and tastes that demonstrated and depicted the biological,…

  2. Integration of distributed computing into the drug discovery process.

    Science.gov (United States)

    von Korff, Modest; Rufener, Christian; Stritt, Manuel; Freyss, Joel; Bär, Roman; Sander, Thomas

    2011-02-01

    Grid computing offers an opportunity to gain massive computing power at low costs. We give a short introduction into the drug discovery process and exemplify the use of grid computing for image processing, docking and 3D pharmacophore descriptor calculations. The principle of a grid and its architecture are briefly explained. More emphasis is laid on the issues related to a company-wide grid installation and embedding the grid into the research process. The future of grid computing in drug discovery is discussed in the expert opinion section. Most needed, besides reliable algorithms to predict compound properties, is embedding the grid seamlessly into the discovery process. User friendly access to powerful algorithms without any restrictions, that is, by a limited number of licenses, has to be the goal of grid computing in drug discovery.

  3. Experience with a distributed computing system for magnetic field analysis

    International Nuclear Information System (INIS)

    Newman, M.J.

    1978-08-01

    The development of a general purpose computer system, THESEUS, is described the initial use for which has been magnetic field analysis. The system involves several computers connected by data links. Some are small computers with interactive graphics facilities and limited analysis capabilities, and others are large computers for batch execution of analysis programs with heavy processor demands. The system is highly modular for easy extension and highly portable for transfer to different computers. It can easily be adapted for a completely different application. It provides a highly efficient and flexible interface between magnet designers and specialised analysis programs. Both the advantages and problems experienced are highlighted, together with a mention of possible future developments. (U.K.)

  4. Discovery of resources using MADM approaches for parallel and distributed computing

    Directory of Open Access Journals (Sweden)

    Mandeep Kaur

    2017-06-01

    Full Text Available Grid, a form of parallel and distributed computing, allows the sharing of data and computational resources among its users from various geographical locations. The grid resources are diverse in terms of their underlying attributes. The majority of the state-of-the-art resource discovery techniques rely on the static resource attributes during resource selection. However, the matching resources based on the static resource attributes may not be the most appropriate resources for the execution of user applications because they may have heavy job loads, less storage space or less working memory (RAM. Hence, there is a need to consider the current state of the resources in order to find the most suitable resources. In this paper, we have proposed a two-phased multi-attribute decision making (MADM approach for discovery of grid resources by using P2P formalism. The proposed approach considers multiple resource attributes for decision making of resource selection and provides the best suitable resource(s to grid users. The first phase describes a mechanism to discover all matching resources and applies SAW method to shortlist the top ranked resources, which are communicated to the requesting super-peer. The second phase of our proposed methodology applies integrated MADM approach (AHP enriched PROMETHEE-II on the list of selected resources received from different super-peers. The pairwise comparison of the resources with respect to their attributes is made and the rank of each resource is determined. The top ranked resource is then communicated to the grid user by the grid scheduler. Our proposed methodology enables the grid scheduler to allocate the most suitable resource to the user application and also reduces the search complexity by filtering out the less suitable resources during resource discovery.

  5. Fourier coefficientes computation in two variables, a distributional version

    Directory of Open Access Journals (Sweden)

    Carlos Manuel Ulate R.

    2015-01-01

    Full Text Available The present article, by considering the distributional summations of Euler-Maclaurin and a suitable choice of the distribution, results in repre- sentations for the Fourier coefficients in two variables are obtained. These representations may be used for the numerical evaluation of coefficients.

  6. Fourier coefficientes computation in two variables, a distributional version

    OpenAIRE

    Carlos Manuel Ulate R.

    2015-01-01

    The present article, by considering the distributional summations of Euler-Maclaurin and a suitable choice of the distribution, results in repre- sentations for the Fourier coefficients in two variables are obtained. These representations may be used for the numerical evaluation of coefficients.

  7. Diffusion with space memory modelled with distributed order space fractional differential equations

    Directory of Open Access Journals (Sweden)

    M. Caputo

    2003-06-01

    Full Text Available Distributed order fractional differential equations (Caputo, 1995, 2001; Bagley and Torvik, 2000a,b were fi rst used in the time domain; they are here considered in the space domain and introduced in the constitutive equation of diffusion. The solution of the classic problems are obtained, with closed form formulae. In general, the Green functions act as low pass fi lters in the frequency domain. The major difference with the case when a single space fractional derivative is present in the constitutive equations of diffusion (Caputo and Plastino, 2002 is that the solutions found here are potentially more fl exible to represent more complex media (Caputo, 2001a. The difference between the space memory medium and that with the time memory is that the former is more fl exible to represent local phenomena while the latter is more fl exible to represent variations in space. Concerning the boundary value problem, the difference with the solution of the classic diffusion medium, in the case when a constant boundary pressure is assigned and in the medium the pressure is initially nil, is that one also needs to assign the fi rst order space derivative at the boundary.

  8. Scaling Techniques for Massive Scale-Free Graphs in Distributed (External) Memory

    KAUST Repository

    Pearce, Roger

    2013-05-01

    We present techniques to process large scale-free graphs in distributed memory. Our aim is to scale to trillions of edges, and our research is targeted at leadership class supercomputers and clusters with local non-volatile memory, e.g., NAND Flash. We apply an edge list partitioning technique, designed to accommodate high-degree vertices (hubs) that create scaling challenges when processing scale-free graphs. In addition to partitioning hubs, we use ghost vertices to represent the hubs to reduce communication hotspots. We present a scaling study with three important graph algorithms: Breadth-First Search (BFS), K-Core decomposition, and Triangle Counting. We also demonstrate scalability on BG/P Intrepid by comparing to best known Graph500 results. We show results on two clusters with local NVRAM storage that are capable of traversing trillion-edge scale-free graphs. By leveraging node-local NAND Flash, our approach can process thirty-two times larger datasets with only a 39% performance degradation in Traversed Edges Per Second (TEPS). © 2013 IEEE.

  9. A Distributed Agent Architecture for a Computer Virus Immune System

    National Research Council Canada - National Science Library

    Harmer, Paul

    2000-01-01

    .... Information protection and information assurance are vital components required for achieving superiority in the Infosphere, but these goals are threatened by the exponential birth rate of new computer viruses...

  10. Building Trust and Confidentiality in Cloud computing Distributed ...

    African Journals Online (AJOL)

    2013-03-01

    Mar 1, 2013 ... Department of Computer Science, University of Port Harcourt, Rivers State ... considering the security and privacy of the information stored and processed within the cloud. .... protection (perhaps access control), through to.

  11. Distributed Scheme to Authenticate Data Storage Security in Cloud Computing

    OpenAIRE

    B. Rakesh; K. Lalitha; M. Ismail; H. Parveen Sultana

    2017-01-01

    Cloud Computing is the revolution in current generation IT enterprise. Cloud computing displaces database and application software to the large data centres, where the management of services and data may not be predictable, where as the conventional solutions, for IT services are under proper logical, physical and personal controls. This aspect attribute, however comprises different security challenges which have not been well understood. It concentrates on cloud data storage security which h...

  12. Distributed computer control systems in future nuclear power plants

    International Nuclear Information System (INIS)

    Yan, G.; L'Archeveque, J.V.R.; Watkins, L.M.

    1978-09-01

    Good operating experience with computer control in CANDU reactors over the last decade justifies a broadening of the role of digital electronic and computer related technologies in future plants. Functions of electronic systems in the total plant context are reappraised to help evolve an appropriate match between technology and future applications. The systems research, development and demonstration program at CRNL is described, focusing on the projects pertinent to the real-time data acquisition and process control requirements. (author)

  13. 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)

  14. Impact of singular excessive computer game and television exposure on sleep patterns and memory performance of school-aged children.

    Science.gov (United States)

    Dworak, Markus; Schierl, Thomas; Bruns, Thomas; Strüder, Heiko Klaus

    2007-11-01

    Television and computer game consumption are a powerful influence in the lives of most children. Previous evidence has supported the notion that media exposure could impair a variety of behavioral characteristics. Excessive television viewing and computer game playing have been associated with many psychiatric symptoms, especially emotional and behavioral symptoms, somatic complaints, attention problems such as hyperactivity, and family interaction problems. Nevertheless, there is insufficient knowledge about the relationship between singular excessive media consumption on sleep patterns and linked implications on children. The aim of this study was to investigate the effects of singular excessive television and computer game consumption on sleep patterns and memory performance of children. Eleven school-aged children were recruited for this polysomnographic study. Children were exposed to voluntary excessive television and computer game consumption. In the subsequent night, polysomnographic measurements were conducted to measure sleep-architecture and sleep-continuity parameters. In addition, a visual and verbal memory test was conducted before media stimulation and after the subsequent sleeping period to determine visuospatial and verbal memory performance. Only computer game playing resulted in significant reduced amounts of slow-wave sleep as well as significant declines in verbal memory performance. Prolonged sleep-onset latency and more stage 2 sleep were also detected after previous computer game consumption. No effects on rapid eye movement sleep were observed. Television viewing reduced sleep efficiency significantly but did not affect sleep patterns. The results suggest that television and computer game exposure affect children's sleep and deteriorate verbal cognitive performance, which supports the hypothesis of the negative influence of media consumption on children's sleep, learning, and memory.

  15. Comparison between sparsely distributed memory and Hopfield-type neural network models

    Science.gov (United States)

    Keeler, James D.

    1986-01-01

    The Sparsely Distributed Memory (SDM) model (Kanerva, 1984) is compared to Hopfield-type neural-network models. A mathematical framework for comparing the two is developed, and the capacity of each model is investigated. The capacity of the SDM can be increased independently of the dimension of the stored vectors, whereas the Hopfield capacity is limited to a fraction of this dimension. However, the total number of stored bits per matrix element is the same in the two models, as well as for extended models with higher order interactions. The models are also compared in their ability to store sequences of patterns. The SDM is extended to include time delays so that contextual information can be used to cover sequences. Finally, it is shown how a generalization of the SDM allows storage of correlated input pattern vectors.

  16. Global exponential stability of bidirectional associative memory neural networks with distributed delays

    Science.gov (United States)

    Song, Qiankun; Cao, Jinde

    2007-05-01

    A bidirectional associative memory neural network model with distributed delays is considered. By constructing a new Lyapunov functional, employing the homeomorphism theory, M-matrix theory and the inequality (a[greater-or-equal, slanted]0,bk[greater-or-equal, slanted]0,qk>0 with , and r>1), a sufficient condition is obtained to ensure the existence, uniqueness and global exponential stability of the equilibrium point for the model. Moreover, the exponential converging velocity index is estimated, which depends on the delay kernel functions and the system parameters. The results generalize and improve the earlier publications, and remove the usual assumption that the activation functions are bounded . Two numerical examples are given to show the effectiveness of the obtained results.

  17. A computer vision-based automated Figure-8 maze for working memory test in rodents.

    Science.gov (United States)

    Pedigo, Samuel F; Song, Eun Young; Jung, Min Whan; Kim, Jeansok J

    2006-09-30

    The benchmark test for prefrontal cortex (PFC)-mediated working memory in rodents is a delayed alternation task utilizing variations of T-maze or Figure-8 maze, which requires the animals to make specific arm entry responses for reward. In this task, however, manual procedures involved in shaping target behavior, imposing delays between trials and delivering rewards can potentially influence the animal's performance on the maze. Here, we report an automated Figure-8 maze which does not necessitate experimenter-subject interaction during shaping, training or testing. This system incorporates a computer vision system for tracking, motorized gates to impose delays, and automated reward delivery. The maze is controlled by custom software that records the animal's location and activates the gates according to the animal's behavior and a control algorithm. The program performs calculations of task accuracy, tracks movement sequence through the maze, and provides other dependent variables (such as running speed, time spent in different maze locations, activity level during delay). Testing in rats indicates that the performance accuracy is inversely proportional to the delay interval, decreases with PFC lesions, and that animals anticipate timing during long delays. Thus, our automated Figure-8 maze is effective at assessing working memory and provides novel behavioral measures in rodents.

  18. Holographic memory system based on projection recording of computer-generated 1D Fourier holograms.

    Science.gov (United States)

    Betin, A Yu; Bobrinev, V I; Donchenko, S S; Odinokov, S B; Evtikhiev, N N; Starikov, R S; Starikov, S N; Zlokazov, E Yu

    2014-10-01

    Utilization of computer generation of holographic structures significantly simplifies the optical scheme that is used to record the microholograms in a holographic memory record system. Also digital holographic synthesis allows to account the nonlinear errors of the record system to improve the microholograms quality. The multiplexed record of holograms is a widespread technique to increase the data record density. In this article we represent the holographic memory system based on digital synthesis of amplitude one-dimensional (1D) Fourier transform holograms and the multiplexed record of these holograms onto the holographic carrier using optical projection scheme. 1D Fourier transform holograms are very sensitive to orientation of the anamorphic optical element (cylindrical lens) that is required for encoded data object reconstruction. The multiplex record of several holograms with different orientation in an optical projection scheme allowed reconstruction of the data object from each hologram by rotating the cylindrical lens on the corresponding angle. Also, we discuss two optical schemes for the recorded holograms readout: a full-page readout system and line-by-line readout system. We consider the benefits of both systems and present the results of experimental modeling of 1D Fourier holograms nonmultiplex and multiplex record and reconstruction.

  19. Logic and memory concepts for all-magnetic computing based on transverse domain walls

    International Nuclear Information System (INIS)

    Vandermeulen, J; Van de Wiele, B; Dupré, L; Van Waeyenberge, B

    2015-01-01

    We introduce a non-volatile digital logic and memory concept in which the binary data is stored in the transverse magnetic domain walls present in in-plane magnetized nanowires with sufficiently small cross sectional dimensions. We assign the digital bit to the two possible orientations of the transverse domain wall. Numerical proofs-of-concept are presented for a NOT-, AND- and OR-gate, a FAN-out as well as a reading and writing device. Contrary to the chirality based vortex domain wall logic gates introduced in Omari and Hayward (2014 Phys. Rev. Appl. 2 044001), the presented concepts remain applicable when miniaturized and are driven by electrical currents, making the technology compatible with the in-plane racetrack memory concept. The individual devices can be easily combined to logic networks working with clock speeds that scale linearly with decreasing design dimensions. This opens opportunities to an all-magnetic computing technology where the digital data is stored and processed under the same magnetic representation. (paper)

  20. Computational Thermodynamics and Kinetics-Based ICME Framework for High-Temperature Shape Memory Alloys

    Science.gov (United States)

    Arróyave, Raymundo; Talapatra, Anjana; Johnson, Luke; Singh, Navdeep; Ma, Ji; Karaman, Ibrahim

    2015-11-01

    Over the last decade, considerable interest in the development of High-Temperature Shape Memory Alloys (HTSMAs) for solid-state actuation has increased dramatically as key applications in the aerospace and automotive industry demand actuation temperatures well above those of conventional SMAs. Most of the research to date has focused on establishing the (forward) connections between chemistry, processing, (micro)structure, properties, and performance. Much less work has been dedicated to the development of frameworks capable of addressing the inverse problem of establishing necessary chemistry and processing schedules to achieve specific performance goals. Integrated Computational Materials Engineering (ICME) has emerged as a powerful framework to address this problem, although it has yet to be applied to the development of HTSMAs. In this paper, the contributions of computational thermodynamics and kinetics to ICME of HTSMAs are described. Some representative examples of the use of computational thermodynamics and kinetics to understand the phase stability and microstructural evolution in HTSMAs are discussed. Some very recent efforts at combining both to assist in the design of HTSMAs and limitations to the full implementation of ICME frameworks for HTSMA development are presented.

  1. The Case for Higher Computational Density in the Memory-Bound FDTD Method within Multicore Environments

    Directory of Open Access Journals (Sweden)

    Mohammed F. Hadi

    2012-01-01

    Full Text Available It is argued here that more accurate though more compute-intensive alternate algorithms to certain computational methods which are deemed too inefficient and wasteful when implemented within serial codes can be more efficient and cost-effective when implemented in parallel codes designed to run on today's multicore and many-core environments. This argument is most germane to methods that involve large data sets with relatively limited computational density—in other words, algorithms with small ratios of floating point operations to memory accesses. The examples chosen here to support this argument represent a variety of high-order finite-difference time-domain algorithms. It will be demonstrated that a three- to eightfold increase in floating-point operations due to higher-order finite-differences will translate to only two- to threefold increases in actual run times using either graphical or central processing units of today. It is hoped that this argument will convince researchers to revisit certain numerical techniques that have long been shelved and reevaluate them for multicore usability.

  2. The Role of Distributed Computing in Big Data Science: Case Studies in Forensics and Bioinformatics

    OpenAIRE

    Roscigno, Gianluca

    2016-01-01

    2014 - 2015 The era of Big Data is leading the generation of large amounts of data, which require storage and analysis capabilities that can be only ad- dressed by distributed computing systems. To facilitate large-scale distributed computing, many programming paradigms and frame- works have been proposed, such as MapReduce and Apache Hadoop, which transparently address some issues of distributed systems and hide most of their technical details. Hadoop is curren...

  3. Prediction of the filtrate particle size distribution from the pore size distribution in membrane filtration: Numerical correlations from computer simulations

    Science.gov (United States)

    Marrufo-Hernández, Norma Alejandra; Hernández-Guerrero, Maribel; Nápoles-Duarte, José Manuel; Palomares-Báez, Juan Pedro; Chávez-Rojo, Marco Antonio

    2018-03-01

    We present a computational model that describes the diffusion of a hard spheres colloidal fluid through a membrane. The membrane matrix is modeled as a series of flat parallel planes with circular pores of different sizes and random spatial distribution. This model was employed to determine how the size distribution of the colloidal filtrate depends on the size distributions of both, the particles in the feed and the pores of the membrane, as well as to describe the filtration kinetics. A Brownian dynamics simulation study considering normal distributions was developed in order to determine empirical correlations between the parameters that characterize these distributions. The model can also be extended to other distributions such as log-normal. This study could, therefore, facilitate the selection of membranes for industrial or scientific filtration processes once the size distribution of the feed is known and the expected characteristics in the filtrate have been defined.

  4. Asynchronous Distributed Execution of Fixpoint-Based Computational Fields

    DEFF Research Database (Denmark)

    Lluch Lafuente, Alberto; Loreti, Michele; Montanari, Ugo

    2017-01-01

    . Computational fields are a key ingredient of aggregate programming, a promising software engineering methodology particularly relevant for the Internet of Things. In our approach, space topology is represented by a fixed graph-shaped field, namely a network with attributes on both nodes and arcs, where arcs...

  5. Parallel distributed computing in modeling of the nanomaterials production technologies

    NARCIS (Netherlands)

    Krzhizhanovskaya, V.V.; Korkhov, V.V.; Zatevakhin, M.A.; Gorbachev, Y.E.

    2008-01-01

    Simulation of physical and chemical processes occurring in the nanomaterial production technologies is a computationally challenging problem, due to the great number of coupled processes, time and length scales to be taken into account. To solve such complex problems with a good level of detail in a

  6. Distributed storage and cloud computing: a test case

    International Nuclear Information System (INIS)

    Piano, S; Ricca, G Delia

    2014-01-01

    Since 2003 the computing farm hosted by the INFN Tier3 facility in Trieste supports the activities of many scientific communities. Hundreds of jobs from 45 different VOs, including those of the LHC experiments, are processed simultaneously. Given that normally the requirements of the different computational communities are not synchronized, the probability that at any given time the resources owned by one of the participants are not fully utilized is quite high. A balanced compensation should in principle allocate the free resources to other users, but there are limits to this mechanism. In fact, the Trieste site may not hold the amount of data needed to attract enough analysis jobs, and even in that case there could be a lack of bandwidth for their access. The Trieste ALICE and CMS computing groups, in collaboration with other Italian groups, aim to overcome the limitations of existing solutions using two approaches: sharing the data among all the participants taking full advantage of GARR-X wide area networks (10 GB/s) and integrating the resources dedicated to batch analysis with the ones reserved for dynamic interactive analysis, through modern solutions as cloud computing.

  7. GridFactory - Distributed computing on ephemeral resources

    DEFF Research Database (Denmark)

    Orellana, Frederik; Niinimaki, Marko

    2011-01-01

    A novel batch system for high throughput computing is presented. The system is specifically designed to leverage virtualization and web technology to facilitate deployment on cloud and other ephemeral resources. In particular, it implements a security model suited for forming collaborations...

  8. Computation of Universal Objects for Distributions Over Co-Trees

    DEFF Research Database (Denmark)

    Petersen, Henrik Densing; Topsøe, Flemming

    2012-01-01

    for the model or, equivalently, the corresponding universal code, can be determined exactly via an algorithm of low complexity. Natural relations to problems on the computation of capacity and on the determination of information projections are established. More surprisingly, a direct connection to a problem...

  9. Polytopol computing for multi-core and distributed systems

    Science.gov (United States)

    Spaanenburg, Henk; Spaanenburg, Lambert; Ranefors, Johan

    2009-05-01

    Multi-core computing provides new challenges to software engineering. The paper addresses such issues in the general setting of polytopol computing, that takes multi-core problems in such widely differing areas as ambient intelligence sensor networks and cloud computing into account. It argues that the essence lies in a suitable allocation of free moving tasks. Where hardware is ubiquitous and pervasive, the network is virtualized into a connection of software snippets judiciously injected to such hardware that a system function looks as one again. The concept of polytopol computing provides a further formalization in terms of the partitioning of labor between collector and sensor nodes. Collectors provide functions such as a knowledge integrator, awareness collector, situation displayer/reporter, communicator of clues and an inquiry-interface provider. Sensors provide functions such as anomaly detection (only communicating singularities, not continuous observation), they are generally powered or self-powered, amorphous (not on a grid) with generation-and-attrition, field re-programmable, and sensor plug-and-play-able. Together the collector and the sensor are part of the skeleton injector mechanism, added to every node, and give the network the ability to organize itself into some of many topologies. Finally we will discuss a number of applications and indicate how a multi-core architecture supports the security aspects of the skeleton injector.

  10. Lightgrid-an agile distributed computing architecture for Geant4

    International Nuclear Information System (INIS)

    Young, Jason; Perry, John O.; Jevremovic, Tatjana

    2010-01-01

    A light weight grid based computing architecture has been developed to accelerate Geant4 computations on a variety of network architectures. This new software is called LightGrid. LightGrid has a variety of features designed to overcome current limitations on other grid based computing platforms, more specifically, smaller network architectures. By focusing on smaller, local grids, LightGrid is able to simplify the grid computing process with minimal changes to existing Geant4 code. LightGrid allows for integration between Geant4 and MySQL, which both increases flexibility in the grid as well as provides a faster, reliable, and more portable method for accessing results than traditional data storage systems. This unique method of data acquisition allows for more fault tolerant runs as well as instant results from simulations as they occur. The performance increases brought along by using LightGrid allow simulation times to be decreased linearly. LightGrid also allows for pseudo-parallelization with minimal Geant4 code changes.

  11. Unwrapping ADMM: Efficient Distributed Computing via Transpose Reduction

    Science.gov (United States)

    2016-05-11

    applications of the Split Bregman method: Segmen- tation and surface reconstruction. J. Sci. Comput., 45:272– 293, October 2010. [17] Stephen Boyd and...Garcia, Gretchen Greene, Fabrizia Guglielmetti, Christopher Hanley, George Hawkins , et al. The second-generation guide star cata- log: description

  12. Computational Platform About Amazon Web Services (Aws Distributed Rendering

    Directory of Open Access Journals (Sweden)

    Gabriel Rojas-Albarracín

    2017-09-01

    Full Text Available Today has created a dynamic in which people require higher image quality in different media formats (games, movies, animations. Further definition usually requires image processing larger; this brings the need for increased computing power. This paper presents a case study in which the implementation of a low-cost platform on the Amazon cloud for parallel processing of images and animation.

  13. Memory architecture for efficient utilization of SDRAM: a case study of the computation/memory access trade-off

    DEFF Research Database (Denmark)

    Gleerup, Thomas Møller; Holten-Lund, Hans Erik; Madsen, Jan

    2000-01-01

    . In software, forward differencing is usually better, but in this hardware implementation, the trade-off has made it possible to develop a very regular memory architecture with a buffering system, which can reach 95% bandwidth utilization using off-the-shelf SDRAM, This is achieved by changing the algorithm......This paper discusses the trade-off between calculations and memory accesses in a 3D graphics tile renderer for visualization of data from medical scanners. The performance requirement of this application is a frame rate of 25 frames per second when rendering 3D models with 2 million triangles, i...... to use a memory access strategy with write-only and read-only phases, and a buffering system, which uses round-robin bank write-access combined with burst read-access....

  14. Distinctive Features Hold a Privileged Status in the Computation of Word Meaning: Implications for Theories of Semantic Memory

    Science.gov (United States)

    Cree, George S.; McNorgan, Chris; McRae, Ken

    2006-01-01

    The authors present data from 2 feature verification experiments designed to determine whether distinctive features have a privileged status in the computation of word meaning. They use an attractor-based connectionist model of semantic memory to derive predictions for the experiments. Contrary to central predictions of the conceptual structure…

  15. Evaluation of a Connectionless NoC for a Real-Time Distributed Shared Memory Many-Core System

    NARCIS (Netherlands)

    Rutgers, J.H.; Bekooij, Marco Jan Gerrit; Smit, Gerardus Johannes Maria

    2012-01-01

    Real-time embedded systems like smartphones tend to comprise an ever increasing number of processing cores. For scalability and the need for guaranteed performance, the use of a connection-oriented network-on-chip (NoC) is advocated. Furthermore, a distributed shared memory architecture is preferred

  16. Distributed cerebellar plasticity implements generalized multiple-scale memory components in real-robot sensorimotor tasks

    Directory of Open Access Journals (Sweden)

    Claudia eCasellato

    2015-02-01

    Full Text Available The cerebellum plays a crucial role in motor learning and it acts as a predictive controller. Modeling it and embedding it into sensorimotor tasks allows us to create functional links between plasticity mechanisms, neural circuits and behavioral learning. Moreover, if applied to real-time control of a neurorobot, the cerebellar model has to deal with a real noisy and changing environment, thus showing its robustness and effectiveness in learning. A biologically inspired cerebellar model with distributed plasticity, both at cortical and nuclear sites, has been used. Two cerebellum-mediated paradigms have been designed: an associative Pavlovian task and a vestibulo-ocular reflex, with multiple sessions of acquisition and extinction and with different stimuli and perturbation patterns. The cerebellar controller succeeded to generate conditioned responses and finely tuned eye movement compensation, thus reproducing human-like behaviors. Through a productive plasticity transfer from cortical to nuclear sites, the distributed cerebellar controller showed in both tasks the capability to optimize learning on multiple time-scales, to store motor memory and to effectively adapt to dynamic ranges of stimuli.

  17. Modern computer networks and distributed intelligence in accelerator controls

    International Nuclear Information System (INIS)

    Briegel, C.

    1991-01-01

    Appropriate hardware and software network protocols are surveyed for accelerator control environments. Accelerator controls network topologies are discussed with respect to the following criteria: vertical versus horizontal and distributed versus centralized. Decision-making considerations are provided for accelerator network architecture specification. Current trends and implementations at Fermilab are discussed

  18. Application of a distributed network in computational fluid dynamic simulations

    Science.gov (United States)

    Deshpande, Manish; Feng, Jinzhang; Merkle, Charles L.; Deshpande, Ashish

    1994-01-01

    A general-purpose 3-D, incompressible Navier-Stokes algorithm is implemented on a network of concurrently operating workstations using parallel virtual machine (PVM) and compared with its performance on a CRAY Y-MP and on an Intel iPSC/860. The problem is relatively computationally intensive, and has a communication structure based primarily on nearest-neighbor communication, making it ideally suited to message passing. Such problems are frequently encountered in computational fluid dynamics (CDF), and their solution is increasingly in demand. The communication structure is explicitly coded in the implementation to fully exploit the regularity in message passing in order to produce a near-optimal solution. Results are presented for various grid sizes using up to eight processors.

  19. Integration of the Chinese HPC Grid in ATLAS Distributed Computing

    Science.gov (United States)

    Filipčič, A.; ATLAS Collaboration

    2017-10-01

    Fifteen Chinese High-Performance Computing sites, many of them on the TOP500 list of most powerful supercomputers, are integrated into a common infrastructure providing coherent access to a user through an interface based on a RESTful interface called SCEAPI. These resources have been integrated into the ATLAS Grid production system using a bridge between ATLAS and SCEAPI which translates the authorization and job submission protocols between the two environments. The ARC Computing Element (ARC-CE) forms the bridge using an extended batch system interface to allow job submission to SCEAPI. The ARC-CE was setup at the Institute for High Energy Physics, Beijing, in order to be as close as possible to the SCEAPI front-end interface at the Computing Network Information Center, also in Beijing. This paper describes the technical details of the integration between ARC-CE and SCEAPI and presents results so far with two supercomputer centers, Tianhe-IA and ERA. These two centers have been the pilots for ATLAS Monte Carlo Simulation in SCEAPI and have been providing CPU power since fall 2015.

  20. Integration of the Chinese HPC Grid in ATLAS Distributed Computing

    CERN Document Server

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

    2016-01-01

    Fifteen Chinese High Performance Computing sites, many of them on the TOP500 list of most powerful supercomputers, are integrated into a common infrastructure providing coherent access to a user through an interface based on a RESTful interface called SCEAPI. These resources have been integrated into the ATLAS Grid production system using a bridge between ATLAS and SCEAPI which translates the authorization and job submission protocols between the two environments. The ARC Computing Element (ARC CE) forms the bridge using an extended batch system interface to allow job submission to SCEAPI. The ARC CE was setup at the Institute for High Energy Physics, Beijing, in order to be as close as possible to the SCEAPI front-end interface at the Computing Network Information Center, also in Beijing. This paper describes the technical details of the integration between ARC CE and SCEAPI and presents results so far with two supercomputer centers, Tianhe-IA and ERA. These two centers have been the pilots for ATLAS Monte C...