Parallel computing of physical maps--a comparative study in SIMD and MIMD parallelism.
Bhandarkar, S M; Chirravuri, S; Arnold, J
1996-01-01
Ordering clones from a genomic library into physical maps of whole chromosomes presents a central computational problem in genetics. Chromosome reconstruction via clone ordering is usually isomorphic to the NP-complete Optimal Linear Arrangement problem. Parallel SIMD and MIMD algorithms for simulated annealing based on Markov chain distribution are proposed and applied to the problem of chromosome reconstruction via clone ordering. Perturbation methods and problem-specific annealing heuristics are proposed and described. The SIMD algorithms are implemented on a 2048 processor MasPar MP-2 system which is an SIMD 2-D toroidal mesh architecture whereas the MIMD algorithms are implemented on an 8 processor Intel iPSC/860 which is an MIMD hypercube architecture. A comparative analysis of the various SIMD and MIMD algorithms is presented in which the convergence, speedup, and scalability characteristics of the various algorithms are analyzed and discussed. On a fine-grained, massively parallel SIMD architecture with a low synchronization overhead such as the MasPar MP-2, a parallel simulated annealing algorithm based on multiple periodically interacting searches performs the best. For a coarse-grained MIMD architecture with high synchronization overhead such as the Intel iPSC/860, a parallel simulated annealing algorithm based on multiple independent searches yields the best results. In either case, distribution of clonal data across multiple processors is shown to exacerbate the tendency of the parallel simulated annealing algorithm to get trapped in a local optimum.
International Nuclear Information System (INIS)
Pic, Marc Michel
1995-01-01
Parallel programming covers task-parallelism and data-parallelism. Many problems need both parallelisms. Multi-SIMD computers allow hierarchical approach of these parallelisms. The T++ language, based on C++, is dedicated to exploit Multi-SIMD computers using a programming paradigm which is an extension of array-programming to tasks managing. Our language introduced array of independent tasks to achieve separately (MIMD), on subsets of processors of identical behaviour (SIMD), in order to translate the hierarchical inclusion of data-parallelism in task-parallelism. To manipulate in a symmetrical way tasks and data we propose meta-operations which have the same behaviour on tasks arrays and on data arrays. We explain how to implement this language on our parallel computer SYMPHONIE in order to profit by the locally-shared memory, by the hardware virtualization, and by the multiplicity of communications networks. We analyse simultaneously a typical application of such architecture. Finite elements scheme for Fluid mechanic needs powerful parallel computers and requires large floating points abilities. Lattice gases is an alternative to such simulations. Boolean lattice bases are simple, stable, modular, need to floating point computation, but include numerical noise. Boltzmann lattice gases present large precision of computation, but needs floating points and are only locally stable. We propose a new scheme, called multi-bit, who keeps the advantages of each boolean model to which it is applied, with large numerical precision and reduced noise. Experiments on viscosity, physical behaviour, noise reduction and spurious invariants are shown and implementation techniques for parallel Multi-SIMD computers detailed. (author) [fr
Monte Carlo simulations on SIMD computer architectures
International Nuclear Information System (INIS)
Burmester, C.P.; Gronsky, R.; Wille, L.T.
1992-01-01
In this paper algorithmic considerations regarding the implementation of various materials science applications of the Monte Carlo technique to single instruction multiple data (SIMD) computer architectures are presented. In particular, implementation of the Ising model with nearest, next nearest, and long range screened Coulomb interactions on the SIMD architecture MasPar MP-1 (DEC mpp-12000) series of massively parallel computers is demonstrated. Methods of code development which optimize processor array use and minimize inter-processor communication are presented including lattice partitioning and the use of processor array spanning tree structures for data reduction. Both geometric and algorithmic parallel approaches are utilized. Benchmarks in terms of Monte Carl updates per second for the MasPar architecture are presented and compared to values reported in the literature from comparable studies on other architectures
Parallel algorithms on the ASTRA SIMD machine
International Nuclear Information System (INIS)
Odor, G.; Rohrbach, F.; Vesztergombi, G.; Varga, G.; Tatrai, F.
1996-01-01
In view of the tremendous computing power jump of modern RISC processors the interest in parallel computing seems to be thinning out. Why use a complicated system of parallel processors, if the problem can be solved by a single powerful micro-chip. It is a general law, however, that exponential growth will always end by some kind of a saturation, and then parallelism will again become a hot topic. We try to prepare ourselves for this eventuality. The MPPC project started in 1990 in the keydeys of parallelism and produced four ASTRA machines (presented at CHEP's 92) with 4k processors (which are expandable to 16k) based on yesterday's chip-technology (chip presented at CHEP'91). These machines now provide excellent test-beds for algorithmic developments in a complete, real environment. We are developing for example fast-pattern recognition algorithms which could be used in high-energy physics experiments at the LHC (planned to be operational after 2004 at CERN) for triggering and data reduction. The basic feature of our ASP (Associate String Processor) approach is to use extremely simple (thus very cheap) processor elements but in huge quantities (up to millions of processors) connected together by a very simple string-like communication chain. In this paper we present powerful algorithms based on this architecture indicating the performance perspectives if the hardware quality reaches present or even future technology levels. (author)
Flexbar 3.0 - SIMD and multicore parallelization.
Roehr, Johannes T; Dieterich, Christoph; Reinert, Knut
2017-09-15
High-throughput sequencing machines can process many samples in a single run. For Illumina systems, sequencing reads are barcoded with an additional DNA tag that is contained in the respective sequencing adapters. The recognition of barcode and adapter sequences is hence commonly needed for the analysis of next-generation sequencing data. Flexbar performs demultiplexing based on barcodes and adapter trimming for such data. The massive amounts of data generated on modern sequencing machines demand that this preprocessing is done as efficiently as possible. We present Flexbar 3.0, the successor of the popular program Flexbar. It employs now twofold parallelism: multi-threading and additionally SIMD vectorization. Both types of parallelism are used to speed-up the computation of pair-wise sequence alignments, which are used for the detection of barcodes and adapters. Furthermore, new features were included to cover a wide range of applications. We evaluated the performance of Flexbar based on a simulated sequencing dataset. Our program outcompetes other tools in terms of speed and is among the best tools in the presented quality benchmark. https://github.com/seqan/flexbar. johannes.roehr@fu-berlin.de or knut.reinert@fu-berlin.de. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com
Characterization of robotics parallel algorithms and mapping onto a reconfigurable SIMD machine
Lee, C. S. G.; Lin, C. T.
1989-01-01
The kinematics, dynamics, Jacobian, and their corresponding inverse computations are six essential problems in the control of robot manipulators. Efficient parallel algorithms for these computations are discussed and analyzed. Their characteristics are identified and a scheme on the mapping of these algorithms to a reconfigurable parallel architecture is presented. Based on the characteristics including type of parallelism, degree of parallelism, uniformity of the operations, fundamental operations, data dependencies, and communication requirement, it is shown that most of the algorithms for robotic computations possess highly regular properties and some common structures, especially the linear recursive structure. Moreover, they are well-suited to be implemented on a single-instruction-stream multiple-data-stream (SIMD) computer with reconfigurable interconnection network. The model of a reconfigurable dual network SIMD machine with internal direct feedback is introduced. A systematic procedure internal direct feedback is introduced. A systematic procedure to map these computations to the proposed machine is presented. A new scheduling problem for SIMD machines is investigated and a heuristic algorithm, called neighborhood scheduling, that reorders the processing sequence of subtasks to reduce the communication time is described. Mapping results of a benchmark algorithm are illustrated and discussed.
Comparing the performance of SIMD computers by running large air pollution models
DEFF Research Database (Denmark)
Brown, J.; Hansen, Per Christian; Wasniewski, J.
1996-01-01
To compare the performance and use of three massively parallel SIMD computers, we implemented a large air pollution model on these computers. Using a realistic large-scale model, we gained detailed insight about the performance of the computers involved when used to solve large-scale scientific...... problems that involve several types of numerical computations. The computers used in our study are the Connection Machines CM-200 and CM-5, and the MasPar MP-2216...
Wakefield calculations on parallel computers
International Nuclear Information System (INIS)
Schoessow, P.
1990-01-01
The use of parallelism in the solution of wakefield problems is illustrated for two different computer architectures (SIMD and MIMD). Results are given for finite difference codes which have been implemented on a Connection Machine and an Alliant FX/8 and which are used to compute wakefields in dielectric loaded structures. Benchmarks on code performance are presented for both cases. 4 refs., 3 figs., 2 tabs
The 2nd Symposium on the Frontiers of Massively Parallel Computations
Mills, Ronnie (Editor)
1988-01-01
Programming languages, computer graphics, neural networks, massively parallel computers, SIMD architecture, algorithms, digital terrain models, sort computation, simulation of charged particle transport on the massively parallel processor and image processing are among the topics discussed.
1982-01-01
Parallel Computations focuses on parallel computation, with emphasis on algorithms used in a variety of numerical and physical applications and for many different types of parallel computers. Topics covered range from vectorization of fast Fourier transforms (FFTs) and of the incomplete Cholesky conjugate gradient (ICCG) algorithm on the Cray-1 to calculation of table lookups and piecewise functions. Single tridiagonal linear systems and vectorized computation of reactive flow are also discussed.Comprised of 13 chapters, this volume begins by classifying parallel computers and describing techn
Performance of Air Pollution Models on Massively Parallel Computers
DEFF Research Database (Denmark)
Brown, John; Hansen, Per Christian; Wasniewski, Jerzy
1996-01-01
To compare the performance and use of three massively parallel SIMD computers, we implemented a large air pollution model on the computers. Using a realistic large-scale model, we gain detailed insight about the performance of the three computers when used to solve large-scale scientific problems...
International Nuclear Information System (INIS)
Jejcic, A.; Maillard, J.; Maurel, G.; Silva, J.; Wolff-Bacha, F.
1997-01-01
The work in the field of parallel processing has developed as research activities using several numerical Monte Carlo simulations related to basic or applied current problems of nuclear and particle physics. For the applications utilizing the GEANT code development or improvement works were done on parts simulating low energy physical phenomena like radiation, transport and interaction. The problem of actinide burning by means of accelerators was approached using a simulation with the GEANT code. A program of neutron tracking in the range of low energies up to the thermal region has been developed. It is coupled to the GEANT code and permits in a single pass the simulation of a hybrid reactor core receiving a proton burst. Other works in this field refers to simulations for nuclear medicine applications like, for instance, development of biological probes, evaluation and characterization of the gamma cameras (collimators, crystal thickness) as well as the method for dosimetric calculations. Particularly, these calculations are suited for a geometrical parallelization approach especially adapted to parallel machines of the TN310 type. Other works mentioned in the same field refer to simulation of the electron channelling in crystals and simulation of the beam-beam interaction effect in colliders. The GEANT code was also used to simulate the operation of germanium detectors designed for natural and artificial radioactivity monitoring of environment
Automatic SIMD vectorization of SSA-based control flow graphs
Karrenberg, Ralf
2015-01-01
Ralf Karrenberg presents Whole-Function Vectorization (WFV), an approach that allows a compiler to automatically create code that exploits data-parallelism using SIMD instructions. Data-parallel applications such as particle simulations, stock option price estimation or video decoding require the same computations to be performed on huge amounts of data. Without WFV, one processor core executes a single instance of a data-parallel function. WFV transforms the function to execute multiple instances at once using SIMD instructions. The author describes an advanced WFV algorithm that includes a v
Implementation of a Monte Carlo algorithm for neutron transport on a massively parallel SIMD machine
International Nuclear Information System (INIS)
Baker, R.S.
1992-01-01
We present some results from the recent adaptation of a vectorized Monte Carlo algorithm to a massively parallel architecture. The performance of the algorithm on a single processor Cray Y-MP and a Thinking Machine Corporations CM-2 and CM-200 is compared for several test problems. The results show that significant speedups are obtainable for vectorized Monte Carlo algorithms on massively parallel machines, even when the algorithms are applied to realistic problems which require extensive variance reduction. However, the architecture of the Connection Machine does place some limitations on the regime in which the Monte Carlo algorithm may be expected to perform well
Implementation of a Monte Carlo algorithm for neutron transport on a massively parallel SIMD machine
International Nuclear Information System (INIS)
Baker, R.S.
1993-01-01
We present some results from the recent adaptation of a vectorized Monte Carlo algorithm to a massively parallel architecture. The performance of the algorithm on a single processor Cray Y-MP and a Thinking Machine Corporations CM-2 and CM-200 is compared for several test problems. The results show that significant speedups are obtainable for vectorized Monte Carlo algorithms on massively parallel machines, even when the algorithms are applied to realistic problems which require extensive variance reduction. However, the architecture of the Connection Machine does place some limitations on the regime in which the Monte Carlo algorithm may be expected to perform well. (orig.)
Parallel Computing:. Some Activities in High Energy Physics
Willers, Ian
This paper examines some activities in High Energy Physics that utilise parallel computing. The topic includes all computing from the proposed SIMD front end detectors, the farming applications, high-powered RISC processors and the large machines in the computer centers. We start by looking at the motivation behind using parallelism for general purpose computing. The developments around farming are then described from its simplest form to the more complex system in Fermilab. Finally, there is a list of some developments that are happening close to the experiments.
Parallel computing and networking; Heiretsu keisanki to network
Energy Technology Data Exchange (ETDEWEB)
Asakawa, E; Tsuru, T [Japan National Oil Corp., Tokyo (Japan); Matsuoka, T [Japan Petroleum Exploration Co. Ltd., Tokyo (Japan)
1996-05-01
This paper describes the trend of parallel computers used in geophysical exploration. Around 1993 was the early days when the parallel computers began to be used for geophysical exploration. Classification of these computers those days was mainly MIMD (multiple instruction stream, multiple data stream), SIMD (single instruction stream, multiple data stream) and the like. Parallel computers were publicized in the 1994 meeting of the Geophysical Exploration Society as a `high precision imaging technology`. Concerning the library of parallel computers, there was a shift to PVM (parallel virtual machine) in 1993 and to MPI (message passing interface) in 1995. In addition, the compiler of FORTRAN90 was released with support implemented for data parallel and vector computers. In 1993, networks used were Ethernet, FDDI, CDDI and HIPPI. In 1995, the OC-3 products under ATM began to propagate. However, ATM remains to be an interoffice high speed network because the ATM service has not spread yet for the public network. 1 ref.
Fox, Geoffrey C; Messina, Guiseppe C
2014-01-01
A clear illustration of how parallel computers can be successfully appliedto large-scale scientific computations. This book demonstrates how avariety of applications in physics, biology, mathematics and other scienceswere implemented on real parallel computers to produce new scientificresults. It investigates issues of fine-grained parallelism relevant forfuture supercomputers with particular emphasis on hypercube architecture. The authors describe how they used an experimental approach to configuredifferent massively parallel machines, design and implement basic systemsoftware, and develop
Electromagnetic Physics Models for Parallel Computing Architectures
International Nuclear Information System (INIS)
Amadio, G; Bianchini, C; Iope, R; Ananya, A; Apostolakis, J; Aurora, A; Bandieramonte, M; Brun, R; Carminati, F; Gheata, A; Gheata, M; Goulas, I; Nikitina, T; Bhattacharyya, A; Mohanty, A; Canal, P; Elvira, D; Jun, S Y; Lima, G; Duhem, L
2016-01-01
The recent emergence of hardware architectures characterized by many-core or accelerated processors has opened new opportunities for concurrent programming models taking advantage of both SIMD and SIMT architectures. GeantV, a next generation detector simulation, has been designed to exploit both the vector capability of mainstream CPUs and multi-threading capabilities of coprocessors including NVidia GPUs and Intel Xeon Phi. The characteristics of these architectures are very different in terms of the vectorization depth and type of parallelization needed to achieve optimal performance. In this paper we describe implementation of electromagnetic physics models developed for parallel computing architectures as a part of the GeantV project. Results of preliminary performance evaluation and physics validation are presented as well. (paper)
Electromagnetic Physics Models for Parallel Computing Architectures
Amadio, G.; Ananya, A.; Apostolakis, J.; Aurora, A.; Bandieramonte, M.; Bhattacharyya, A.; Bianchini, C.; Brun, R.; Canal, P.; Carminati, F.; Duhem, L.; Elvira, D.; Gheata, A.; Gheata, M.; Goulas, I.; Iope, R.; Jun, S. Y.; Lima, G.; Mohanty, A.; Nikitina, T.; Novak, M.; Pokorski, W.; Ribon, A.; Seghal, R.; Shadura, O.; Vallecorsa, S.; Wenzel, S.; Zhang, Y.
2016-10-01
The recent emergence of hardware architectures characterized by many-core or accelerated processors has opened new opportunities for concurrent programming models taking advantage of both SIMD and SIMT architectures. GeantV, a next generation detector simulation, has been designed to exploit both the vector capability of mainstream CPUs and multi-threading capabilities of coprocessors including NVidia GPUs and Intel Xeon Phi. The characteristics of these architectures are very different in terms of the vectorization depth and type of parallelization needed to achieve optimal performance. In this paper we describe implementation of electromagnetic physics models developed for parallel computing architectures as a part of the GeantV project. Results of preliminary performance evaluation and physics validation are presented as well.
Computation and parallel implementation for early vision
Gualtieri, J. Anthony
1990-01-01
The problem of early vision is to transform one or more retinal illuminance images-pixel arrays-to image representations built out of such primitive visual features such as edges, regions, disparities, and clusters. These transformed representations form the input to later vision stages that perform higher level vision tasks including matching and recognition. Researchers developed algorithms for: (1) edge finding in the scale space formulation; (2) correlation methods for computing matches between pairs of images; and (3) clustering of data by neural networks. These algorithms are formulated for parallel implementation of SIMD machines, such as the Massively Parallel Processor, a 128 x 128 array processor with 1024 bits of local memory per processor. For some cases, researchers can show speedups of three orders of magnitude over serial implementations.
Energy Technology Data Exchange (ETDEWEB)
1991-10-23
An account of the Caltech Concurrent Computation Program (C{sup 3}P), a five year project that focused on answering the question: Can parallel computers be used to do large-scale scientific computations '' As the title indicates, the question is answered in the affirmative, by implementing numerous scientific applications on real parallel computers and doing computations that produced new scientific results. In the process of doing so, C{sup 3}P helped design and build several new computers, designed and implemented basic system software, developed algorithms for frequently used mathematical computations on massively parallel machines, devised performance models and measured the performance of many computers, and created a high performance computing facility based exclusively on parallel computers. While the initial focus of C{sup 3}P was the hypercube architecture developed by C. Seitz, many of the methods developed and lessons learned have been applied successfully on other massively parallel architectures.
Parallelism in matrix computations
Gallopoulos, Efstratios; Sameh, Ahmed H
2016-01-01
This book is primarily intended as a research monograph that could also be used in graduate courses for the design of parallel algorithms in matrix computations. It assumes general but not extensive knowledge of numerical linear algebra, parallel architectures, and parallel programming paradigms. The book consists of four parts: (I) Basics; (II) Dense and Special Matrix Computations; (III) Sparse Matrix Computations; and (IV) Matrix functions and characteristics. Part I deals with parallel programming paradigms and fundamental kernels, including reordering schemes for sparse matrices. Part II is devoted to dense matrix computations such as parallel algorithms for solving linear systems, linear least squares, the symmetric algebraic eigenvalue problem, and the singular-value decomposition. It also deals with the development of parallel algorithms for special linear systems such as banded ,Vandermonde ,Toeplitz ,and block Toeplitz systems. Part III addresses sparse matrix computations: (a) the development of pa...
Morse, H Stephen
1994-01-01
Practical Parallel Computing provides information pertinent to the fundamental aspects of high-performance parallel processing. This book discusses the development of parallel applications on a variety of equipment.Organized into three parts encompassing 12 chapters, this book begins with an overview of the technology trends that converge to favor massively parallel hardware over traditional mainframes and vector machines. This text then gives a tutorial introduction to parallel hardware architectures. Other chapters provide worked-out examples of programs using several parallel languages. Thi
Algorithmically specialized parallel computers
Snyder, Lawrence; Gannon, Dennis B
1985-01-01
Algorithmically Specialized Parallel Computers focuses on the concept and characteristics of an algorithmically specialized computer.This book discusses the algorithmically specialized computers, algorithmic specialization using VLSI, and innovative architectures. The architectures and algorithms for digital signal, speech, and image processing and specialized architectures for numerical computations are also elaborated. Other topics include the model for analyzing generalized inter-processor, pipelined architecture for search tree maintenance, and specialized computer organization for raster
Parallel reservoir simulator computations
International Nuclear Information System (INIS)
Hemanth-Kumar, K.; Young, L.C.
1995-01-01
The adaptation of a reservoir simulator for parallel computations is described. The simulator was originally designed for vector processors. It performs approximately 99% of its calculations in vector/parallel mode and relative to scalar calculations it achieves speedups of 65 and 81 for black oil and EOS simulations, respectively on the CRAY C-90
Centaure: an heterogeneous parallel architecture for computer vision
International Nuclear Information System (INIS)
Peythieux, Marc
1997-01-01
This dissertation deals with the architecture of parallel computers dedicated to computer vision. In the first chapter, the problem to be solved is presented, as well as the architecture of the Sympati and Symphonie computers, on which this work is based. The second chapter is about the state of the art of computers and integrated processors that can execute computer vision and image processing codes. The third chapter contains a description of the architecture of Centaure. It has an heterogeneous structure: it is composed of a multiprocessor system based on Analog Devices ADSP21060 Sharc digital signal processor, and of a set of Symphonie computers working in a multi-SIMD fashion. Centaure also has a modular structure. Its basic node is composed of one Symphonie computer, tightly coupled to a Sharc thanks to a dual ported memory. The nodes of Centaure are linked together by the Sharc communication links. The last chapter deals with a performance validation of Centaure. The execution times on Symphonie and on Centaure of a benchmark which is typical of industrial vision, are presented and compared. In the first place, these results show that the basic node of Centaure allows a faster execution than Symphonie, and that increasing the size of the tested computer leads to a better speed-up with Centaure than with Symphonie. In the second place, these results validate the choice of running the low level structure of Centaure in a multi- SIMD fashion. (author) [fr
Algorithms for parallel computers
International Nuclear Information System (INIS)
Churchhouse, R.F.
1985-01-01
Until relatively recently almost all the algorithms for use on computers had been designed on the (usually unstated) assumption that they were to be run on single processor, serial machines. With the introduction of vector processors, array processors and interconnected systems of mainframes, minis and micros, however, various forms of parallelism have become available. The advantage of parallelism is that it offers increased overall processing speed but it also raises some fundamental questions, including: (i) which, if any, of the existing 'serial' algorithms can be adapted for use in the parallel mode. (ii) How close to optimal can such adapted algorithms be and, where relevant, what are the convergence criteria. (iii) How can we design new algorithms specifically for parallel systems. (iv) For multi-processor systems how can we handle the software aspects of the interprocessor communications. Aspects of these questions illustrated by examples are considered in these lectures. (orig.)
Architecture and VHDL behavioural validation of a parallel processor dedicated to computer vision
International Nuclear Information System (INIS)
Collette, Thierry
1992-01-01
Speeding up image processing is mainly obtained using parallel computers; SIMD processors (single instruction stream, multiple data stream) have been developed, and have proven highly efficient regarding low-level image processing operations. Nevertheless, their performances drop for most intermediate of high level operations, mainly when random data reorganisations in processor memories are involved. The aim of this thesis was to extend the SIMD computer capabilities to allow it to perform more efficiently at the image processing intermediate level. The study of some representative algorithms of this class, points out the limits of this computer. Nevertheless, these limits can be erased by architectural modifications. This leads us to propose SYMPATIX, a new SIMD parallel computer. To valid its new concept, a behavioural model written in VHDL - Hardware Description Language - has been elaborated. With this model, the new computer performances have been estimated running image processing algorithm simulations. VHDL modeling approach allows to perform the system top down electronic design giving an easy coupling between system architectural modifications and their electronic cost. The obtained results show SYMPATIX to be an efficient computer for low and intermediate level image processing. It can be connected to a high level computer, opening up the development of new computer vision applications. This thesis also presents, a top down design method, based on the VHDL, intended for electronic system architects. (author) [fr
International Nuclear Information System (INIS)
DeHart, Mark D.; Williams, Mark L.; Bowman, Stephen M.
2010-01-01
The SCALE computational architecture has remained basically the same since its inception 30 years ago, although constituent modules and capabilities have changed significantly. This SCALE concept was intended to provide a framework whereby independent codes can be linked to provide a more comprehensive capability than possible with the individual programs - allowing flexibility to address a wide variety of applications. However, the current system was designed originally for mainframe computers with a single CPU and with significantly less memory than today's personal computers. It has been recognized that the present SCALE computation system could be restructured to take advantage of modern hardware and software capabilities, while retaining many of the modular features of the present system. Preliminary work is being done to define specifications and capabilities for a more advanced computational architecture. This paper describes the state of current SCALE development activities and plans for future development. With the release of SCALE 6.1 in 2010, a new phase of evolutionary development will be available to SCALE users within the TRITON and NEWT modules. The SCALE (Standardized Computer Analyses for Licensing Evaluation) code system developed by Oak Ridge National Laboratory (ORNL) provides a comprehensive and integrated package of codes and nuclear data for a wide range of applications in criticality safety, reactor physics, shielding, isotopic depletion and decay, and sensitivity/uncertainty (S/U) analysis. Over the last three years, since the release of version 5.1 in 2006, several important new codes have been introduced within SCALE, and significant advances applied to existing codes. Many of these new features became available with the release of SCALE 6.0 in early 2009. However, beginning with SCALE 6.1, a first generation of parallel computing is being introduced. In addition to near-term improvements, a plan for longer term SCALE enhancement
Applied Parallel Computing Industrial Computation and Optimization
DEFF Research Database (Denmark)
Madsen, Kaj; NA NA NA Olesen, Dorte
Proceedings and the Third International Workshop on Applied Parallel Computing in Industrial Problems and Optimization (PARA96)......Proceedings and the Third International Workshop on Applied Parallel Computing in Industrial Problems and Optimization (PARA96)...
A finite element solution method for quadrics parallel computer
International Nuclear Information System (INIS)
Zucchini, A.
1996-08-01
A distributed preconditioned conjugate gradient method for finite element analysis has been developed and implemented on a parallel SIMD Quadrics computer. The main characteristic of the method is that it does not require any actual assembling of all element equations in a global system. The physical domain of the problem is partitioned in cells of n p finite elements and each cell element is assigned to a different node of an n p -processors machine. Element stiffness matrices are stored in the data memory of the assigned processing node and the solution process is completely executed in parallel at element level. Inter-element and therefore inter-processor communications are required once per iteration to perform local sums of vector quantities between neighbouring elements. A prototype implementation has been tested on an 8-nodes Quadrics machine in a simple 2D benchmark problem
Event monitoring of parallel computations
Directory of Open Access Journals (Sweden)
Gruzlikov Alexander M.
2015-06-01
Full Text Available The paper considers the monitoring of parallel computations for detection of abnormal events. It is assumed that computations are organized according to an event model, and monitoring is based on specific test sequences
Real time image synthesis on a SIMD linear array processor: algorithms and architectures
International Nuclear Information System (INIS)
Letellier, Laurent
1993-01-01
Nowadays, image synthesis has become a widely used technique. The impressive computing power required for real time applications necessitates the use of parallel architectures. In this context, we evaluate an SIMD linear parallel architecture, SYMPATI2, dedicated to image processing. The objective of this study is to propose a cost-effective graphics accelerator relying on SYMPATI2's modular and programmable structure. The parallelization of basic image synthesis algorithms on SYMPATI2 enables us to determine its limits in this application field. These limits lead us to evaluate a new structure with a fast intercommunication network between processors, but processors have to support the message consistency, which brings about a strong decrease in performance. To solve this problem, we suggest a simple network whose access priorities are represented by tokens. The simulations of this new architecture indicate that the SIMD mode causes a drastic cut in parallelism. To cope with this drawback, we propose a context switching procedure which reduces the SIMD rigidity and increases the parallelism rate significantly. Then, the graphics accelerator we propose is compared with existing graphics workstations. This comparison indicates that our structure, which is able to accelerate both image synthesis and image processing, is competitive and well-suited for multimedia applications. (author) [fr
Massively parallel quantum computer simulator
De Raedt, K.; Michielsen, K.; De Raedt, H.; Trieu, B.; Arnold, G.; Richter, M.; Lippert, Th.; Watanabe, H.; Ito, N.
2007-01-01
We describe portable software to simulate universal quantum computers on massive parallel Computers. We illustrate the use of the simulation software by running various quantum algorithms on different computer architectures, such as a IBM BlueGene/L, a IBM Regatta p690+, a Hitachi SR11000/J1, a Cray
Akl, Selim G
1985-01-01
Parallel Sorting Algorithms explains how to use parallel algorithms to sort a sequence of items on a variety of parallel computers. The book reviews the sorting problem, the parallel models of computation, parallel algorithms, and the lower bounds on the parallel sorting problems. The text also presents twenty different algorithms, such as linear arrays, mesh-connected computers, cube-connected computers. Another example where algorithm can be applied is on the shared-memory SIMD (single instruction stream multiple data stream) computers in which the whole sequence to be sorted can fit in the
Effective SIMD Vectorization for Intel Xeon Phi Coprocessors
Directory of Open Access Journals (Sweden)
Xinmin Tian
2015-01-01
Full Text Available Efficiently exploiting SIMD vector units is one of the most important aspects in achieving high performance of the application code running on Intel Xeon Phi coprocessors. In this paper, we present several effective SIMD vectorization techniques such as less-than-full-vector loop vectorization, Intel MIC specific alignment optimization, and small matrix transpose/multiplication 2D vectorization implemented in the Intel C/C++ and Fortran production compilers for Intel Xeon Phi coprocessors. A set of workloads from several application domains is employed to conduct the performance study of our SIMD vectorization techniques. The performance results show that we achieved up to 12.5x performance gain on the Intel Xeon Phi coprocessor. We also demonstrate a 2000x performance speedup from the seamless integration of SIMD vectorization and parallelization.
Parallel algorithms and cluster computing
Hoffmann, Karl Heinz
2007-01-01
This book presents major advances in high performance computing as well as major advances due to high performance computing. It contains a collection of papers in which results achieved in the collaboration of scientists from computer science, mathematics, physics, and mechanical engineering are presented. From the science problems to the mathematical algorithms and on to the effective implementation of these algorithms on massively parallel and cluster computers we present state-of-the-art methods and technology as well as exemplary results in these fields. This book shows that problems which seem superficially distinct become intimately connected on a computational level.
International Nuclear Information System (INIS)
Heggarty, J.W.
1999-06-01
For almost thirty years, sequential R-matrix computation has been used by atomic physics research groups, from around the world, to model collision phenomena involving the scattering of electrons or positrons with atomic or molecular targets. As considerable progress has been made in the understanding of fundamental scattering processes, new data, obtained from more complex calculations, is of current interest to experimentalists. Performing such calculations, however, places considerable demands on the computational resources to be provided by the target machine, in terms of both processor speed and memory requirement. Indeed, in some instances the computational requirements are so great that the proposed R-matrix calculations are intractable, even when utilising contemporary classic supercomputers. Historically, increases in the computational requirements of R-matrix computation were accommodated by porting the problem codes to a more powerful classic supercomputer. Although this approach has been successful in the past, it is no longer considered to be a satisfactory solution due to the limitations of current (and future) Von Neumann machines. As a consequence, there has been considerable interest in the high performance multicomputers, that have emerged over the last decade which appear to offer the computational resources required by contemporary R-matrix research. Unfortunately, developing codes for these machines is not as simple a task as it was to develop codes for successive classic supercomputers. The difficulty arises from the considerable differences in the computing models that exist between the two types of machine and results in the programming of multicomputers to be widely acknowledged as a difficult, time consuming and error-prone task. Nevertheless, unless parallel R-matrix computation is realised, important theoretical and experimental atomic physics research will continue to be hindered. This thesis describes work that was undertaken in
Implementation and analysis of a Navier-Stokes algorithm on parallel computers
Fatoohi, Raad A.; Grosch, Chester E.
1988-01-01
The results of the implementation of a Navier-Stokes algorithm on three parallel/vector computers are presented. The object of this research is to determine how well, or poorly, a single numerical algorithm would map onto three different architectures. The algorithm is a compact difference scheme for the solution of the incompressible, two-dimensional, time-dependent Navier-Stokes equations. The computers were chosen so as to encompass a variety of architectures. They are the following: the MPP, an SIMD machine with 16K bit serial processors; Flex/32, an MIMD machine with 20 processors; and Cray/2. The implementation of the algorithm is discussed in relation to these architectures and measures of the performance on each machine are given. The basic comparison is among SIMD instruction parallelism on the MPP, MIMD process parallelism on the Flex/32, and vectorization of a serial code on the Cray/2. Simple performance models are used to describe the performance. These models highlight the bottlenecks and limiting factors for this algorithm on these architectures. Finally, conclusions are presented.
A flexible algorithm for calculating pair interactions on SIMD architectures
Páll, Szilárd; Hess, Berk
2013-12-01
Calculating interactions or correlations between pairs of particles is typically the most time-consuming task in particle simulation or correlation analysis. Straightforward implementations using a double loop over particle pairs have traditionally worked well, especially since compilers usually do a good job of unrolling the inner loop. In order to reach high performance on modern CPU and accelerator architectures, single-instruction multiple-data (SIMD) parallelization has become essential. Avoiding memory bottlenecks is also increasingly important and requires reducing the ratio of memory to arithmetic operations. Moreover, when pairs only interact within a certain cut-off distance, good SIMD utilization can only be achieved by reordering input and output data, which quickly becomes a limiting factor. Here we present an algorithm for SIMD parallelization based on grouping a fixed number of particles, e.g. 2, 4, or 8, into spatial clusters. Calculating all interactions between particles in a pair of such clusters improves data reuse compared to the traditional scheme and results in a more efficient SIMD parallelization. Adjusting the cluster size allows the algorithm to map to SIMD units of various widths. This flexibility not only enables fast and efficient implementation on current CPUs and accelerator architectures like GPUs or Intel MIC, but it also makes the algorithm future-proof. We present the algorithm with an application to molecular dynamics simulations, where we can also make use of the effective buffering the method introduces.
Parallel computing: numerics, applications, and trends
National Research Council Canada - National Science Library
Trobec, Roman; Vajteršic, Marián; Zinterhof, Peter
2009-01-01
... and/or distributed systems. The contributions to this book are focused on topics most concerned in the trends of today's parallel computing. These range from parallel algorithmics, programming, tools, network computing to future parallel computing. Particular attention is paid to parallel numerics: linear algebra, differential equations, numerica...
Parallel computation of Euler and Navier-Stokes flows
International Nuclear Information System (INIS)
Swisshelm, J.M.; Johnson, G.M.; Kumar, S.P.
1986-01-01
A multigrid technique useful for accelerating the convergence of Euler and Navier-Stokes flow computations has been restructured to improve its performance on both SIMD and MIMD computers. The new algorithm allows both the construction of longer coarse-grid vectors and the multitasking of entire grids. Computational results are presented for the CDC Cyber 205, Cray X-MP, and Denelcor HEP I. 15 references
The numerical parallel computing of photon transport
International Nuclear Information System (INIS)
Huang Qingnan; Liang Xiaoguang; Zhang Lifa
1998-12-01
The parallel computing of photon transport is investigated, the parallel algorithm and the parallelization of programs on parallel computers both with shared memory and with distributed memory are discussed. By analyzing the inherent law of the mathematics and physics model of photon transport according to the structure feature of parallel computers, using the strategy of 'to divide and conquer', adjusting the algorithm structure of the program, dissolving the data relationship, finding parallel liable ingredients and creating large grain parallel subtasks, the sequential computing of photon transport into is efficiently transformed into parallel and vector computing. The program was run on various HP parallel computers such as the HY-1 (PVP), the Challenge (SMP) and the YH-3 (MPP) and very good parallel speedup has been gotten
Empirical study of parallel LRU simulation algorithms
Carr, Eric; Nicol, David M.
1994-01-01
This paper reports on the performance of five parallel algorithms for simulating a fully associative cache operating under the LRU (Least-Recently-Used) replacement policy. Three of the algorithms are SIMD, and are implemented on the MasPar MP-2 architecture. Two other algorithms are parallelizations of an efficient serial algorithm on the Intel Paragon. One SIMD algorithm is quite simple, but its cost is linear in the cache size. The two other SIMD algorithm are more complex, but have costs that are independent on the cache size. Both the second and third SIMD algorithms compute all stack distances; the second SIMD algorithm is completely general, whereas the third SIMD algorithm presumes and takes advantage of bounds on the range of reference tags. Both MIMD algorithm implemented on the Paragon are general and compute all stack distances; they differ in one step that may affect their respective scalability. We assess the strengths and weaknesses of these algorithms as a function of problem size and characteristics, and compare their performance on traces derived from execution of three SPEC benchmark programs.
CERN. Geneva
2016-01-01
Large scale scientific computing raises questions on different levels ranging from the fomulation of the problems to the choice of the best algorithms and their implementation for a specific platform. There are similarities in these different topics that can be exploited by modern-style C++ template metaprogramming techniques to produce readable, maintainable and generic code. Traditional low-level code tend to be fast but platform-dependent, and it obfuscates the meaning of the algorithm. On the other hand, object-oriented approach is nice to read, but may come with an inherent performance penalty. These lectures aim to present he basics of the Expression Template (ET) idiom which allows us to keep the object-oriented approach without sacrificing performance. We will in particular show to to enhance ET to include SIMD vectorization. We will then introduce techniques for abstracting iteration, and introduce thread-level parallelism for use in heavy data-centric loads. We will show to to apply these methods i...
Some multigrid algorithms for SIMD machines
Energy Technology Data Exchange (ETDEWEB)
Dendy, J.E. Jr. [Los Alamos National Lab., NM (United States)
1996-12-31
Previously a semicoarsening multigrid algorithm suitable for use on SIMD architectures was investigated. Through the use of new software tools, the performance of this algorithm has been considerably improved. The method has also been extended to three space dimensions. The method performs well for strongly anisotropic problems and for problems with coefficients jumping by orders of magnitude across internal interfaces. The parallel efficiency of this method is analyzed, and its actual performance on the CM-5 is compared with its performance on the CRAY-YMP. A standard coarsening multigrid algorithm is also considered, and we compare its performance on these two platforms as well.
Parallel computation of rotating flows
DEFF Research Database (Denmark)
Lundin, Lars Kristian; Barker, Vincent A.; Sørensen, Jens Nørkær
1999-01-01
This paper deals with the simulation of 3‐D rotating flows based on the velocity‐vorticity formulation of the Navier‐Stokes equations in cylindrical coordinates. The governing equations are discretized by a finite difference method. The solution is advanced to a new time level by a two‐step process...... is that of solving a singular, large, sparse, over‐determined linear system of equations, and the iterative method CGLS is applied for this purpose. We discuss some of the mathematical and numerical aspects of this procedure and report on the performance of our software on a wide range of parallel computers. Darbe...
Parallel computing in enterprise modeling.
Energy Technology Data Exchange (ETDEWEB)
Goldsby, Michael E.; Armstrong, Robert C.; Shneider, Max S.; Vanderveen, Keith; Ray, Jaideep; Heath, Zach; Allan, Benjamin A.
2008-08-01
This report presents the results of our efforts to apply high-performance computing to entity-based simulations with a multi-use plugin for parallel computing. We use the term 'Entity-based simulation' to describe a class of simulation which includes both discrete event simulation and agent based simulation. What simulations of this class share, and what differs from more traditional models, is that the result sought is emergent from a large number of contributing entities. Logistic, economic and social simulations are members of this class where things or people are organized or self-organize to produce a solution. Entity-based problems never have an a priori ergodic principle that will greatly simplify calculations. Because the results of entity-based simulations can only be realized at scale, scalable computing is de rigueur for large problems. Having said that, the absence of a spatial organizing principal makes the decomposition of the problem onto processors problematic. In addition, practitioners in this domain commonly use the Java programming language which presents its own problems in a high-performance setting. The plugin we have developed, called the Parallel Particle Data Model, overcomes both of these obstacles and is now being used by two Sandia frameworks: the Decision Analysis Center, and the Seldon social simulation facility. While the ability to engage U.S.-sized problems is now available to the Decision Analysis Center, this plugin is central to the success of Seldon. Because Seldon relies on computationally intensive cognitive sub-models, this work is necessary to achieve the scale necessary for realistic results. With the recent upheavals in the financial markets, and the inscrutability of terrorist activity, this simulation domain will likely need a capability with ever greater fidelity. High-performance computing will play an important part in enabling that greater fidelity.
Streaming nested data parallelism on multicores
DEFF Research Database (Denmark)
Madsen, Frederik Meisner; Filinski, Andrzej
2016-01-01
The paradigm of nested data parallelism (NDP) allows a variety of semi-regular computation tasks to be mapped onto SIMD-style hardware, including GPUs and vector units. However, some care is needed to keep down space consumption in situations where the available parallelism may vastly exceed...
Cloud identification using genetic algorithms and massively parallel computation
Buckles, Bill P.; Petry, Frederick E.
1996-01-01
As a Guest Computational Investigator under the NASA administered component of the High Performance Computing and Communication Program, we implemented a massively parallel genetic algorithm on the MasPar SIMD computer. Experiments were conducted using Earth Science data in the domains of meteorology and oceanography. Results obtained in these domains are competitive with, and in most cases better than, similar problems solved using other methods. In the meteorological domain, we chose to identify clouds using AVHRR spectral data. Four cloud speciations were used although most researchers settle for three. Results were remarkedly consistent across all tests (91% accuracy). Refinements of this method may lead to more timely and complete information for Global Circulation Models (GCMS) that are prevalent in weather forecasting and global environment studies. In the oceanographic domain, we chose to identify ocean currents from a spectrometer having similar characteristics to AVHRR. Here the results were mixed (60% to 80% accuracy). Given that one is willing to run the experiment several times (say 10), then it is acceptable to claim the higher accuracy rating. This problem has never been successfully automated. Therefore, these results are encouraging even though less impressive than the cloud experiment. Successful conclusion of an automated ocean current detection system would impact coastal fishing, naval tactics, and the study of micro-climates. Finally we contributed to the basic knowledge of GA (genetic algorithm) behavior in parallel environments. We developed better knowledge of the use of subpopulations in the context of shared breeding pools and the migration of individuals. Rigorous experiments were conducted based on quantifiable performance criteria. While much of the work confirmed current wisdom, for the first time we were able to submit conclusive evidence. The software developed under this grant was placed in the public domain. An extensive user
An Introduction to Parallel Computation R
Indian Academy of Sciences (India)
How are they programmed? This article provides an introduction. A parallel computer is a network of processors built for ... and have been used to solve problems much faster than a single ... in parallel computer design is to select an organization which ..... The most ambitious approach to parallel computing is to develop.
I - Template Metaprogramming for Massively Parallel Scientific Computing - Expression Templates
CERN. Geneva
2016-01-01
Large scale scientific computing raises questions on different levels ranging from the fomulation of the problems to the choice of the best algorithms and their implementation for a specific platform. There are similarities in these different topics that can be exploited by modern-style C++ template metaprogramming techniques to produce readable, maintainable and generic code. Traditional low-level code tend to be fast but platform-dependent, and it obfuscates the meaning of the algorithm. On the other hand, object-oriented approach is nice to read, but may come with an inherent performance penalty. These lectures aim to present he basics of the Expression Template (ET) idiom which allows us to keep the object-oriented approach without sacrificing performance. We will in particular show to to enhance ET to include SIMD vectorization. We will then introduce techniques for abstracting iteration, and introduce thread-level parallelism for use in heavy data-centric loads. We will show to to apply these methods i...
Advances in randomized parallel computing
Rajasekaran, Sanguthevar
1999-01-01
The technique of randomization has been employed to solve numerous prob lems of computing both sequentially and in parallel. Examples of randomized algorithms that are asymptotically better than their deterministic counterparts in solving various fundamental problems abound. Randomized algorithms have the advantages of simplicity and better performance both in theory and often in practice. This book is a collection of articles written by renowned experts in the area of randomized parallel computing. A brief introduction to randomized algorithms In the aflalysis of algorithms, at least three different measures of performance can be used: the best case, the worst case, and the average case. Often, the average case run time of an algorithm is much smaller than the worst case. 2 For instance, the worst case run time of Hoare's quicksort is O(n ), whereas its average case run time is only O( n log n). The average case analysis is conducted with an assumption on the input space. The assumption made to arrive at t...
Parallel Computing for Brain Simulation.
Pastur-Romay, L A; Porto-Pazos, A B; Cedron, F; Pazos, A
2017-01-01
The human brain is the most complex system in the known universe, it is therefore one of the greatest mysteries. It provides human beings with extraordinary abilities. However, until now it has not been understood yet how and why most of these abilities are produced. For decades, researchers have been trying to make computers reproduce these abilities, focusing on both understanding the nervous system and, on processing data in a more efficient way than before. Their aim is to make computers process information similarly to the brain. Important technological developments and vast multidisciplinary projects have allowed creating the first simulation with a number of neurons similar to that of a human brain. This paper presents an up-to-date review about the main research projects that are trying to simulate and/or emulate the human brain. They employ different types of computational models using parallel computing: digital models, analog models and hybrid models. This review includes the current applications of these works, as well as future trends. It is focused on various works that look for advanced progress in Neuroscience and still others which seek new discoveries in Computer Science (neuromorphic hardware, machine learning techniques). Their most outstanding characteristics are summarized and the latest advances and future plans are presented. In addition, this review points out the importance of considering not only neurons: Computational models of the brain should also include glial cells, given the proven importance of astrocytes in information processing. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.
Aspects of computation on asynchronous parallel processors
International Nuclear Information System (INIS)
Wright, M.
1989-01-01
The increasing availability of asynchronous parallel processors has provided opportunities for original and useful work in scientific computing. However, the field of parallel computing is still in a highly volatile state, and researchers display a wide range of opinion about many fundamental questions such as models of parallelism, approaches for detecting and analyzing parallelism of algorithms, and tools that allow software developers and users to make effective use of diverse forms of complex hardware. This volume collects the work of researchers specializing in different aspects of parallel computing, who met to discuss the framework and the mechanics of numerical computing. The far-reaching impact of high-performance asynchronous systems is reflected in the wide variety of topics, which include scientific applications (e.g. linear algebra, lattice gauge simulation, ordinary and partial differential equations), models of parallelism, parallel language features, task scheduling, automatic parallelization techniques, tools for algorithm development in parallel environments, and system design issues
Parallel Computing Using Web Servers and "Servlets".
Lo, Alfred; Bloor, Chris; Choi, Y. K.
2000-01-01
Describes parallel computing and presents inexpensive ways to implement a virtual parallel computer with multiple Web servers. Highlights include performance measurement of parallel systems; models for using Java and intranet technology including single server, multiple clients and multiple servers, single client; and a comparison of CGI (common…
Broadcasting a message in a parallel computer
Berg, Jeremy E [Rochester, MN; Faraj, Ahmad A [Rochester, MN
2011-08-02
Methods, systems, and products are disclosed for broadcasting a message in a parallel computer. The parallel computer includes a plurality of compute nodes connected together using a data communications network. The data communications network optimized for point to point data communications and is characterized by at least two dimensions. The compute nodes are organized into at least one operational group of compute nodes for collective parallel operations of the parallel computer. One compute node of the operational group assigned to be a logical root. Broadcasting a message in a parallel computer includes: establishing a Hamiltonian path along all of the compute nodes in at least one plane of the data communications network and in the operational group; and broadcasting, by the logical root to the remaining compute nodes, the logical root's message along the established Hamiltonian path.
International Nuclear Information System (INIS)
Zee, S.K.
1987-01-01
A numeric algorithm and an associated computer code were developed for the rapid solution of the finite-difference method representation of the few-group neutron-diffusion equations on parallel computers. Applications of the numeric algorithm on both SIMD (vector pipeline) and MIMD/SIMD (multi-CUP/vector pipeline) architectures were explored. The algorithm was successfully implemented in the two-group, 3-D neutron diffusion computer code named DIFPAR3D (DIFfusion PARallel 3-Dimension). Numerical-solution techniques used in the code include the Chebyshev polynomial acceleration technique in conjunction with the power method of outer iteration. For inner iterations, a parallel form of red-black (cyclic) line SOR with automated determination of group dependent relaxation factors and iteration numbers required to achieve specified inner iteration error tolerance is incorporated. The code employs a macroscopic depletion model with trace capability for selected fission products' transients and critical boron. In addition to this, moderator and fuel temperature feedback models are also incorporated into the DIFPAR3D code, for realistic simulation of power reactor cores. The physics models used were proven acceptable in separate benchmarking studies
Performance modeling and analysis of parallel Gaussian elimination on multi-core computers
Directory of Open Access Journals (Sweden)
Fadi N. Sibai
2014-01-01
Full Text Available Gaussian elimination is used in many applications and in particular in the solution of systems of linear equations. This paper presents mathematical performance models and analysis of four parallel Gaussian Elimination methods (precisely the Original method and the new Meet in the Middle –MiM– algorithms and their variants with SIMD vectorization on multi-core systems. Analytical performance models of the four methods are formulated and presented followed by evaluations of these models with modern multi-core systems’ operation latencies. Our results reveal that the four methods generally exhibit good performance scaling with increasing matrix size and number of cores. SIMD vectorization only makes a large difference in performance for low number of cores. For a large matrix size (n ⩾ 16 K, the performance difference between the MiM and Original methods falls from 16× with four cores to 4× with 16 K cores. The efficiencies of all four methods are low with 1 K cores or more stressing a major problem of multi-core systems where the network-on-chip and memory latencies are too high in relation to basic arithmetic operations. Thus Gaussian Elimination can greatly benefit from the resources of multi-core systems, but higher performance gains can be achieved if multi-core systems can be designed with lower memory operation, synchronization, and interconnect communication latencies, requirements of utmost importance and challenge in the exascale computing age.
Template based parallel checkpointing in a massively parallel computer system
Archer, Charles Jens [Rochester, MN; Inglett, Todd Alan [Rochester, MN
2009-01-13
A method and apparatus for a template based parallel checkpoint save for a massively parallel super computer system using a parallel variation of the rsync protocol, and network broadcast. In preferred embodiments, the checkpoint data for each node is compared to a template checkpoint file that resides in the storage and that was previously produced. Embodiments herein greatly decrease the amount of data that must be transmitted and stored for faster checkpointing and increased efficiency of the computer system. Embodiments are directed to a parallel computer system with nodes arranged in a cluster with a high speed interconnect that can perform broadcast communication. The checkpoint contains a set of actual small data blocks with their corresponding checksums from all nodes in the system. The data blocks may be compressed using conventional non-lossy data compression algorithms to further reduce the overall checkpoint size.
Compiler Technology for Parallel Scientific Computation
Directory of Open Access Journals (Sweden)
Can Özturan
1994-01-01
Full Text Available There is a need for compiler technology that, given the source program, will generate efficient parallel codes for different architectures with minimal user involvement. Parallel computation is becoming indispensable in solving large-scale problems in science and engineering. Yet, the use of parallel computation is limited by the high costs of developing the needed software. To overcome this difficulty we advocate a comprehensive approach to the development of scalable architecture-independent software for scientific computation based on our experience with equational programming language (EPL. Our approach is based on a program decomposition, parallel code synthesis, and run-time support for parallel scientific computation. The program decomposition is guided by the source program annotations provided by the user. The synthesis of parallel code is based on configurations that describe the overall computation as a set of interacting components. Run-time support is provided by the compiler-generated code that redistributes computation and data during object program execution. The generated parallel code is optimized using techniques of data alignment, operator placement, wavefront determination, and memory optimization. In this article we discuss annotations, configurations, parallel code generation, and run-time support suitable for parallel programs written in the functional parallel programming language EPL and in Fortran.
Parallel algorithms for mapping pipelined and parallel computations
Nicol, David M.
1988-01-01
Many computational problems in image processing, signal processing, and scientific computing are naturally structured for either pipelined or parallel computation. When mapping such problems onto a parallel architecture it is often necessary to aggregate an obvious problem decomposition. Even in this context the general mapping problem is known to be computationally intractable, but recent advances have been made in identifying classes of problems and architectures for which optimal solutions can be found in polynomial time. Among these, the mapping of pipelined or parallel computations onto linear array, shared memory, and host-satellite systems figures prominently. This paper extends that work first by showing how to improve existing serial mapping algorithms. These improvements have significantly lower time and space complexities: in one case a published O(nm sup 3) time algorithm for mapping m modules onto n processors is reduced to an O(nm log m) time complexity, and its space requirements reduced from O(nm sup 2) to O(m). Run time complexity is further reduced with parallel mapping algorithms based on these improvements, which run on the architecture for which they create the mappings.
Massively parallel evolutionary computation on GPGPUs
Tsutsui, Shigeyoshi
2013-01-01
Evolutionary algorithms (EAs) are metaheuristics that learn from natural collective behavior and are applied to solve optimization problems in domains such as scheduling, engineering, bioinformatics, and finance. Such applications demand acceptable solutions with high-speed execution using finite computational resources. Therefore, there have been many attempts to develop platforms for running parallel EAs using multicore machines, massively parallel cluster machines, or grid computing environments. Recent advances in general-purpose computing on graphics processing units (GPGPU) have opened u
Energy Technology Data Exchange (ETDEWEB)
Amadio, G.; et al.
2017-11-22
An intensive R&D and programming effort is required to accomplish new challenges posed by future experimental high-energy particle physics (HEP) programs. The GeantV project aims to narrow the gap between the performance of the existing HEP detector simulation software and the ideal performance achievable, exploiting latest advances in computing technology. The project has developed a particle detector simulation prototype capable of transporting in parallel particles in complex geometries exploiting instruction level microparallelism (SIMD and SIMT), task-level parallelism (multithreading) and high-level parallelism (MPI), leveraging both the multi-core and the many-core opportunities. We present preliminary verification results concerning the electromagnetic (EM) physics models developed for parallel computing architectures within the GeantV project. In order to exploit the potential of vectorization and accelerators and to make the physics model effectively parallelizable, advanced sampling techniques have been implemented and tested. In this paper we introduce a set of automated statistical tests in order to verify the vectorized models by checking their consistency with the corresponding Geant4 models and to validate them against experimental data.
Collectively loading an application in a parallel computer
Aho, Michael E.; Attinella, John E.; Gooding, Thomas M.; Miller, Samuel J.; Mundy, Michael B.
2016-01-05
Collectively loading an application in a parallel computer, the parallel computer comprising a plurality of compute nodes, including: identifying, by a parallel computer control system, a subset of compute nodes in the parallel computer to execute a job; selecting, by the parallel computer control system, one of the subset of compute nodes in the parallel computer as a job leader compute node; retrieving, by the job leader compute node from computer memory, an application for executing the job; and broadcasting, by the job leader to the subset of compute nodes in the parallel computer, the application for executing the job.
Parallel Computing Strategies for Irregular Algorithms
Biswas, Rupak; Oliker, Leonid; Shan, Hongzhang; Biegel, Bryan (Technical Monitor)
2002-01-01
Parallel computing promises several orders of magnitude increase in our ability to solve realistic computationally-intensive problems, but relies on their efficient mapping and execution on large-scale multiprocessor architectures. Unfortunately, many important applications are irregular and dynamic in nature, making their effective parallel implementation a daunting task. Moreover, with the proliferation of parallel architectures and programming paradigms, the typical scientist is faced with a plethora of questions that must be answered in order to obtain an acceptable parallel implementation of the solution algorithm. In this paper, we consider three representative irregular applications: unstructured remeshing, sparse matrix computations, and N-body problems, and parallelize them using various popular programming paradigms on a wide spectrum of computer platforms ranging from state-of-the-art supercomputers to PC clusters. We present the underlying problems, the solution algorithms, and the parallel implementation strategies. Smart load-balancing, partitioning, and ordering techniques are used to enhance parallel performance. Overall results demonstrate the complexity of efficiently parallelizing irregular algorithms.
Massively Parallel Computing: A Sandia Perspective
Energy Technology Data Exchange (ETDEWEB)
Dosanjh, Sudip S.; Greenberg, David S.; Hendrickson, Bruce; Heroux, Michael A.; Plimpton, Steve J.; Tomkins, James L.; Womble, David E.
1999-05-06
The computing power available to scientists and engineers has increased dramatically in the past decade, due in part to progress in making massively parallel computing practical and available. The expectation for these machines has been great. The reality is that progress has been slower than expected. Nevertheless, massively parallel computing is beginning to realize its potential for enabling significant break-throughs in science and engineering. This paper provides a perspective on the state of the field, colored by the authors' experiences using large scale parallel machines at Sandia National Laboratories. We address trends in hardware, system software and algorithms, and we also offer our view of the forces shaping the parallel computing industry.
Domain decomposition methods and parallel computing
International Nuclear Information System (INIS)
Meurant, G.
1991-01-01
In this paper, we show how to efficiently solve large linear systems on parallel computers. These linear systems arise from discretization of scientific computing problems described by systems of partial differential equations. We show how to get a discrete finite dimensional system from the continuous problem and the chosen conjugate gradient iterative algorithm is briefly described. Then, the different kinds of parallel architectures are reviewed and their advantages and deficiencies are emphasized. We sketch the problems found in programming the conjugate gradient method on parallel computers. For this algorithm to be efficient on parallel machines, domain decomposition techniques are introduced. We give results of numerical experiments showing that these techniques allow a good rate of convergence for the conjugate gradient algorithm as well as computational speeds in excess of a billion of floating point operations per second. (author). 5 refs., 11 figs., 2 tabs., 1 inset
Parallel quantum computing in a single ensemble quantum computer
International Nuclear Information System (INIS)
Long Guilu; Xiao, L.
2004-01-01
We propose a parallel quantum computing mode for ensemble quantum computer. In this mode, some qubits are in pure states while other qubits are in mixed states. It enables a single ensemble quantum computer to perform 'single-instruction-multidata' type of parallel computation. Parallel quantum computing can provide additional speedup in Grover's algorithm and Shor's algorithm. In addition, it also makes a fuller use of qubit resources in an ensemble quantum computer. As a result, some qubits discarded in the preparation of an effective pure state in the Schulman-Varizani and the Cleve-DiVincenzo algorithms can be reutilized
Structured Parallel Programming Patterns for Efficient Computation
McCool, Michael; Robison, Arch
2012-01-01
Programming is now parallel programming. Much as structured programming revolutionized traditional serial programming decades ago, a new kind of structured programming, based on patterns, is relevant to parallel programming today. Parallel computing experts and industry insiders Michael McCool, Arch Robison, and James Reinders describe how to design and implement maintainable and efficient parallel algorithms using a pattern-based approach. They present both theory and practice, and give detailed concrete examples using multiple programming models. Examples are primarily given using two of th
Rapid prototyping and evaluation of programmable SIMD SDR processors in LISA
Chen, Ting; Liu, Hengzhu; Zhang, Botao; Liu, Dongpei
2013-03-01
With the development of international wireless communication standards, there is an increase in computational requirement for baseband signal processors. Time-to-market pressure makes it impossible to completely redesign new processors for the evolving standards. Due to its high flexibility and low power, software defined radio (SDR) digital signal processors have been proposed as promising technology to replace traditional ASIC and FPGA fashions. In addition, there are large numbers of parallel data processed in computation-intensive functions, which fosters the development of single instruction multiple data (SIMD) architecture in SDR platform. So a new way must be found to prototype the SDR processors efficiently. In this paper we present a bit-and-cycle accurate model of programmable SIMD SDR processors in a machine description language LISA. LISA is a language for instruction set architecture which can gain rapid model at architectural level. In order to evaluate the availability of our proposed processor, three common baseband functions, FFT, FIR digital filter and matrix multiplication have been mapped on the SDR platform. Analytical results showed that the SDR processor achieved the maximum of 47.1% performance boost relative to the opponent processor.
Parallel computation of rotating flows
DEFF Research Database (Denmark)
Lundin, Lars Kristian; Barker, Vincent A.; Sørensen, Jens Nørkær
1999-01-01
This paper deals with the simulation of 3‐D rotating flows based on the velocity‐vorticity formulation of the Navier‐Stokes equations in cylindrical coordinates. The governing equations are discretized by a finite difference method. The solution is advanced to a new time level by a two‐step process....... In the first step, the vorticity at the new time level is computed using the velocity at the previous time level. In the second step, the velocity at the new time level is computed using the new vorticity. We discuss here the second part which is by far the most time‐consuming. The numerical problem...
Computer-Aided Parallelizer and Optimizer
Jin, Haoqiang
2011-01-01
The Computer-Aided Parallelizer and Optimizer (CAPO) automates the insertion of compiler directives (see figure) to facilitate parallel processing on Shared Memory Parallel (SMP) machines. While CAPO currently is integrated seamlessly into CAPTools (developed at the University of Greenwich, now marketed as ParaWise), CAPO was independently developed at Ames Research Center as one of the components for the Legacy Code Modernization (LCM) project. The current version takes serial FORTRAN programs, performs interprocedural data dependence analysis, and generates OpenMP directives. Due to the widely supported OpenMP standard, the generated OpenMP codes have the potential to run on a wide range of SMP machines. CAPO relies on accurate interprocedural data dependence information currently provided by CAPTools. Compiler directives are generated through identification of parallel loops in the outermost level, construction of parallel regions around parallel loops and optimization of parallel regions, and insertion of directives with automatic identification of private, reduction, induction, and shared variables. Attempts also have been made to identify potential pipeline parallelism (implemented with point-to-point synchronization). Although directives are generated automatically, user interaction with the tool is still important for producing good parallel codes. A comprehensive graphical user interface is included for users to interact with the parallelization process.
High performance parallel computers for science
International Nuclear Information System (INIS)
Nash, T.; Areti, H.; Atac, R.; Biel, J.; Cook, A.; Deppe, J.; Edel, M.; Fischler, M.; Gaines, I.; Hance, R.
1989-01-01
This paper reports that Fermilab's Advanced Computer Program (ACP) has been developing cost effective, yet practical, parallel computers for high energy physics since 1984. The ACP's latest developments are proceeding in two directions. A Second Generation ACP Multiprocessor System for experiments will include $3500 RISC processors each with performance over 15 VAX MIPS. To support such high performance, the new system allows parallel I/O, parallel interprocess communication, and parallel host processes. The ACP Multi-Array Processor, has been developed for theoretical physics. Each $4000 node is a FORTRAN or C programmable pipelined 20 Mflops (peak), 10 MByte single board computer. These are plugged into a 16 port crossbar switch crate which handles both inter and intra crate communication. The crates are connected in a hypercube. Site oriented applications like lattice gauge theory are supported by system software called CANOPY, which makes the hardware virtually transparent to users. A 256 node, 5 GFlop, system is under construction
Vectorization with SIMD extensions speeds up reconstruction in electron tomography.
Agulleiro, J I; Garzón, E M; García, I; Fernández, J J
2010-06-01
Electron tomography allows structural studies of cellular structures at molecular detail. Large 3D reconstructions are needed to meet the resolution requirements. The processing time to compute these large volumes may be considerable and so, high performance computing techniques have been used traditionally. This work presents a vector approach to tomographic reconstruction that relies on the exploitation of the SIMD extensions available in modern processors in combination to other single processor optimization techniques. This approach succeeds in producing full resolution tomograms with an important reduction in processing time, as evaluated with the most common reconstruction algorithms, namely WBP and SIRT. The main advantage stems from the fact that this approach is to be run on standard computers without the need of specialized hardware, which facilitates the development, use and management of programs. Future trends in processor design open excellent opportunities for vector processing with processor's SIMD extensions in the field of 3D electron microscopy.
International Nuclear Information System (INIS)
McGhee, J.M.; Roberts, R.M.; Morel, J.E.
1997-01-01
A spherical harmonics research code (DANTE) has been developed which is compatible with parallel computer architectures. DANTE provides 3-D, multi-material, deterministic, transport capabilities using an arbitrary finite element mesh. The linearized Boltzmann transport equation is solved in a second order self-adjoint form utilizing a Galerkin finite element spatial differencing scheme. The core solver utilizes a preconditioned conjugate gradient algorithm. Other distinguishing features of the code include options for discrete-ordinates and simplified spherical harmonics angular differencing, an exact Marshak boundary treatment for arbitrarily oriented boundary faces, in-line matrix construction techniques to minimize memory consumption, and an effective diffusion based preconditioner for scattering dominated problems. Algorithm efficiency is demonstrated for a massively parallel SIMD architecture (CM-5), and compatibility with MPP multiprocessor platforms or workstation clusters is anticipated
Parallel computational in nuclear group constant calculation
International Nuclear Information System (INIS)
Su'ud, Zaki; Rustandi, Yaddi K.; Kurniadi, Rizal
2002-01-01
In this paper parallel computational method in nuclear group constant calculation using collision probability method will be discuss. The main focus is on the calculation of collision matrix which need large amount of computational time. The geometry treated here is concentric cylinder. The calculation of collision probability matrix is carried out using semi analytic method using Beckley Naylor Function. To accelerate computation speed some computer parallel used to solve the problem. We used LINUX based parallelization using PVM software with C or fortran language. While in windows based we used socket programming using DELPHI or C builder. The calculation results shows the important of optimal weight for each processor in case there area many type of processor speed
Locating hardware faults in a parallel computer
Archer, Charles J.; Megerian, Mark G.; Ratterman, Joseph D.; Smith, Brian E.
2010-04-13
Locating hardware faults in a parallel computer, including defining within a tree network of the parallel computer two or more sets of non-overlapping test levels of compute nodes of the network that together include all the data communications links of the network, each non-overlapping test level comprising two or more adjacent tiers of the tree; defining test cells within each non-overlapping test level, each test cell comprising a subtree of the tree including a subtree root compute node and all descendant compute nodes of the subtree root compute node within a non-overlapping test level; performing, separately on each set of non-overlapping test levels, an uplink test on all test cells in a set of non-overlapping test levels; and performing, separately from the uplink tests and separately on each set of non-overlapping test levels, a downlink test on all test cells in a set of non-overlapping test levels.
Impact analysis on a massively parallel computer
International Nuclear Information System (INIS)
Zacharia, T.; Aramayo, G.A.
1994-01-01
Advanced mathematical techniques and computer simulation play a major role in evaluating and enhancing the design of beverage cans, industrial, and transportation containers for improved performance. Numerical models are used to evaluate the impact requirements of containers used by the Department of Energy (DOE) for transporting radioactive materials. Many of these models are highly compute-intensive. An analysis may require several hours of computational time on current supercomputers despite the simplicity of the models being studied. As computer simulations and materials databases grow in complexity, massively parallel computers have become important tools. Massively parallel computational research at the Oak Ridge National Laboratory (ORNL) and its application to the impact analysis of shipping containers is briefly described in this paper
Internode data communications in a parallel computer
Archer, Charles J.; Blocksome, Michael A.; Miller, Douglas R.; Parker, Jeffrey J.; Ratterman, Joseph D.; Smith, Brian E.
2013-09-03
Internode data communications in a parallel computer that includes compute nodes that each include main memory and a messaging unit, the messaging unit including computer memory and coupling compute nodes for data communications, in which, for each compute node at compute node boot time: a messaging unit allocates, in the messaging unit's computer memory, a predefined number of message buffers, each message buffer associated with a process to be initialized on the compute node; receives, prior to initialization of a particular process on the compute node, a data communications message intended for the particular process; and stores the data communications message in the message buffer associated with the particular process. Upon initialization of the particular process, the process establishes a messaging buffer in main memory of the compute node and copies the data communications message from the message buffer of the messaging unit into the message buffer of main memory.
Link failure detection in a parallel computer
Archer, Charles J.; Blocksome, Michael A.; Megerian, Mark G.; Smith, Brian E.
2010-11-09
Methods, apparatus, and products are disclosed for link failure detection in a parallel computer including compute nodes connected in a rectangular mesh network, each pair of adjacent compute nodes in the rectangular mesh network connected together using a pair of links, that includes: assigning each compute node to either a first group or a second group such that adjacent compute nodes in the rectangular mesh network are assigned to different groups; sending, by each of the compute nodes assigned to the first group, a first test message to each adjacent compute node assigned to the second group; determining, by each of the compute nodes assigned to the second group, whether the first test message was received from each adjacent compute node assigned to the first group; and notifying a user, by each of the compute nodes assigned to the second group, whether the first test message was received.
Implementations of BLAST for parallel computers.
Jülich, A
1995-02-01
The BLAST sequence comparison programs have been ported to a variety of parallel computers-the shared memory machine Cray Y-MP 8/864 and the distributed memory architectures Intel iPSC/860 and nCUBE. Additionally, the programs were ported to run on workstation clusters. We explain the parallelization techniques and consider the pros and cons of these methods. The BLAST programs are very well suited for parallelization for a moderate number of processors. We illustrate our results using the program blastp as an example. As input data for blastp, a 799 residue protein query sequence and the protein database PIR were used.
A 3D gyrokinetic particle-in-cell simulation of fusion plasma microturbulence on parallel computers
Williams, T. J.
1992-12-01
One of the grand challenge problems now supported by HPCC is the Numerical Tokamak Project. A goal of this project is the study of low-frequency micro-instabilities in tokamak plasmas, which are believed to cause energy loss via turbulent thermal transport across the magnetic field lines. An important tool in this study is gyrokinetic particle-in-cell (PIC) simulation. Gyrokinetic, as opposed to fully-kinetic, methods are particularly well suited to the task because they are optimized to study the frequency and wavelength domain of the microinstabilities. Furthermore, many researchers now employ low-noise delta(f) methods to greatly reduce statistical noise by modelling only the perturbation of the gyrokinetic distribution function from a fixed background, not the entire distribution function. In spite of the increased efficiency of these improved algorithms over conventional PIC algorithms, gyrokinetic PIC simulations of tokamak micro-turbulence are still highly demanding of computer power--even fully-vectorized codes on vector supercomputers. For this reason, we have worked for several years to redevelop these codes on massively parallel computers. We have developed 3D gyrokinetic PIC simulation codes for SIMD and MIMD parallel processors, using control-parallel, data-parallel, and domain-decomposition message-passing (DDMP) programming paradigms. This poster summarizes our earlier work on codes for the Connection Machine and BBN TC2000 and our development of a generic DDMP code for distributed-memory parallel machines. We discuss the memory-access issues which are of key importance in writing parallel PIC codes, with special emphasis on issues peculiar to gyrokinetic PIC. We outline the domain decompositions in our new DDMP code and discuss the interplay of different domain decompositions suited for the particle-pushing and field-solution components of the PIC algorithm.
Parallel visualization on leadership computing resources
Energy Technology Data Exchange (ETDEWEB)
Peterka, T; Ross, R B [Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL 60439 (United States); Shen, H-W [Department of Computer Science and Engineering, Ohio State University, Columbus, OH 43210 (United States); Ma, K-L [Department of Computer Science, University of California at Davis, Davis, CA 95616 (United States); Kendall, W [Department of Electrical Engineering and Computer Science, University of Tennessee at Knoxville, Knoxville, TN 37996 (United States); Yu, H, E-mail: tpeterka@mcs.anl.go [Sandia National Laboratories, California, Livermore, CA 94551 (United States)
2009-07-01
Changes are needed in the way that visualization is performed, if we expect the analysis of scientific data to be effective at the petascale and beyond. By using similar techniques as those used to parallelize simulations, such as parallel I/O, load balancing, and effective use of interprocess communication, the supercomputers that compute these datasets can also serve as analysis and visualization engines for them. Our team is assessing the feasibility of performing parallel scientific visualization on some of the most powerful computational resources of the U.S. Department of Energy's National Laboratories in order to pave the way for analyzing the next generation of computational results. This paper highlights some of the conclusions of that research.
Parallel visualization on leadership computing resources
International Nuclear Information System (INIS)
Peterka, T; Ross, R B; Shen, H-W; Ma, K-L; Kendall, W; Yu, H
2009-01-01
Changes are needed in the way that visualization is performed, if we expect the analysis of scientific data to be effective at the petascale and beyond. By using similar techniques as those used to parallelize simulations, such as parallel I/O, load balancing, and effective use of interprocess communication, the supercomputers that compute these datasets can also serve as analysis and visualization engines for them. Our team is assessing the feasibility of performing parallel scientific visualization on some of the most powerful computational resources of the U.S. Department of Energy's National Laboratories in order to pave the way for analyzing the next generation of computational results. This paper highlights some of the conclusions of that research.
The new landscape of parallel computer architecture
Energy Technology Data Exchange (ETDEWEB)
Shalf, John [NERSC Division, Lawrence Berkeley National Laboratory 1 Cyclotron Road, Berkeley California, 94720 (United States)
2007-07-15
The past few years has seen a sea change in computer architecture that will impact every facet of our society as every electronic device from cell phone to supercomputer will need to confront parallelism of unprecedented scale. Whereas the conventional multicore approach (2, 4, and even 8 cores) adopted by the computing industry will eventually hit a performance plateau, the highest performance per watt and per chip area is achieved using manycore technology (hundreds or even thousands of cores). However, fully unleashing the potential of the manycore approach to ensure future advances in sustained computational performance will require fundamental advances in computer architecture and programming models that are nothing short of reinventing computing. In this paper we examine the reasons behind the movement to exponentially increasing parallelism, and its ramifications for system design, applications and programming models.
The new landscape of parallel computer architecture
International Nuclear Information System (INIS)
Shalf, John
2007-01-01
The past few years has seen a sea change in computer architecture that will impact every facet of our society as every electronic device from cell phone to supercomputer will need to confront parallelism of unprecedented scale. Whereas the conventional multicore approach (2, 4, and even 8 cores) adopted by the computing industry will eventually hit a performance plateau, the highest performance per watt and per chip area is achieved using manycore technology (hundreds or even thousands of cores). However, fully unleashing the potential of the manycore approach to ensure future advances in sustained computational performance will require fundamental advances in computer architecture and programming models that are nothing short of reinventing computing. In this paper we examine the reasons behind the movement to exponentially increasing parallelism, and its ramifications for system design, applications and programming models
Temporal fringe pattern analysis with parallel computing
International Nuclear Information System (INIS)
Tuck Wah Ng; Kar Tien Ang; Argentini, Gianluca
2005-01-01
Temporal fringe pattern analysis is invaluable in transient phenomena studies but necessitates long processing times. Here we describe a parallel computing strategy based on the single-program multiple-data model and hyperthreading processor technology to reduce the execution time. In a two-node cluster workstation configuration we found that execution periods were reduced by 1.6 times when four virtual processors were used. To allow even lower execution times with an increasing number of processors, the time allocated for data transfer, data read, and waiting should be minimized. Parallel computing is found here to present a feasible approach to reduce execution times in temporal fringe pattern analysis
Archer, Charles J.; Blocksome, Michael A.; Ratterman, Joseph D.; Smith, Brian E.
2014-08-12
Endpoint-based parallel data processing in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI composed of data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes coupled for data communications through the PAMI, including establishing a data communications geometry, the geometry specifying, for tasks representing processes of execution of the parallel application, a set of endpoints that are used in collective operations of the PAMI including a plurality of endpoints for one of the tasks; receiving in endpoints of the geometry an instruction for a collective operation; and executing the instruction for a collective operation through the endpoints in dependence upon the geometry, including dividing data communications operations among the plurality of endpoints for one of the tasks.
Arkin, Ethem; Tekinerdogan, Bedir; Imre, Kayhan M.
2017-01-01
The need for high-performance computing together with the increasing trend from single processor to parallel computer architectures has leveraged the adoption of parallel computing. To benefit from parallel computing power, usually parallel algorithms are defined that can be mapped and executed
Parallel computation of nondeterministic algorithms in VLSI
Energy Technology Data Exchange (ETDEWEB)
Hortensius, P D
1987-01-01
This work examines parallel VLSI implementations of nondeterministic algorithms. It is demonstrated that conventional pseudorandom number generators are unsuitable for highly parallel applications. Efficient parallel pseudorandom sequence generation can be accomplished using certain classes of elementary one-dimensional cellular automata. The pseudorandom numbers appear in parallel on each clock cycle. Extensive study of the properties of these new pseudorandom number generators is made using standard empirical random number tests, cycle length tests, and implementation considerations. Furthermore, it is shown these particular cellular automata can form the basis of efficient VLSI architectures for computations involved in the Monte Carlo simulation of both the percolation and Ising models from statistical mechanics. Finally, a variation on a Built-In Self-Test technique based upon cellular automata is presented. These Cellular Automata-Logic-Block-Observation (CALBO) circuits improve upon conventional design for testability circuitry.
Frontiers of massively parallel scientific computation
International Nuclear Information System (INIS)
Fischer, J.R.
1987-07-01
Practical applications using massively parallel computer hardware first appeared during the 1980s. Their development was motivated by the need for computing power orders of magnitude beyond that available today for tasks such as numerical simulation of complex physical and biological processes, generation of interactive visual displays, satellite image analysis, and knowledge based systems. Representative of the first generation of this new class of computers is the Massively Parallel Processor (MPP). A team of scientists was provided the opportunity to test and implement their algorithms on the MPP. The first results are presented. The research spans a broad variety of applications including Earth sciences, physics, signal and image processing, computer science, and graphics. The performance of the MPP was very good. Results obtained using the Connection Machine and the Distributed Array Processor (DAP) are presented
Analysis of parallel computing performance of the code MCNP
International Nuclear Information System (INIS)
Wang Lei; Wang Kan; Yu Ganglin
2006-01-01
Parallel computing can reduce the running time of the code MCNP effectively. With the MPI message transmitting software, MCNP5 can achieve its parallel computing on PC cluster with Windows operating system. Parallel computing performance of MCNP is influenced by factors such as the type, the complexity level and the parameter configuration of the computing problem. This paper analyzes the parallel computing performance of MCNP regarding with these factors and gives measures to improve the MCNP parallel computing performance. (authors)
Vector and parallel processors in computational science
International Nuclear Information System (INIS)
Duff, I.S.; Reid, J.K.
1985-01-01
These proceedings contain the articles presented at the named conference. These concern hardware and software for vector and parallel processors, numerical methods and algorithms for the computation on such processors, as well as applications of such methods to different fields of physics and related sciences. See hints under the relevant topics. (HSI)
Contributions to computational stereology and parallel programming
DEFF Research Database (Denmark)
Rasmusson, Allan
rotator, even without the need for isotropic sections. To meet the need for computational power to perform image restoration of virtual tissue sections, parallel programming on GPUs has also been part of the project. This has lead to a significant change in paradigm for a previously developed surgical...
International Nuclear Information System (INIS)
Pucello, N.; D'Agostino, G.; Pisacane, F.
1997-01-01
A genetic algorithm for the optimization of the ground-state structure of a metallic cluster has been developed and ported on a SIMD-MIMD parallel platform. The SIMD part of the parallel platform is represented by a Quadrics/APE100 consisting of 512 floating point units, while the MIMD part is formed by a cluster of workstations. The proposed algorithm is composed by a part where the genetic operators are applied to the elements of the population and a part which performs a further local relaxation and the fitness calculation via Molecular Dynamics. These parts have been implemented on the MIMD and on the SIMD part, respectively. Results have been compared to those generated by using Simulated Annealing
Java parallel secure stream for grid computing
International Nuclear Information System (INIS)
Chen, J.; Akers, W.; Chen, Y.; Watson, W.
2001-01-01
The emergence of high speed wide area networks makes grid computing a reality. However grid applications that need reliable data transfer still have difficulties to achieve optimal TCP performance due to network tuning of TCP window size to improve the bandwidth and to reduce latency on a high speed wide area network. The authors present a pure Java package called JPARSS (Java Parallel Secure Stream) that divides data into partitions that are sent over several parallel Java streams simultaneously and allows Java or Web applications to achieve optimal TCP performance in a gird environment without the necessity of tuning the TCP window size. Several experimental results are provided to show that using parallel stream is more effective than tuning TCP window size. In addition X.509 certificate based single sign-on mechanism and SSL based connection establishment are integrated into this package. Finally a few applications using this package will be discussed
Intranode data communications in a parallel computer
Archer, Charles J; Blocksome, Michael A; Miller, Douglas R; Ratterman, Joseph D; Smith, Brian E
2014-01-07
Intranode data communications in a parallel computer that includes compute nodes configured to execute processes, where the data communications include: allocating, upon initialization of a first process of a computer node, a region of shared memory; establishing, by the first process, a predefined number of message buffers, each message buffer associated with a process to be initialized on the compute node; sending, to a second process on the same compute node, a data communications message without determining whether the second process has been initialized, including storing the data communications message in the message buffer of the second process; and upon initialization of the second process: retrieving, by the second process, a pointer to the second process's message buffer; and retrieving, by the second process from the second process's message buffer in dependence upon the pointer, the data communications message sent by the first process.
Intranode data communications in a parallel computer
Archer, Charles J; Blocksome, Michael A; Miller, Douglas R; Ratterman, Joseph D; Smith, Brian E
2013-07-23
Intranode data communications in a parallel computer that includes compute nodes configured to execute processes, where the data communications include: allocating, upon initialization of a first process of a compute node, a region of shared memory; establishing, by the first process, a predefined number of message buffers, each message buffer associated with a process to be initialized on the compute node; sending, to a second process on the same compute node, a data communications message without determining whether the second process has been initialized, including storing the data communications message in the message buffer of the second process; and upon initialization of the second process: retrieving, by the second process, a pointer to the second process's message buffer; and retrieving, by the second process from the second process's message buffer in dependence upon the pointer, the data communications message sent by the first process.
Parallel evolutionary computation in bioinformatics applications.
Pinho, Jorge; Sobral, João Luis; Rocha, Miguel
2013-05-01
A large number of optimization problems within the field of Bioinformatics require methods able to handle its inherent complexity (e.g. NP-hard problems) and also demand increased computational efforts. In this context, the use of parallel architectures is a necessity. In this work, we propose ParJECoLi, a Java based library that offers a large set of metaheuristic methods (such as Evolutionary Algorithms) and also addresses the issue of its efficient execution on a wide range of parallel architectures. The proposed approach focuses on the easiness of use, making the adaptation to distinct parallel environments (multicore, cluster, grid) transparent to the user. Indeed, this work shows how the development of the optimization library can proceed independently of its adaptation for several architectures, making use of Aspect-Oriented Programming. The pluggable nature of parallelism related modules allows the user to easily configure its environment, adding parallelism modules to the base source code when needed. The performance of the platform is validated with two case studies within biological model optimization. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.
Parallel computers and three-dimensional computational electromagnetics
International Nuclear Information System (INIS)
Madsen, N.K.
1994-01-01
The authors have continued to enhance their ability to use new massively parallel processing computers to solve time-domain electromagnetic problems. New vectorization techniques have improved the performance of their code DSI3D by factors of 5 to 15, depending on the computer used. New radiation boundary conditions and far-field transformations now allow the computation of radar cross-section values for complex objects. A new parallel-data extraction code has been developed that allows the extraction of data subsets from large problems, which have been run on parallel computers, for subsequent post-processing on workstations with enhanced graphics capabilities. A new charged-particle-pushing version of DSI3D is under development. Finally, DSI3D has become a focal point for several new Cooperative Research and Development Agreement activities with industrial companies such as Lockheed Advanced Development Company, Varian, Hughes Electron Dynamics Division, General Atomic, and Cray
On synchronous parallel computations with independent probabilistic choice
International Nuclear Information System (INIS)
Reif, J.H.
1984-01-01
This paper introduces probabilistic choice to synchronous parallel machine models; in particular parallel RAMs. The power of probabilistic choice in parallel computations is illustrate by parallelizing some known probabilistic sequential algorithms. The authors characterize the computational complexity of time, space, and processor bounded probabilistic parallel RAMs in terms of the computational complexity of probabilistic sequential RAMs. They show that parallelism uniformly speeds up time bounded probabilistic sequential RAM computations by nearly a quadratic factor. They also show that probabilistic choice can be eliminated from parallel computations by introducing nonuniformity
Efficient Parallel Engineering Computing on Linux Workstations
Lou, John Z.
2010-01-01
A C software module has been developed that creates lightweight processes (LWPs) dynamically to achieve parallel computing performance in a variety of engineering simulation and analysis applications to support NASA and DoD project tasks. The required interface between the module and the application it supports is simple, minimal and almost completely transparent to the user applications, and it can achieve nearly ideal computing speed-up on multi-CPU engineering workstations of all operating system platforms. The module can be integrated into an existing application (C, C++, Fortran and others) either as part of a compiled module or as a dynamically linked library (DLL).
Mills, R. T.; Rupp, K.; Smith, B. F.; Brown, J.; Knepley, M.; Zhang, H.; Adams, M.; Hammond, G. E.
2017-12-01
As the high-performance computing community pushes towards the exascale horizon, power and heat considerations have driven the increasing importance and prevalence of fine-grained parallelism in new computer architectures. High-performance computing centers have become increasingly reliant on GPGPU accelerators and "manycore" processors such as the Intel Xeon Phi line, and 512-bit SIMD registers have even been introduced in the latest generation of Intel's mainstream Xeon server processors. The high degree of fine-grained parallelism and more complicated memory hierarchy considerations of such "manycore" processors present several challenges to existing scientific software. Here, we consider how the massively parallel, open-source hydrologic flow and reactive transport code PFLOTRAN - and the underlying Portable, Extensible Toolkit for Scientific Computation (PETSc) library on which it is built - can best take advantage of such architectures. We will discuss some key features of these novel architectures and our code optimizations and algorithmic developments targeted at them, and present experiences drawn from working with a wide range of PFLOTRAN benchmark problems on these architectures.
MoviCompile : An LLVM based compiler for heterogeneous SIMD code generation
Diken, E.; Jordans, R.; O'Riordan, M.
2015-01-01
Numerous applications in communication and multimedia domains show significant data-level parallelism (DLP). The amount of DLP varies between applications in the same domain or even within a single application. Most architectures support a single vector-, SIMD-width which may not be optimal. This
Computational chaos in massively parallel neural networks
Barhen, Jacob; Gulati, Sandeep
1989-01-01
A fundamental issue which directly impacts the scalability of current theoretical neural network models to massively parallel embodiments, in both software as well as hardware, is the inherent and unavoidable concurrent asynchronicity of emerging fine-grained computational ensembles and the possible emergence of chaotic manifestations. Previous analyses attributed dynamical instability to the topology of the interconnection matrix, to parasitic components or to propagation delays. However, researchers have observed the existence of emergent computational chaos in a concurrently asynchronous framework, independent of the network topology. Researcher present a methodology enabling the effective asynchronous operation of large-scale neural networks. Necessary and sufficient conditions guaranteeing concurrent asynchronous convergence are established in terms of contracting operators. Lyapunov exponents are computed formally to characterize the underlying nonlinear dynamics. Simulation results are presented to illustrate network convergence to the correct results, even in the presence of large delays.
(Nearly) portable PIC code for parallel computers
International Nuclear Information System (INIS)
Decyk, V.K.
1993-01-01
As part of the Numerical Tokamak Project, the author has developed a (nearly) portable, one dimensional version of the GCPIC algorithm for particle-in-cell codes on parallel computers. This algorithm uses a spatial domain decomposition for the fields, and passes particles from one domain to another as the particles move spatially. With only minor changes, the code has been run in parallel on the Intel Delta, the Cray C-90, the IBM ES/9000 and a cluster of workstations. After a line by line translation into cmfortran, the code was also run on the CM-200. Impressive speeds have been achieved, both on the Intel Delta and the Cray C-90, around 30 nanoseconds per particle per time step. In addition, the author was able to isolate the data management modules, so that the physics modules were not changed much from their sequential version, and the data management modules can be used as open-quotes black boxes.close quotes
Parallel computing techniques for rotorcraft aerodynamics
Ekici, Kivanc
The modification of unsteady three-dimensional Navier-Stokes codes for application on massively parallel and distributed computing environments is investigated. The Euler/Navier-Stokes code TURNS (Transonic Unsteady Rotor Navier-Stokes) was chosen as a test bed because of its wide use by universities and industry. For the efficient implementation of TURNS on parallel computing systems, two algorithmic changes are developed. First, main modifications to the implicit operator, Lower-Upper Symmetric Gauss Seidel (LU-SGS) originally used in TURNS, is performed. Second, application of an inexact Newton method, coupled with a Krylov subspace iterative method (Newton-Krylov method) is carried out. Both techniques have been tried previously for the Euler equations mode of the code. In this work, we have extended the methods to the Navier-Stokes mode. Several new implicit operators were tried because of convergence problems of traditional operators with the high cell aspect ratio (CAR) grids needed for viscous calculations on structured grids. Promising results for both Euler and Navier-Stokes cases are presented for these operators. For the efficient implementation of Newton-Krylov methods to the Navier-Stokes mode of TURNS, efficient preconditioners must be used. The parallel implicit operators used in the previous step are employed as preconditioners and the results are compared. The Message Passing Interface (MPI) protocol has been used because of its portability to various parallel architectures. It should be noted that the proposed methodology is general and can be applied to several other CFD codes (e.g. OVERFLOW).
Computational fluid dynamics on a massively parallel computer
Jespersen, Dennis C.; Levit, Creon
1989-01-01
A finite difference code was implemented for the compressible Navier-Stokes equations on the Connection Machine, a massively parallel computer. The code is based on the ARC2D/ARC3D program and uses the implicit factored algorithm of Beam and Warming. The codes uses odd-even elimination to solve linear systems. Timings and computation rates are given for the code, and a comparison is made with a Cray XMP.
CERN. Geneva
2016-01-01
Large scale scientific computing raises questions on different levels ranging from the fomulation of the problems to the choice of the best algorithms and their implementation for a specific platform. There are similarities in these different topics that can be exploited by modern-style C++ template metaprogramming techniques to produce readable, maintainable and generic code. Traditional low-level code tend to be fast but platform-dependent, and it obfuscates the meaning of the algorithm. On the other hand, object-oriented approach is nice to read, but may come with an inherent performance penalty. These lectures aim to present he basics of the Expression Template (ET) idiom which allows us to keep the object-oriented approach without sacrificing performance. We will in particular show to to enhance ET to include SIMD vectorization. We will then introduce techniques for abstracting iteration, and introduce thread-level parallelism for use in heavy data-centric loads. We will show to to apply these methods i...
Climate models on massively parallel computers
International Nuclear Information System (INIS)
Vitart, F.; Rouvillois, P.
1993-01-01
First results got on massively parallel computers (Multiple Instruction Multiple Data and Simple Instruction Multiple Data) allow to consider building of coupled models with high resolutions. This would make possible simulation of thermoaline circulation and other interaction phenomena between atmosphere and ocean. The increasing of computers powers, and then the improvement of resolution will go us to revise our approximations. Then hydrostatic approximation (in ocean circulation) will not be valid when the grid mesh will be of a dimension lower than a few kilometers: We shall have to find other models. The expert appraisement got in numerical analysis at the Center of Limeil-Valenton (CEL-V) will be used again to imagine global models taking in account atmosphere, ocean, ice floe and biosphere, allowing climate simulation until a regional scale
Massively parallel computation of conservation laws
Energy Technology Data Exchange (ETDEWEB)
Garbey, M [Univ. Claude Bernard, Villeurbanne (France); Levine, D [Argonne National Lab., IL (United States)
1990-01-01
The authors present a new method for computing solutions of conservation laws based on the use of cellular automata with the method of characteristics. The method exploits the high degree of parallelism available with cellular automata and retains important features of the method of characteristics. It yields high numerical accuracy and extends naturally to adaptive meshes and domain decomposition methods for perturbed conservation laws. They describe the method and its implementation for a Dirichlet problem with a single conservation law for the one-dimensional case. Numerical results for the one-dimensional law with the classical Burgers nonlinearity or the Buckley-Leverett equation show good numerical accuracy outside the neighborhood of the shocks. The error in the area of the shocks is of the order of the mesh size. The algorithm is well suited for execution on both massively parallel computers and vector machines. They present timing results for an Alliant FX/8, Connection Machine Model 2, and CRAY X-MP.
A Computational Fluid Dynamics Algorithm on a Massively Parallel Computer
Jespersen, Dennis C.; Levit, Creon
1989-01-01
The discipline of computational fluid dynamics is demanding ever-increasing computational power to deal with complex fluid flow problems. We investigate the performance of a finite-difference computational fluid dynamics algorithm on a massively parallel computer, the Connection Machine. Of special interest is an implicit time-stepping algorithm; to obtain maximum performance from the Connection Machine, it is necessary to use a nonstandard algorithm to solve the linear systems that arise in the implicit algorithm. We find that the Connection Machine ran achieve very high computation rates on both explicit and implicit algorithms. The performance of the Connection Machine puts it in the same class as today's most powerful conventional supercomputers.
Reduction operator for wide-SIMDs reconsidered
Waeijen, L.J.W.; She, D.; Corporaal, H.; He, Y.
2014-01-01
It has been shown that wide Single Instruction Multiple Data architectures (wide-SIMDs) can achieve high energy efficiency, especially in domains such as image and vision processing. In these and various other application domains, reduction is a frequently encountered operation, where multiple input
External parallel sorting with multiprocessor computers
International Nuclear Information System (INIS)
Comanceau, S.I.
1984-01-01
This article describes methods of external sorting in which the entire main computer memory is used for the internal sorting of entries, forming out of them sorted segments of the greatest possible size, and outputting them to external memories. The obtained segments are merged into larger segments until all entries form one ordered segment. The described methods are suitable for sequential files stored on magnetic tape. The needs of the sorting algorithm can be met by using the relatively slow peripheral storage devices (e.g., tapes, disks, drums). The efficiency of the external sorting methods is determined by calculating the total sorting time as a function of the number of entries to be sorted and the number of parallel processors participating in the sorting process
Contact-impact algorithms on parallel computers
International Nuclear Information System (INIS)
Zhong Zhihua; Nilsson, Larsgunnar
1994-01-01
Contact-impact algorithms on parallel computers are discussed within the context of explicit finite element analysis. The algorithms concerned include a contact searching algorithm and an algorithm for contact force calculations. The contact searching algorithm is based on the territory concept of the general HITA algorithm. However, no distinction is made between different contact bodies, or between different contact surfaces. All contact segments from contact boundaries are taken as a single set. Hierarchy territories and contact territories are expanded. A three-dimensional bucket sort algorithm is used to sort contact nodes. The defence node algorithm is used in the calculation of contact forces. Both the contact searching algorithm and the defence node algorithm are implemented on the connection machine CM-200. The performance of the algorithms is examined under different circumstances, and numerical results are presented. ((orig.))
Distributed Memory Parallel Computing with SEAWAT
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
Automatic Parallelization Tool: Classification of Program Code for Parallel Computing
Directory of Open Access Journals (Sweden)
Mustafa Basthikodi
2016-04-01
Full Text Available Performance growth of single-core processors has come to a halt in the past decade, but was re-enabled by the introduction of parallelism in processors. Multicore frameworks along with Graphical Processing Units empowered to enhance parallelism broadly. Couples of compilers are updated to developing challenges forsynchronization and threading issues. Appropriate program and algorithm classifications will have advantage to a great extent to the group of software engineers to get opportunities for effective parallelization. In present work we investigated current species for classification of algorithms, in that related work on classification is discussed along with the comparison of issues that challenges the classification. The set of algorithms are chosen which matches the structure with different issues and perform given task. We have tested these algorithms utilizing existing automatic species extraction toolsalong with Bones compiler. We have added functionalities to existing tool, providing a more detailed characterization. The contributions of our work include support for pointer arithmetic, conditional and incremental statements, user defined types, constants and mathematical functions. With this, we can retain significant data which is not captured by original speciesof algorithms. We executed new theories into the device, empowering automatic characterization of program code.
Broadcasting collective operation contributions throughout a parallel computer
Faraj, Ahmad [Rochester, MN
2012-02-21
Methods, systems, and products are disclosed for broadcasting collective operation contributions throughout a parallel computer. The parallel computer includes a plurality of compute nodes connected together through a data communications network. Each compute node has a plurality of processors for use in collective parallel operations on the parallel computer. Broadcasting collective operation contributions throughout a parallel computer according to embodiments of the present invention includes: transmitting, by each processor on each compute node, that processor's collective operation contribution to the other processors on that compute node using intra-node communications; and transmitting on a designated network link, by each processor on each compute node according to a serial processor transmission sequence, that processor's collective operation contribution to the other processors on the other compute nodes using inter-node communications.
Applications of the parallel computing system using network
International Nuclear Information System (INIS)
Ido, Shunji; Hasebe, Hiroki
1994-01-01
Parallel programming is applied to multiple processors connected in Ethernet. Data exchanges between tasks located in each processing element are realized by two ways. One is socket which is standard library on recent UNIX operating systems. Another is a network connecting software, named as Parallel Virtual Machine (PVM) which is a free software developed by ORNL, to use many workstations connected to network as a parallel computer. This paper discusses the availability of parallel computing using network and UNIX workstations and comparison between specialized parallel systems (Transputer and iPSC/860) in a Monte Carlo simulation which generally shows high parallelization ratio. (author)
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
Arkin, Ethem; Tekinerdogan, Bedir
2016-01-01
Mapping parallel algorithms to parallel computing platforms requires several activities such as the analysis of the parallel algorithm, the definition of the logical configuration of the platform, the mapping of the algorithm to the logical configuration platform and the implementation of the
Data communications in a parallel active messaging interface of a parallel computer
Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E
2013-11-12
Data communications in a parallel active messaging interface (`PAMI`) of a parallel computer composed of compute nodes that execute a parallel application, each compute node including application processors that execute the parallel application and at least one management processor dedicated to gathering information regarding data communications. The PAMI is composed of data communications endpoints, each endpoint composed of a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes and the endpoints coupled for data communications through the PAMI and through data communications resources. Embodiments function by gathering call site statistics describing data communications resulting from execution of data communications instructions and identifying in dependence upon the call cite statistics a data communications algorithm for use in executing a data communications instruction at a call site in the parallel application.
Parallel Computing for Terrestrial Ecosystem Carbon Modeling
International Nuclear Information System (INIS)
Wang, Dali; Post, Wilfred M.; Ricciuto, Daniel M.; Berry, Michael
2011-01-01
Terrestrial ecosystems are a primary component of research on global environmental change. Observational and modeling research on terrestrial ecosystems at the global scale, however, has lagged behind their counterparts for oceanic and atmospheric systems, largely because the unique challenges associated with the tremendous diversity and complexity of terrestrial ecosystems. There are 8 major types of terrestrial ecosystem: tropical rain forest, savannas, deserts, temperate grassland, deciduous forest, coniferous forest, tundra, and chaparral. The carbon cycle is an important mechanism in the coupling of terrestrial ecosystems with climate through biological fluxes of CO 2 . The influence of terrestrial ecosystems on atmospheric CO 2 can be modeled via several means at different timescales. Important processes include plant dynamics, change in land use, as well as ecosystem biogeography. Over the past several decades, many terrestrial ecosystem models (see the 'Model developments' section) have been developed to understand the interactions between terrestrial carbon storage and CO 2 concentration in the atmosphere, as well as the consequences of these interactions. Early TECMs generally adapted simple box-flow exchange models, in which photosynthetic CO 2 uptake and respiratory CO 2 release are simulated in an empirical manner with a small number of vegetation and soil carbon pools. Demands on kinds and amount of information required from global TECMs have grown. Recently, along with the rapid development of parallel computing, spatially explicit TECMs with detailed process based representations of carbon dynamics become attractive, because those models can readily incorporate a variety of additional ecosystem processes (such as dispersal, establishment, growth, mortality etc.) and environmental factors (such as landscape position, pest populations, disturbances, resource manipulations, etc.), and provide information to frame policy options for climate change
Fast parallel computation of polynomials using few processors
DEFF Research Database (Denmark)
Valiant, Leslie; Skyum, Sven
1981-01-01
It is shown that any multivariate polynomial that can be computed sequentially in C steps and has degree d can be computed in parallel in 0((log d) (log C + log d)) steps using only (Cd)0(1) processors....
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...
Solving the Stokes problem on a massively parallel computer
DEFF Research Database (Denmark)
Axelsson, Owe; Barker, Vincent A.; Neytcheva, Maya
2001-01-01
boundary value problem for each velocity component, are solved by the conjugate gradient method with a preconditioning based on the algebraic multi‐level iteration (AMLI) technique. The velocity is found from the computed pressure. The method is optimal in the sense that the computational work...... is proportional to the number of unknowns. Further, it is designed to exploit a massively parallel computer with distributed memory architecture. Numerical experiments on a Cray T3E computer illustrate the parallel performance of the method....
Tramm, John R.; Gunow, Geoffrey; He, Tim; Smith, Kord S.; Forget, Benoit; Siegel, Andrew R.
2016-05-01
In this study we present and analyze a formulation of the 3D Method of Characteristics (MOC) technique applied to the simulation of full core nuclear reactors. Key features of the algorithm include a task-based parallelism model that allows independent MOC tracks to be assigned to threads dynamically, ensuring load balancing, and a wide vectorizable inner loop that takes advantage of modern SIMD computer architectures. The algorithm is implemented in a set of highly optimized proxy applications in order to investigate its performance characteristics on CPU, GPU, and Intel Xeon Phi architectures. Speed, power, and hardware cost efficiencies are compared. Additionally, performance bottlenecks are identified for each architecture in order to determine the prospects for continued scalability of the algorithm on next generation HPC architectures.
Numerical discrepancy between serial and MPI parallel computations
Directory of Open Access Journals (Sweden)
Sang Bong Lee
2016-09-01
Full Text Available Numerical simulations of 1D Burgers equation and 2D sloshing problem were carried out to study numerical discrepancy between serial and parallel computations. The numerical domain was decomposed into 2 and 4 subdomains for parallel computations with message passing interface. The numerical solution of Burgers equation disclosed that fully explicit boundary conditions used on subdomains of parallel computation was responsible for the numerical discrepancy of transient solution between serial and parallel computations. Two dimensional sloshing problems in a rectangular domain were solved using OpenFOAM. After a lapse of initial transient time sloshing patterns of water were significantly different in serial and parallel computations although the same numerical conditions were given. Based on the histograms of pressure measured at two points near the wall the statistical characteristics of numerical solution was not affected by the number of subdomains as much as the transient solution was dependent on the number of subdomains.
Parallel computation for solving the tridiagonal linear system of equations
International Nuclear Information System (INIS)
Ishiguro, Misako; Harada, Hiroo; Fujii, Minoru; Fujimura, Toichiro; Nakamura, Yasuhiro; Nanba, Katsumi.
1981-09-01
Recently, applications of parallel computation for scientific calculations have increased from the need of the high speed calculation of large scale programs. At the JAERI computing center, an array processor FACOM 230-75 APU has installed to study the applicability of parallel computation for nuclear codes. We made some numerical experiments by using the APU on the methods of solution of tridiagonal linear equation which is an important problem in scientific calculations. Referring to the recent papers with parallel methods, we investigate eight ones. These are Gauss elimination method, Parallel Gauss method, Accelerated parallel Gauss method, Jacobi method, Recursive doubling method, Cyclic reduction method, Chebyshev iteration method, and Conjugate gradient method. The computing time and accuracy were compared among the methods on the basis of the numerical experiments. As the result, it is found that the Cyclic reduction method is best both in computing time and accuracy and the Gauss elimination method is the second one. (author)
The Research of the Parallel Computing Development from the Angle of Cloud Computing
Peng, Zhensheng; Gong, Qingge; Duan, Yanyu; Wang, Yun
2017-10-01
Cloud computing is the development of parallel computing, distributed computing and grid computing. The development of cloud computing makes parallel computing come into people’s lives. Firstly, this paper expounds the concept of cloud computing and introduces two several traditional parallel programming model. Secondly, it analyzes and studies the principles, advantages and disadvantages of OpenMP, MPI and Map Reduce respectively. Finally, it takes MPI, OpenMP models compared to Map Reduce from the angle of cloud computing. The results of this paper are intended to provide a reference for the development of parallel computing.
Data communications in a parallel active messaging interface of a parallel computer
Archer, Charles J; Blocksome, Michael A; Ratterman, Joseph D; Smith, Brian E
2013-10-29
Data communications in a parallel active messaging interface (`PAMI`) of a parallel computer, the parallel computer including a plurality of compute nodes that execute a parallel application, the PAMI composed of data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task, the compute nodes and the endpoints coupled for data communications through the PAMI and through data communications resources, including receiving in an origin endpoint of the PAMI a data communications instruction, the instruction characterized by an instruction type, the instruction specifying a transmission of transfer data from the origin endpoint to a target endpoint and transmitting, in accordance with the instruction type, the transfer data from the origin endpoint to the target endpoint.
The ongoing investigation of high performance parallel computing in HEP
Peach, Kenneth J; Böck, R K; Dobinson, Robert W; Hansroul, M; Norton, Alan Robert; Willers, Ian Malcolm; Baud, J P; Carminati, F; Gagliardi, F; McIntosh, E; Metcalf, M; Robertson, L; CERN. Geneva. Detector Research and Development Committee
1993-01-01
Past and current exploitation of parallel computing in High Energy Physics is summarized and a list of R & D projects in this area is presented. The applicability of new parallel hardware and software to physics problems is investigated, in the light of the requirements for computing power of LHC experiments and the current trends in the computer industry. Four main themes are discussed (possibilities for a finer grain of parallelism; fine-grain communication mechanism; usable parallel programming environment; different programming models and architectures, using standard commercial products). Parallel computing technology is potentially of interest for offline and vital for real time applications in LHC. A substantial investment in applications development and evaluation of state of the art hardware and software products is needed. A solid development environment is required at an early stage, before mainline LHC program development begins.
Murni, Bustamam, A.; Ernastuti, Handhika, T.; Kerami, D.
2017-07-01
Calculation of the matrix-vector multiplication in the real-world problems often involves large matrix with arbitrary size. Therefore, parallelization is needed to speed up the calculation process that usually takes a long time. Graph partitioning techniques that have been discussed in the previous studies cannot be used to complete the parallelized calculation of matrix-vector multiplication with arbitrary size. This is due to the assumption of graph partitioning techniques that can only solve the square and symmetric matrix. Hypergraph partitioning techniques will overcome the shortcomings of the graph partitioning technique. This paper addresses the efficient parallelization of matrix-vector multiplication through hypergraph partitioning techniques using CUDA GPU-based parallel computing. CUDA (compute unified device architecture) is a parallel computing platform and programming model that was created by NVIDIA and implemented by the GPU (graphics processing unit).
Vector and parallel processors in computational science
International Nuclear Information System (INIS)
Duff, I.S.; Reid, J.K.
1985-01-01
This book presents the papers given at a conference which reviewed the new developments in parallel and vector processing. Topics considered at the conference included hardware (array processors, supercomputers), programming languages, software aids, numerical methods (e.g., Monte Carlo algorithms, iterative methods, finite elements, optimization), and applications (e.g., neutron transport theory, meteorology, image processing)
Partitions in languages and parallel computations
Energy Technology Data Exchange (ETDEWEB)
Burgin, M S; Burgina, E S
1982-05-01
Partitions of entries (linguistic structures) are studied that are intended for parallel data processing. The representations of formal languages with the aid of such structures is examined, and the relationships are considered between partitions of entries and abstract families of languages and automata. 18 references.
Heuristic framework for parallel sorting computations | Nwanze ...
African Journals Online (AJOL)
Parallel sorting techniques have become of practical interest with the advent of new multiprocessor architectures. The decreasing cost of these processors will probably in the future, make the solutions that are derived thereof to be more appealing. Efficient algorithms for sorting scheme that are encountered in a number of ...
Algorithms for parallel and vector computations
Ortega, James M.
1995-01-01
This is a final report on work performed under NASA grant NAG-1-1112-FOP during the period March, 1990 through February 1995. Four major topics are covered: (1) solution of nonlinear poisson-type equations; (2) parallel reduced system conjugate gradient method; (3) orderings for conjugate gradient preconditioners, and (4) SOR as a preconditioner.
Parallel computing, failure recovery, and extreme values
DEFF Research Database (Denmark)
Andersen, Lars Nørvang; Asmussen, Søren
A task of random size T is split into M subtasks of lengths T1, . . . , TM, each of which is sent to one out of M parallel processors. Each processor may fail at a random time before completing its allocated task, and then has to restart it from the beginning. If X1, . . . ,XM are the total task ...
Parallel computing by Monte Carlo codes MVP/GMVP
International Nuclear Information System (INIS)
Nagaya, Yasunobu; Nakagawa, Masayuki; Mori, Takamasa
2001-01-01
General-purpose Monte Carlo codes MVP/GMVP are well-vectorized and thus enable us to perform high-speed Monte Carlo calculations. In order to achieve more speedups, we parallelized the codes on the different types of parallel computing platforms or by using a standard parallelization library MPI. The platforms used for benchmark calculations are a distributed-memory vector-parallel computer Fujitsu VPP500, a distributed-memory massively parallel computer Intel paragon and a distributed-memory scalar-parallel computer Hitachi SR2201, IBM SP2. As mentioned generally, linear speedup could be obtained for large-scale problems but parallelization efficiency decreased as the batch size per a processing element(PE) was smaller. It was also found that the statistical uncertainty for assembly powers was less than 0.1% by the PWR full-core calculation with more than 10 million histories and it took about 1.5 hours by massively parallel computing. (author)
Parallel algorithms and architecture for computation of manipulator forward dynamics
Fijany, Amir; Bejczy, Antal K.
1989-01-01
Parallel computation of manipulator forward dynamics is investigated. Considering three classes of algorithms for the solution of the problem, that is, the O(n), the O(n exp 2), and the O(n exp 3) algorithms, parallelism in the problem is analyzed. It is shown that the problem belongs to the class of NC and that the time and processors bounds are of O(log2/2n) and O(n exp 4), respectively. However, the fastest stable parallel algorithms achieve the computation time of O(n) and can be derived by parallelization of the O(n exp 3) serial algorithms. Parallel computation of the O(n exp 3) algorithms requires the development of parallel algorithms for a set of fundamentally different problems, that is, the Newton-Euler formulation, the computation of the inertia matrix, decomposition of the symmetric, positive definite matrix, and the solution of triangular systems. Parallel algorithms for this set of problems are developed which can be efficiently implemented on a unique architecture, a triangular array of n(n+2)/2 processors with a simple nearest-neighbor interconnection. This architecture is particularly suitable for VLSI and WSI implementations. The developed parallel algorithm, compared to the best serial O(n) algorithm, achieves an asymptotic speedup of more than two orders-of-magnitude in the computation the forward dynamics.
Streaming for Functional Data-Parallel Languages
DEFF Research Database (Denmark)
Madsen, Frederik Meisner
In this thesis, we investigate streaming as a general solution to the space inefficiency commonly found in functional data-parallel programming languages. The data-parallel paradigm maps well to parallel SIMD-style hardware. However, the traditional fully materializing execution strategy...... by extending two existing data-parallel languages: NESL and Accelerate. In the extensions we map bulk operations to data-parallel streams that can evaluate fully sequential, fully parallel or anything in between. By a dataflow, piecewise parallel execution strategy, the runtime system can adjust to any target...... flattening necessitates all sub-computations to materialize at the same time. For example, naive n by n matrix multiplication requires n^3 space in NESL because the algorithm contains n^3 independent scalar multiplications. For large values of n, this is completely unacceptable. We address the problem...
Fast parallel event reconstruction
CERN. Geneva
2010-01-01
On-line processing of large data volumes produced in modern HEP experiments requires using maximum capabilities of modern and future many-core CPU and GPU architectures.One of such powerful feature is a SIMD instruction set, which allows packing several data items in one register and to operate on all of them, thus achievingmore operations per clock cycle. Motivated by the idea of using the SIMD unit ofmodern processors, the KF based track fit has been adapted for parallelism, including memory optimization, numerical analysis, vectorization with inline operator overloading, and optimization using SDKs. The speed of the algorithm has been increased in 120000 times with 0.1 ms/track, running in parallel on 16 SPEs of a Cell Blade computer. Running on a Nehalem CPU with 8 cores it shows the processing speed of 52 ns/track using the Intel Threading Building Blocks. The same KF algorithm running on an Nvidia GTX 280 in the CUDA frameworkprovi...
Highly parallel machines and future of scientific computing
International Nuclear Information System (INIS)
Singh, G.S.
1992-01-01
Computing requirement of large scale scientific computing has always been ahead of what state of the art hardware could supply in the form of supercomputers of the day. And for any single processor system the limit to increase in the computing power was realized a few years back itself. Now with the advent of parallel computing systems the availability of machines with the required computing power seems a reality. In this paper the author tries to visualize the future large scale scientific computing in the penultimate decade of the present century. The author summarized trends in parallel computers and emphasize the need for a better programming environment and software tools for optimal performance. The author concludes this paper with critique on parallel architectures, software tools and algorithms. (author). 10 refs., 2 tabs
Parallel computing in genomic research: advances and applications
Directory of Open Access Journals (Sweden)
Ocaña K
2015-11-01
Full Text Available Kary Ocaña,1 Daniel de Oliveira2 1National Laboratory of Scientific Computing, Petrópolis, Rio de Janeiro, 2Institute of Computing, Fluminense Federal University, Niterói, Brazil Abstract: Today's genomic experiments have to process the so-called "biological big data" that is now reaching the size of Terabytes and Petabytes. To process this huge amount of data, scientists may require weeks or months if they use their own workstations. Parallelism techniques and high-performance computing (HPC environments can be applied for reducing the total processing time and to ease the management, treatment, and analyses of this data. However, running bioinformatics experiments in HPC environments such as clouds, grids, clusters, and graphics processing unit requires the expertise from scientists to integrate computational, biological, and mathematical techniques and technologies. Several solutions have already been proposed to allow scientists for processing their genomic experiments using HPC capabilities and parallelism techniques. This article brings a systematic review of literature that surveys the most recently published research involving genomics and parallel computing. Our objective is to gather the main characteristics, benefits, and challenges that can be considered by scientists when running their genomic experiments to benefit from parallelism techniques and HPC capabilities. Keywords: high-performance computing, genomic research, cloud computing, grid computing, cluster computing, parallel computing
Basic design of parallel computational program for probabilistic structural analysis
International Nuclear Information System (INIS)
Kaji, Yoshiyuki; Arai, Taketoshi; Gu, Wenwei; Nakamura, Hitoshi
1999-06-01
In our laboratory, for 'development of damage evaluation method of structural brittle materials by microscopic fracture mechanics and probabilistic theory' (nuclear computational science cross-over research) we examine computational method related to super parallel computation system which is coupled with material strength theory based on microscopic fracture mechanics for latent cracks and continuum structural model to develop new structural reliability evaluation methods for ceramic structures. This technical report is the review results regarding probabilistic structural mechanics theory, basic terms of formula and program methods of parallel computation which are related to principal terms in basic design of computational mechanics program. (author)
Basic design of parallel computational program for probabilistic structural analysis
Energy Technology Data Exchange (ETDEWEB)
Kaji, Yoshiyuki; Arai, Taketoshi [Japan Atomic Energy Research Inst., Tokai, Ibaraki (Japan). Tokai Research Establishment; Gu, Wenwei; Nakamura, Hitoshi
1999-06-01
In our laboratory, for `development of damage evaluation method of structural brittle materials by microscopic fracture mechanics and probabilistic theory` (nuclear computational science cross-over research) we examine computational method related to super parallel computation system which is coupled with material strength theory based on microscopic fracture mechanics for latent cracks and continuum structural model to develop new structural reliability evaluation methods for ceramic structures. This technical report is the review results regarding probabilistic structural mechanics theory, basic terms of formula and program methods of parallel computation which are related to principal terms in basic design of computational mechanics program. (author)
Optimized scalar promotion with load and splat SIMD instructions
Eichenberger, Alexander E; Gschwind, Michael K; Gunnels, John A
2013-10-29
Mechanisms for optimizing scalar code executed on a single instruction multiple data (SIMD) engine are provided. Placement of vector operation-splat operations may be determined based on an identification of scalar and SIMD operations in an original code representation. The original code representation may be modified to insert the vector operation-splat operations based on the determined placement of vector operation-splat operations to generate a first modified code representation. Placement of separate splat operations may be determined based on identification of scalar and SIMD operations in the first modified code representation. The first modified code representation may be modified to insert or delete separate splat operations based on the determined placement of the separate splat operations to generate a second modified code representation. SIMD code may be output based on the second modified code representation for execution by the SIMD engine.
Parallel computing in plasma physics: Nonlinear instabilities
International Nuclear Information System (INIS)
Pohn, E.; Kamelander, G.; Shoucri, M.
2000-01-01
A Vlasov-Poisson-system is used for studying the time evolution of the charge-separation at a spatial one- as well as a two-dimensional plasma-edge. Ions are advanced in time using the Vlasov-equation. The whole three-dimensional velocity-space is considered leading to very time-consuming four-resp. five-dimensional fully kinetic simulations. In the 1D simulations electrons are assumed to behave adiabatic, i.e. they are Boltzmann-distributed, leading to a nonlinear Poisson-equation. In the 2D simulations a gyro-kinetic approximation is used for the electrons. The plasma is assumed to be initially neutral. The simulations are performed at an equidistant grid. A constant time-step is used for advancing the density-distribution function in time. The time-evolution of the distribution function is performed using a splitting scheme. Each dimension (x, y, υ x , υ y , υ z ) of the phase-space is advanced in time separately. The value of the distribution function for the next time is calculated from the value of an - in general - interstitial point at the present time (fractional shift). One-dimensional cubic-spline interpolation is used for calculating the interstitial function values. After the fractional shifts are performed for each dimension of the phase-space, a whole time-step for advancing the distribution function is finished. Afterwards the charge density is calculated, the Poisson-equation is solved and the electric field is calculated before the next time-step is performed. The fractional shift method sketched above was parallelized for p processors as follows. Considering first the shifts in y-direction, a proper parallelization strategy is to split the grid into p disjoint υ z -slices, which are sub-grids, each containing a different 1/p-th part of the υ z range but the whole range of all other dimensions. Each processor is responsible for performing the y-shifts on a different slice, which can be done in parallel without any communication between
2D-RBUC for efficient parallel compression of residuals
Đurđević, Đorđe M.; Tartalja, Igor I.
2018-02-01
In this paper, we present a method for lossless compression of residuals with an efficient SIMD parallel decompression. The residuals originate from lossy or near lossless compression of height fields, which are commonly used to represent models of terrains. The algorithm is founded on the existing RBUC method for compression of non-uniform data sources. We have adapted the method to capture 2D spatial locality of height fields, and developed the data decompression algorithm for modern GPU architectures already present even in home computers. In combination with the point-level SIMD-parallel lossless/lossy high field compression method HFPaC, characterized by fast progressive decompression and seamlessly reconstructed surface, the newly proposed method trades off small efficiency degradation for a non negligible compression ratio (measured up to 91%) benefit.
Research in Parallel Algorithms and Software for Computational Aerosciences
Domel, Neal D.
1996-01-01
Phase 1 is complete for the development of a computational fluid dynamics CFD) parallel code with automatic grid generation and adaptation for the Euler analysis of flow over complex geometries. SPLITFLOW, an unstructured Cartesian grid code developed at Lockheed Martin Tactical Aircraft Systems, has been modified for a distributed memory/massively parallel computing environment. The parallel code is operational on an SGI network, Cray J90 and C90 vector machines, SGI Power Challenge, and Cray T3D and IBM SP2 massively parallel machines. Parallel Virtual Machine (PVM) is the message passing protocol for portability to various architectures. A domain decomposition technique was developed which enforces dynamic load balancing to improve solution speed and memory requirements. A host/node algorithm distributes the tasks. The solver parallelizes very well, and scales with the number of processors. Partially parallelized and non-parallelized tasks consume most of the wall clock time in a very fine grain environment. Timing comparisons on a Cray C90 demonstrate that Parallel SPLITFLOW runs 2.4 times faster on 8 processors than its non-parallel counterpart autotasked over 8 processors.
Parallel computing solution of Boltzmann neutron transport equation
International Nuclear Information System (INIS)
Ansah-Narh, T.
2010-01-01
The focus of the research was on developing parallel computing algorithm for solving Eigen-values of the Boltzmam Neutron Transport Equation (BNTE) in a slab geometry using multi-grid approach. In response to the problem of slow execution of serial computing when solving large problems, such as BNTE, the study was focused on the design of parallel computing systems which was an evolution of serial computing that used multiple processing elements simultaneously to solve complex physical and mathematical problems. Finite element method (FEM) was used for the spatial discretization scheme, while angular discretization was accomplished by expanding the angular dependence in terms of Legendre polynomials. The eigenvalues representing the multiplication factors in the BNTE were determined by the power method. MATLAB Compiler Version 4.1 (R2009a) was used to compile the MATLAB codes of BNTE. The implemented parallel algorithms were enabled with matlabpool, a Parallel Computing Toolbox function. The option UseParallel was set to 'always' and the default value of the option was 'never'. When those conditions held, the solvers computed estimated gradients in parallel. The parallel computing system was used to handle all the bottlenecks in the matrix generated from the finite element scheme and each domain of the power method generated. The parallel algorithm was implemented on a Symmetric Multi Processor (SMP) cluster machine, which had Intel 32 bit quad-core x 86 processors. Convergence rates and timings for the algorithm on the SMP cluster machine were obtained. Numerical experiments indicated the designed parallel algorithm could reach perfect speedup and had good stability and scalability. (au)
Fluid dynamics parallel computer development at NASA Langley Research Center
Townsend, James C.; Zang, Thomas A.; Dwoyer, Douglas L.
1987-01-01
To accomplish more detailed simulations of highly complex flows, such as the transition to turbulence, fluid dynamics research requires computers much more powerful than any available today. Only parallel processing on multiple-processor computers offers hope for achieving the required effective speeds. Looking ahead to the use of these machines, the fluid dynamicist faces three issues: algorithm development for near-term parallel computers, architecture development for future computer power increases, and assessment of possible advantages of special purpose designs. Two projects at NASA Langley address these issues. Software development and algorithm exploration is being done on the FLEX/32 Parallel Processing Research Computer. New architecture features are being explored in the special purpose hardware design of the Navier-Stokes Computer. These projects are complementary and are producing promising results.
Climate Ocean Modeling on Parallel Computers
Wang, P.; Cheng, B. N.; Chao, Y.
1998-01-01
Ocean modeling plays an important role in both understanding the current climatic conditions and predicting future climate change. However, modeling the ocean circulation at various spatial and temporal scales is a very challenging computational task.
History Matching in Parallel Computational Environments
Energy Technology Data Exchange (ETDEWEB)
Steven Bryant; Sanjay Srinivasan; Alvaro Barrera; Sharad Yadav
2004-08-31
In the probabilistic approach for history matching, the information from the dynamic data is merged with the prior geologic information in order to generate permeability models consistent with the observed dynamic data as well as the prior geology. The relationship between dynamic response data and reservoir attributes may vary in different regions of the reservoir due to spatial variations in reservoir attributes, fluid properties, well configuration, flow constrains on wells etc. This implies probabilistic approach should then update different regions of the reservoir in different ways. This necessitates delineation of multiple reservoir domains in order to increase the accuracy of the approach. The research focuses on a probabilistic approach to integrate dynamic data that ensures consistency between reservoir models developed from one stage to the next. The algorithm relies on efficient parameterization of the dynamic data integration problem and permits rapid assessment of the updated reservoir model at each stage. The report also outlines various domain decomposition schemes from the perspective of increasing the accuracy of probabilistic approach of history matching. Research progress in three important areas of the project are discussed: {lg_bullet}Validation and testing the probabilistic approach to incorporating production data in reservoir models. {lg_bullet}Development of a robust scheme for identifying reservoir regions that will result in a more robust parameterization of the history matching process. {lg_bullet}Testing commercial simulators for parallel capability and development of a parallel algorithm for history matching.
Parallel computing for event reconstruction in high-energy physics
International Nuclear Information System (INIS)
Wolbers, S.
1993-01-01
Parallel computing has been recognized as a solution to large computing problems. In High Energy Physics offline event reconstruction of detector data is a very large computing problem that has been solved with parallel computing techniques. A review of the parallel programming package CPS (Cooperative Processes Software) developed and used at Fermilab for offline reconstruction of Terabytes of data requiring the delivery of hundreds of Vax-Years per experiment is given. The Fermilab UNIX farms, consisting of 180 Silicon Graphics workstations and 144 IBM RS6000 workstations, are used to provide the computing power for the experiments. Fermilab has had a long history of providing production parallel computing starting with the ACP (Advanced Computer Project) Farms in 1986. The Fermilab UNIX Farms have been in production for over 2 years with 24 hour/day service to experimental user groups. Additional tools for management, control and monitoring these large systems will be described. Possible future directions for parallel computing in High Energy Physics will be given
Parallelism, fractal geometry and other aspects of computational mathematics
International Nuclear Information System (INIS)
Churchhouse, R.F.
1991-01-01
In some fields such as meteorology, theoretical physics, quantum chemistry and hydrodynamics there are problems which involve so much computation that computers of the power of a thousand times a Cray 2 could be fully utilised if they were available. Since it is unlikely that uniprocessors of such power will be available, such large scale problems could be solved by using systems of computers running in parallel. This approach, of course, requires to find appropriate algorithms for the solution of such problems which can efficiently make use of a large number of computers working in parallel. 11 refs, 10 figs, 1 tab
Parallel ray tracing for one-dimensional discrete ordinate computations
International Nuclear Information System (INIS)
Jarvis, R.D.; Nelson, P.
1996-01-01
The ray-tracing sweep in discrete-ordinates, spatially discrete numerical approximation methods applied to the linear, steady-state, plane-parallel, mono-energetic, azimuthally symmetric, neutral-particle transport equation can be reduced to a parallel prefix computation. In so doing, the often severe penalty in convergence rate of the source iteration, suffered by most current parallel algorithms using spatial domain decomposition, can be avoided while attaining parallelism in the spatial domain to whatever extent desired. In addition, the reduction implies parallel algorithm complexity limits for the ray-tracing sweep. The reduction applies to all closed, linear, one-cell functional (CLOF) spatial approximation methods, which encompasses most in current popular use. Scalability test results of an implementation of the algorithm on a 64-node nCube-2S hypercube-connected, message-passing, multi-computer are described. (author)
Parallel computer calculation of quantum spin lattices
International Nuclear Information System (INIS)
Lamarcq, J.
1998-01-01
Numerical simulation allows the theorists to convince themselves about the validity of the models they use. Particularly by simulating the spin lattices one can judge about the validity of a conjecture. Simulating a system defined by a large number of degrees of freedom requires highly sophisticated machines. This study deals with modelling the magnetic interactions between the ions of a crystal. Many exact results have been found for spin 1/2 systems but not for systems of other spins for which many simulation have been carried out. The interest for simulations has been renewed by the Haldane's conjecture stipulating the existence of a energy gap between the ground state and the first excited states of a spin 1 lattice. The existence of this gap has been experimentally demonstrated. This report contains the following four chapters: 1. Spin systems; 2. Calculation of eigenvalues; 3. Programming; 4. Parallel calculation
Parallel structures in human and computer memory
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.
Misleading Performance Claims in Parallel Computations
Energy Technology Data Exchange (ETDEWEB)
Bailey, David H.
2009-05-29
In a previous humorous note entitled 'Twelve Ways to Fool the Masses,' I outlined twelve common ways in which performance figures for technical computer systems can be distorted. In this paper and accompanying conference talk, I give a reprise of these twelve 'methods' and give some actual examples that have appeared in peer-reviewed literature in years past. I then propose guidelines for reporting performance, the adoption of which would raise the level of professionalism and reduce the level of confusion, not only in the world of device simulation but also in the larger arena of technical computing.
Global seismic tomography and modern parallel computers
Directory of Open Access Journals (Sweden)
A. Piersanti
2006-06-01
Full Text Available A fast technological progress is providing seismic tomographers with computers of rapidly increasing speed and RAM, that are not always properly taken advantage of. Large computers with both shared-memory and distributedmemory architectures have made it possible to approach the tomographic inverse problem more accurately. For example, resolution can be quantified from the resolution matrix rather than checkerboard tests; the covariance matrix can be calculated to evaluate the propagation of errors from data to model parameters; the L-curve method can be applied to determine a range of acceptable regularization schemes. We show how these exercises can be implemented efficiently on different hardware architectures.
Integrated computer network high-speed parallel interface
International Nuclear Information System (INIS)
Frank, R.B.
1979-03-01
As the number and variety of computers within Los Alamos Scientific Laboratory's Central Computer Facility grows, the need for a standard, high-speed intercomputer interface has become more apparent. This report details the development of a High-Speed Parallel Interface from conceptual through implementation stages to meet current and future needs for large-scle network computing within the Integrated Computer Network. 4 figures
Parallel algorithms and archtectures for computational structural mechanics
Patrick, Merrell; Ma, Shing; Mahajan, Umesh
1989-01-01
The determination of the fundamental (lowest) natural vibration frequencies and associated mode shapes is a key step used to uncover and correct potential failures or problem areas in most complex structures. However, the computation time taken by finite element codes to evaluate these natural frequencies is significant, often the most computationally intensive part of structural analysis calculations. There is continuing need to reduce this computation time. This study addresses this need by developing methods for parallel computation.
Finite element electromagnetic field computation on the Sequent Symmetry 81 parallel computer
International Nuclear Information System (INIS)
Ratnajeevan, S.; Hoole, H.
1990-01-01
Finite element field analysis algorithms lend themselves to parallelization and this fact is exploited in this paper to implement a finite element analysis program for electromagnetic field computation on the Sequent Symmetry 81 parallel computer with three processors. In terms of waiting time, the maximum gains are to be made in matrix solution and therefore this paper concentrates on the gains in parallelizing the solution part of finite element analysis. An outline of how parallelization could be exploited in most finite element operations is given in this paper although the actual implemention of parallelism on the Sequent Symmetry 81 parallel computer was in sparsity computation, matrix assembly and the matrix solution areas. In all cases, the algorithms were modified suit the parallel programming application rather than allowing the compiler to parallelize on existing algorithms
A microeconomic scheduler for parallel computers
Stoica, Ion; Abdel-Wahab, Hussein; Pothen, Alex
1995-01-01
We describe a scheduler based on the microeconomic paradigm for scheduling on-line a set of parallel jobs in a multiprocessor system. In addition to the classical objectives of increasing the system throughput and reducing the response time, we consider fairness in allocating system resources among the users, and providing the user with control over the relative performances of his jobs. We associate with every user a savings account in which he receives money at a constant rate. When a user wants to run a job, he creates an expense account for that job to which he transfers money from his savings account. The job uses the funds in its expense account to obtain the system resources it needs for execution. The share of the system resources allocated to the user is directly related to the rate at which the user receives money; the rate at which the user transfers money into a job expense account controls the job's performance. We prove that starvation is not possible in our model. Simulation results show that our scheduler improves both system and user performances in comparison with two different variable partitioning policies. It is also shown to be effective in guaranteeing fairness and providing control over the performance of jobs.
Efficient Parallel Kernel Solvers for Computational Fluid Dynamics Applications
Sun, Xian-He
1997-01-01
Distributed-memory parallel computers dominate today's parallel computing arena. These machines, such as Intel Paragon, IBM SP2, and Cray Origin2OO, have successfully delivered high performance computing power for solving some of the so-called "grand-challenge" problems. Despite initial success, parallel machines have not been widely accepted in production engineering environments due to the complexity of parallel programming. On a parallel computing system, a task has to be partitioned and distributed appropriately among processors to reduce communication cost and to attain load balance. More importantly, even with careful partitioning and mapping, the performance of an algorithm may still be unsatisfactory, since conventional sequential algorithms may be serial in nature and may not be implemented efficiently on parallel machines. In many cases, new algorithms have to be introduced to increase parallel performance. In order to achieve optimal performance, in addition to partitioning and mapping, a careful performance study should be conducted for a given application to find a good algorithm-machine combination. This process, however, is usually painful and elusive. The goal of this project is to design and develop efficient parallel algorithms for highly accurate Computational Fluid Dynamics (CFD) simulations and other engineering applications. The work plan is 1) developing highly accurate parallel numerical algorithms, 2) conduct preliminary testing to verify the effectiveness and potential of these algorithms, 3) incorporate newly developed algorithms into actual simulation packages. The work plan has well achieved. Two highly accurate, efficient Poisson solvers have been developed and tested based on two different approaches: (1) Adopting a mathematical geometry which has a better capacity to describe the fluid, (2) Using compact scheme to gain high order accuracy in numerical discretization. The previously developed Parallel Diagonal Dominant (PDD) algorithm
History Matching in Parallel Computational Environments
Energy Technology Data Exchange (ETDEWEB)
Steven Bryant; Sanjay Srinivasan; Alvaro Barrera; Sharad Yadav
2005-10-01
A novel methodology for delineating multiple reservoir domains for the purpose of history matching in a distributed computing environment has been proposed. A fully probabilistic approach to perturb permeability within the delineated zones is implemented. The combination of robust schemes for identifying reservoir zones and distributed computing significantly increase the accuracy and efficiency of the probabilistic approach. The information pertaining to the permeability variations in the reservoir that is contained in dynamic data is calibrated in terms of a deformation parameter rD. This information is merged with the prior geologic information in order to generate permeability models consistent with the observed dynamic data as well as the prior geology. The relationship between dynamic response data and reservoir attributes may vary in different regions of the reservoir due to spatial variations in reservoir attributes, well configuration, flow constrains etc. The probabilistic approach then has to account for multiple r{sub D} values in different regions of the reservoir. In order to delineate reservoir domains that can be characterized with different rD parameters, principal component analysis (PCA) of the Hessian matrix has been done. The Hessian matrix summarizes the sensitivity of the objective function at a given step of the history matching to model parameters. It also measures the interaction of the parameters in affecting the objective function. The basic premise of PC analysis is to isolate the most sensitive and least correlated regions. The eigenvectors obtained during the PCA are suitably scaled and appropriate grid block volume cut-offs are defined such that the resultant domains are neither too large (which increases interactions between domains) nor too small (implying ineffective history matching). The delineation of domains requires calculation of Hessian, which could be computationally costly and as well as restricts the current approach to
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
Models of parallel computation :a survey and classification
Institute of Scientific and Technical Information of China (English)
ZHANG Yunquan; CHEN Guoliang; SUN Guangzhong; MIAO Qiankun
2007-01-01
In this paper,the state-of-the-art parallel computational model research is reviewed.We will introduce various models that were developed during the past decades.According to their targeting architecture features,especially memory organization,we classify these parallel computational models into three generations.These models and their characteristics are discussed based on three generations classification.We believe that with the ever increasing speed gap between the CPU and memory systems,incorporating non-uniform memory hierarchy into computational models will become unavoidable.With the emergence of multi-core CPUs,the parallelism hierarchy of current computing platforms becomes more and more complicated.Describing this complicated parallelism hierarchy in future computational models becomes more and more important.A semi-automatic toolkit that can extract model parameters and their values on real computers can reduce the model analysis complexity,thus allowing more complicated models with more parameters to be adopted.Hierarchical memory and hierarchical parallelism will be two very important features that should be considered in future model design and research.
Identifying failure in a tree network of a parallel computer
Archer, Charles J.; Pinnow, Kurt W.; Wallenfelt, Brian P.
2010-08-24
Methods, parallel computers, and products are provided for identifying failure in a tree network of a parallel computer. The parallel computer includes one or more processing sets including an I/O node and a plurality of compute nodes. For each processing set embodiments include selecting a set of test compute nodes, the test compute nodes being a subset of the compute nodes of the processing set; measuring the performance of the I/O node of the processing set; measuring the performance of the selected set of test compute nodes; calculating a current test value in dependence upon the measured performance of the I/O node of the processing set, the measured performance of the set of test compute nodes, and a predetermined value for I/O node performance; and comparing the current test value with a predetermined tree performance threshold. If the current test value is below the predetermined tree performance threshold, embodiments include selecting another set of test compute nodes. If the current test value is not below the predetermined tree performance threshold, embodiments include selecting from the test compute nodes one or more potential problem nodes and testing individually potential problem nodes and links to potential problem nodes.
Fast Parallel Computation of Polynomials Using Few Processors
DEFF Research Database (Denmark)
Valiant, Leslie G.; Skyum, Sven; Berkowitz, S.
1983-01-01
It is shown that any multivariate polynomial of degree $d$ that can be computed sequentially in $C$ steps can be computed in parallel in $O((\\log d)(\\log C + \\log d))$ steps using only $(Cd)^{O(1)} $ processors....
Tutorial: Parallel Computing of Simulation Models for Risk Analysis.
Reilly, Allison C; Staid, Andrea; Gao, Michael; Guikema, Seth D
2016-10-01
Simulation models are widely used in risk analysis to study the effects of uncertainties on outcomes of interest in complex problems. Often, these models are computationally complex and time consuming to run. This latter point may be at odds with time-sensitive evaluations or may limit the number of parameters that are considered. In this article, we give an introductory tutorial focused on parallelizing simulation code to better leverage modern computing hardware, enabling risk analysts to better utilize simulation-based methods for quantifying uncertainty in practice. This article is aimed primarily at risk analysts who use simulation methods but do not yet utilize parallelization to decrease the computational burden of these models. The discussion is focused on conceptual aspects of embarrassingly parallel computer code and software considerations. Two complementary examples are shown using the languages MATLAB and R. A brief discussion of hardware considerations is located in the Appendix. © 2016 Society for Risk Analysis.
Dynamic grid refinement for partial differential equations on parallel computers
International Nuclear Information System (INIS)
Mccormick, S.; Quinlan, D.
1989-01-01
The fast adaptive composite grid method (FAC) is an algorithm that uses various levels of uniform grids to provide adaptive resolution and fast solution of PDEs. An asynchronous version of FAC, called AFAC, that completely eliminates the bottleneck to parallelism is presented. This paper describes the advantage that this algorithm has in adaptive refinement for moving singularities on multiprocessor computers. This work is applicable to the parallel solution of two- and three-dimensional shock tracking problems. 6 refs
RAMA: A file system for massively parallel computers
Miller, Ethan L.; Katz, Randy H.
1993-01-01
This paper describes a file system design for massively parallel computers which makes very efficient use of a few disks per processor. This overcomes the traditional I/O bottleneck of massively parallel machines by storing the data on disks within the high-speed interconnection network. In addition, the file system, called RAMA, requires little inter-node synchronization, removing another common bottleneck in parallel processor file systems. Support for a large tertiary storage system can easily be integrated in lo the file system; in fact, RAMA runs most efficiently when tertiary storage is used.
Parallel grid generation algorithm for distributed memory computers
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.
CUBESIM, Hypercube and Denelcor Hep Parallel Computer Simulation
International Nuclear Information System (INIS)
Dunigan, T.H.
1988-01-01
1 - Description of program or function: CUBESIM is a set of subroutine libraries and programs for the simulation of message-passing parallel computers and shared-memory parallel computers. Subroutines are supplied to simulate the Intel hypercube and the Denelcor HEP parallel computers. The system permits a user to develop and test parallel programs written in C or FORTRAN on a single processor. The user may alter such hypercube parameters as message startup times, packet size, and the computation-to-communication ratio. The simulation generates a trace file that can be used for debugging, performance analysis, or graphical display. 2 - Method of solution: The CUBESIM simulator is linked with the user's parallel application routines to run as a single UNIX process. The simulator library provides a small operating system to perform process and message management. 3 - Restrictions on the complexity of the problem: Up to 128 processors can be simulated with a virtual memory limit of 6 million bytes. Up to 1000 processes can be simulated
Effective SIMD Vectorization for Intel Xeon Phi Coprocessors
Tian, Xinmin; Saito, Hideki; Preis, Serguei V.; Garcia, Eric N.; Kozhukhov, Sergey S.; Masten, Matt; Cherkasov, Aleksei G.; Panchenko, Nikolay
2015-01-01
Efficiently exploiting SIMD vector units is one of the most important aspects in achieving high performance of the application code running on Intel Xeon Phi coprocessors. In this paper, we present several effective SIMD vectorization techniques such as less-than-full-vector loop vectorization, Intel MIC specific alignment optimization, and small matrix transpose/multiplication 2D vectorization implemented in the Intel C/C++ and Fortran production compilers for Intel Xeon Phi coprocessors. A ...
Architecture Without Explicit Locks for Logic Simulation on SIMD Machines
Cockshott, W. Paul; Chimeh, Mozhgan Kabiri
2016-01-01
The presentation describes an architecture for logic simulation that takes advantages of the features of multi-core SIMD architectures. It uses neither explicit locks nor queues, using instead oblivious simulation. Data structures are targeted to efficient SIMD and multi-core cache operation. We demonstrate high levels of parallelisation on Xeon Phi and AMD multi-core machines. Performance on a Xeon Phi is comparable to or better than on a 1000 core Blue Gene machine.
Archer, Charles J.; Blocksome, Michael A.; Ratterman, Joseph D.; Smith, Brian E.
2016-03-15
Processing data communications events in a parallel active messaging interface (`PAMI`) of a parallel computer that includes compute nodes that execute a parallel application, with the PAMI including data communications endpoints, and the endpoints are coupled for data communications through the PAMI and through other data communications resources, including determining by an advance function that there are no actionable data communications events pending for its context, placing by the advance function its thread of execution into a wait state, waiting for a subsequent data communications event for the context; responsive to occurrence of a subsequent data communications event for the context, awakening by the thread from the wait state; and processing by the advance function the subsequent data communications event now pending for the context.
IPython: components for interactive and parallel computing across disciplines. (Invited)
Perez, F.; Bussonnier, M.; Frederic, J. D.; Froehle, B. M.; Granger, B. E.; Ivanov, P.; Kluyver, T.; Patterson, E.; Ragan-Kelley, B.; Sailer, Z.
2013-12-01
Scientific computing is an inherently exploratory activity that requires constantly cycling between code, data and results, each time adjusting the computations as new insights and questions arise. To support such a workflow, good interactive environments are critical. The IPython project (http://ipython.org) provides a rich architecture for interactive computing with: 1. Terminal-based and graphical interactive consoles. 2. A web-based Notebook system with support for code, text, mathematical expressions, inline plots and other rich media. 3. Easy to use, high performance tools for parallel computing. Despite its roots in Python, the IPython architecture is designed in a language-agnostic way to facilitate interactive computing in any language. This allows users to mix Python with Julia, R, Octave, Ruby, Perl, Bash and more, as well as to develop native clients in other languages that reuse the IPython clients. In this talk, I will show how IPython supports all stages in the lifecycle of a scientific idea: 1. Individual exploration. 2. Collaborative development. 3. Production runs with parallel resources. 4. Publication. 5. Education. In particular, the IPython Notebook provides an environment for "literate computing" with a tight integration of narrative and computation (including parallel computing). These Notebooks are stored in a JSON-based document format that provides an "executable paper": notebooks can be version controlled, exported to HTML or PDF for publication, and used for teaching.
Small file aggregation in a parallel computing system
Faibish, Sorin; Bent, John M.; Tzelnic, Percy; Grider, Gary; Zhang, Jingwang
2014-09-02
Techniques are provided for small file aggregation in a parallel computing system. An exemplary method for storing a plurality of files generated by a plurality of processes in a parallel computing system comprises aggregating the plurality of files into a single aggregated file; and generating metadata for the single aggregated file. The metadata comprises an offset and a length of each of the plurality of files in the single aggregated file. The metadata can be used to unpack one or more of the files from the single aggregated file.
Computational acceleration for MR image reconstruction in partially parallel imaging.
Ye, Xiaojing; Chen, Yunmei; Huang, Feng
2011-05-01
In this paper, we present a fast numerical algorithm for solving total variation and l(1) (TVL1) based image reconstruction with application in partially parallel magnetic resonance imaging. Our algorithm uses variable splitting method to reduce computational cost. Moreover, the Barzilai-Borwein step size selection method is adopted in our algorithm for much faster convergence. Experimental results on clinical partially parallel imaging data demonstrate that the proposed algorithm requires much fewer iterations and/or less computational cost than recently developed operator splitting and Bregman operator splitting methods, which can deal with a general sensing matrix in reconstruction framework, to get similar or even better quality of reconstructed images.
Automatic SIMD parallelization of embedded applications based on pattern recognition
Manniesing, R.; Karkowski, I.P.; Corporaal, H.
2000-01-01
This paper investigates the potential for automatic mapping of typical embedded applications to architectures with multimedia instruction set extensions. For this purpose a (pattern matching based) code transformation engine is used, which involves a three-step process of matching, condition
Algorithms for computational fluid dynamics n parallel processors
International Nuclear Information System (INIS)
Van de Velde, E.F.
1986-01-01
A study of parallel algorithms for the numerical solution of partial differential equations arising in computational fluid dynamics is presented. The actual implementation on parallel processors of shared and nonshared memory design is discussed. The performance of these algorithms is analyzed in terms of machine efficiency, communication time, bottlenecks and software development costs. For elliptic equations, a parallel preconditioned conjugate gradient method is described, which has been used to solve pressure equations discretized with high order finite elements on irregular grids. A parallel full multigrid method and a parallel fast Poisson solver are also presented. Hyperbolic conservation laws were discretized with parallel versions of finite difference methods like the Lax-Wendroff scheme and with the Random Choice method. Techniques are developed for comparing the behavior of an algorithm on different architectures as a function of problem size and local computational effort. Effective use of these advanced architecture machines requires the use of machine dependent programming. It is shown that the portability problems can be minimized by introducing high level operations on vectors and matrices structured into program libraries
Hybrid parallel computing architecture for multiview phase shifting
Zhong, Kai; Li, Zhongwei; Zhou, Xiaohui; Shi, Yusheng; Wang, Congjun
2014-11-01
The multiview phase-shifting method shows its powerful capability in achieving high resolution three-dimensional (3-D) shape measurement. Unfortunately, this ability results in very high computation costs and 3-D computations have to be processed offline. To realize real-time 3-D shape measurement, a hybrid parallel computing architecture is proposed for multiview phase shifting. In this architecture, the central processing unit can co-operate with the graphic processing unit (GPU) to achieve hybrid parallel computing. The high computation cost procedures, including lens distortion rectification, phase computation, correspondence, and 3-D reconstruction, are implemented in GPU, and a three-layer kernel function model is designed to simultaneously realize coarse-grained and fine-grained paralleling computing. Experimental results verify that the developed system can perform 50 fps (frame per second) real-time 3-D measurement with 260 K 3-D points per frame. A speedup of up to 180 times is obtained for the performance of the proposed technique using a NVIDIA GT560Ti graphics card rather than a sequential C in a 3.4 GHZ Inter Core i7 3770.
Parallel computing for homogeneous diffusion and transport equations in neutronics
International Nuclear Information System (INIS)
Pinchedez, K.
1999-06-01
Parallel computing meets the ever-increasing requirements for neutronic computer code speed and accuracy. In this work, two different approaches have been considered. We first parallelized the sequential algorithm used by the neutronics code CRONOS developed at the French Atomic Energy Commission. The algorithm computes the dominant eigenvalue associated with PN simplified transport equations by a mixed finite element method. Several parallel algorithms have been developed on distributed memory machines. The performances of the parallel algorithms have been studied experimentally by implementation on a T3D Cray and theoretically by complexity models. A comparison of various parallel algorithms has confirmed the chosen implementations. We next applied a domain sub-division technique to the two-group diffusion Eigen problem. In the modal synthesis-based method, the global spectrum is determined from the partial spectra associated with sub-domains. Then the Eigen problem is expanded on a family composed, on the one hand, from eigenfunctions associated with the sub-domains and, on the other hand, from functions corresponding to the contribution from the interface between the sub-domains. For a 2-D homogeneous core, this modal method has been validated and its accuracy has been measured. (author)
Parallelism in computations in quantum and statistical mechanics
International Nuclear Information System (INIS)
Clementi, E.; Corongiu, G.; Detrich, J.H.
1985-01-01
Often very fundamental biochemical and biophysical problems defy simulations because of limitations in today's computers. We present and discuss a distributed system composed of two IBM 4341 s and/or an IBM 4381 as front-end processors and ten FPS-164 attached array processors. This parallel system - called LCAP - has presently a peak performance of about 110 Mflops; extensions to higher performance are discussed. Presently, the system applications use a modified version of VM/SP as the operating system: description of the modifications is given. Three applications programs have been migrated from sequential to parallel: a molecular quantum mechanical, a Metropolis-Monte Carlo and a molecular dynamics program. Descriptions of the parallel codes are briefly outlined. Use of these parallel codes has already opened up new capabilities for our research. The very positive performance comparisons with today's supercomputers allow us to conclude that parallel computers and programming, of the type we have considered, represent a pragmatic answer to many computationally intensive problems. (orig.)
A Novel Parallel Algorithm for Edit Distance Computation
Directory of Open Access Journals (Sweden)
Muhammad Murtaza Yousaf
2018-01-01
Full Text Available The edit distance between two sequences is the minimum number of weighted transformation-operations that are required to transform one string into the other. The weighted transformation-operations are insert, remove, and substitute. Dynamic programming solution to find edit distance exists but it becomes computationally intensive when the lengths of strings become very large. This work presents a novel parallel algorithm to solve edit distance problem of string matching. The algorithm is based on resolving dependencies in the dynamic programming solution of the problem and it is able to compute each row of edit distance table in parallel. In this way, it becomes possible to compute the complete table in min(m,n iterations for strings of size m and n whereas state-of-the-art parallel algorithm solves the problem in max(m,n iterations. The proposed algorithm also increases the amount of parallelism in each of its iteration. The algorithm is also capable of exploiting spatial locality while its implementation. Additionally, the algorithm works in a load balanced way that further improves its performance. The algorithm is implemented for multicore systems having shared memory. Implementation of the algorithm in OpenMP shows linear speedup and better execution time as compared to state-of-the-art parallel approach. Efficiency of the algorithm is also proven better in comparison to its competitor.
Analysis of multigrid methods on massively parallel computers: Architectural implications
Matheson, Lesley R.; Tarjan, Robert E.
1993-01-01
We study the potential performance of multigrid algorithms running on massively parallel computers with the intent of discovering whether presently envisioned machines will provide an efficient platform for such algorithms. We consider the domain parallel version of the standard V cycle algorithm on model problems, discretized using finite difference techniques in two and three dimensions on block structured grids of size 10(exp 6) and 10(exp 9), respectively. Our models of parallel computation were developed to reflect the computing characteristics of the current generation of massively parallel multicomputers. These models are based on an interconnection network of 256 to 16,384 message passing, 'workstation size' processors executing in an SPMD mode. The first model accomplishes interprocessor communications through a multistage permutation network. The communication cost is a logarithmic function which is similar to the costs in a variety of different topologies. The second model allows single stage communication costs only. Both models were designed with information provided by machine developers and utilize implementation derived parameters. With the medium grain parallelism of the current generation and the high fixed cost of an interprocessor communication, our analysis suggests an efficient implementation requires the machine to support the efficient transmission of long messages, (up to 1000 words) or the high initiation cost of a communication must be significantly reduced through an alternative optimization technique. Furthermore, with variable length message capability, our analysis suggests the low diameter multistage networks provide little or no advantage over a simple single stage communications network.
General-purpose parallel simulator for quantum computing
International Nuclear Information System (INIS)
Niwa, Jumpei; Matsumoto, Keiji; Imai, Hiroshi
2002-01-01
With current technologies, it seems to be very difficult to implement quantum computers with many qubits. It is therefore of importance to simulate quantum algorithms and circuits on the existing computers. However, for a large-size problem, the simulation often requires more computational power than is available from sequential processing. Therefore, simulation methods for parallel processors are required. We have developed a general-purpose simulator for quantum algorithms/circuits on the parallel computer (Sun Enterprise4500). It can simulate algorithms/circuits with up to 30 qubits. In order to test efficiency of our proposed methods, we have simulated Shor's factorization algorithm and Grover's database search, and we have analyzed robustness of the corresponding quantum circuits in the presence of both decoherence and operational errors. The corresponding results, statistics, and analyses are presented in this paper
Parallel algorithms for computation of the manipulator inertia matrix
Amin-Javaheri, Masoud; Orin, David E.
1989-01-01
The development of an O(log2N) parallel algorithm for the manipulator inertia matrix is presented. It is based on the most efficient serial algorithm which uses the composite rigid body method. Recursive doubling is used to reformulate the linear recurrence equations which are required to compute the diagonal elements of the matrix. It results in O(log2N) levels of computation. Computation of the off-diagonal elements involves N linear recurrences of varying-size and a new method, which avoids redundant computation of position and orientation transforms for the manipulator, is developed. The O(log2N) algorithm is presented in both equation and graphic forms which clearly show the parallelism inherent in the algorithm.
Fencing data transfers in a parallel active messaging interface of a parallel computer
Blocksome, Michael A.; Mamidala, Amith R.
2015-06-02
Fencing data transfers in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI including data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task; the compute nodes coupled for data communications through the PAMI and through data communications resources including at least one segment of shared random access memory; including initiating execution through the PAMI of an ordered sequence of active SEND instructions for SEND data transfers between two endpoints, effecting deterministic SEND data transfers through a segment of shared memory; and executing through the PAMI, with no FENCE accounting for SEND data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all SEND instructions initiated prior to execution of the FENCE instruction for SEND data transfers between the two endpoints.
Element-topology-independent preconditioners for parallel finite element computations
Park, K. C.; Alexander, Scott
1992-01-01
A family of preconditioners for the solution of finite element equations are presented, which are element-topology independent and thus can be applicable to element order-free parallel computations. A key feature of the present preconditioners is the repeated use of element connectivity matrices and their left and right inverses. The properties and performance of the present preconditioners are demonstrated via beam and two-dimensional finite element matrices for implicit time integration computations.
Image processing with massively parallel computer Quadrics Q1
International Nuclear Information System (INIS)
Della Rocca, A.B.; La Porta, L.; Ferriani, S.
1995-05-01
Aimed to evaluate the image processing capabilities of the massively parallel computer Quadrics Q1, a convolution algorithm that has been implemented is described in this report. At first the discrete convolution mathematical definition is recalled together with the main Q1 h/w and s/w features. Then the different codification forms of the algorythm are described and the Q1 performances are compared with those obtained by different computers. Finally, the conclusions report on main results and suggestions
WEKA-G: Parallel data mining on computational grids
Directory of Open Access Journals (Sweden)
PIMENTA, A.
2009-12-01
Full Text Available Data mining is a technology that can extract useful information from large amounts of data. However, mining a database often requires a high computational power. To resolve this problem, this paper presents a tool (Weka-G, which runs in parallel algorithms used in the mining process data. As the environment for doing so, we use a computational grid by adding several features within a WAN.
Hardware packet pacing using a DMA in a parallel computer
Chen, Dong; Heidelberger, Phillip; Vranas, Pavlos
2013-08-13
Method and system for hardware packet pacing using a direct memory access controller in a parallel computer which, in one aspect, keeps track of a total number of bytes put on the network as a result of a remote get operation, using a hardware token counter.
On the efficient parallel computation of Legendre transforms
Inda, M.A.; Bisseling, R.H.; Maslen, D.K.
2001-01-01
In this article, we discuss a parallel implementation of efficient algorithms for computation of Legendre polynomial transforms and other orthogonal polynomial transforms. We develop an approach to the Driscoll-Healy algorithm using polynomial arithmetic and present experimental results on the
On the efficient parallel computation of Legendre transforms
Inda, M.A.; Bisseling, R.H.; Maslen, D.K.
1999-01-01
In this article we discuss a parallel implementation of efficient algorithms for computation of Legendre polynomial transforms and other orthogonal polynomial transforms. We develop an approach to the Driscoll-Healy algorithm using polynomial arithmetic and present experimental results on the
Emerging Nanophotonic Applications Explored with Advanced Scientific Parallel Computing
Meng, Xiang
The domain of nanoscale optical science and technology is a combination of the classical world of electromagnetics and the quantum mechanical regime of atoms and molecules. Recent advancements in fabrication technology allows the optical structures to be scaled down to nanoscale size or even to the atomic level, which are far smaller than the wavelength they are designed for. These nanostructures can have unique, controllable, and tunable optical properties and their interactions with quantum materials can have important near-field and far-field optical response. Undoubtedly, these optical properties can have many important applications, ranging from the efficient and tunable light sources, detectors, filters, modulators, high-speed all-optical switches; to the next-generation classical and quantum computation, and biophotonic medical sensors. This emerging research of nanoscience, known as nanophotonics, is a highly interdisciplinary field requiring expertise in materials science, physics, electrical engineering, and scientific computing, modeling and simulation. It has also become an important research field for investigating the science and engineering of light-matter interactions that take place on wavelength and subwavelength scales where the nature of the nanostructured matter controls the interactions. In addition, the fast advancements in the computing capabilities, such as parallel computing, also become as a critical element for investigating advanced nanophotonic devices. This role has taken on even greater urgency with the scale-down of device dimensions, and the design for these devices require extensive memory and extremely long core hours. Thus distributed computing platforms associated with parallel computing are required for faster designs processes. Scientific parallel computing constructs mathematical models and quantitative analysis techniques, and uses the computing machines to analyze and solve otherwise intractable scientific challenges. In
Computationally efficient implementation of combustion chemistry in parallel PDF calculations
International Nuclear Information System (INIS)
Lu Liuyan; Lantz, Steven R.; Ren Zhuyin; Pope, Stephen B.
2009-01-01
In parallel calculations of combustion processes with realistic chemistry, the serial in situ adaptive tabulation (ISAT) algorithm [S.B. Pope, Computationally efficient implementation of combustion chemistry using in situ adaptive tabulation, Combustion Theory and Modelling, 1 (1997) 41-63; L. Lu, S.B. Pope, An improved algorithm for in situ adaptive tabulation, Journal of Computational Physics 228 (2009) 361-386] substantially speeds up the chemistry calculations on each processor. To improve the parallel efficiency of large ensembles of such calculations in parallel computations, in this work, the ISAT algorithm is extended to the multi-processor environment, with the aim of minimizing the wall clock time required for the whole ensemble. Parallel ISAT strategies are developed by combining the existing serial ISAT algorithm with different distribution strategies, namely purely local processing (PLP), uniformly random distribution (URAN), and preferential distribution (PREF). The distribution strategies enable the queued load redistribution of chemistry calculations among processors using message passing. They are implemented in the software x2f m pi, which is a Fortran 95 library for facilitating many parallel evaluations of a general vector function. The relative performance of the parallel ISAT strategies is investigated in different computational regimes via the PDF calculations of multiple partially stirred reactors burning methane/air mixtures. The results show that the performance of ISAT with a fixed distribution strategy strongly depends on certain computational regimes, based on how much memory is available and how much overlap exists between tabulated information on different processors. No one fixed strategy consistently achieves good performance in all the regimes. Therefore, an adaptive distribution strategy, which blends PLP, URAN and PREF, is devised and implemented. It yields consistently good performance in all regimes. In the adaptive parallel
A Parallel Prefix Algorithm for Almost Toeplitz Tridiagonal Systems
Sun, Xian-He; Joslin, Ronald D.
1995-01-01
A compact scheme is a discretization scheme that is advantageous in obtaining highly accurate solutions. However, the resulting systems from compact schemes are tridiagonal systems that are difficult to solve efficiently on parallel computers. Considering the almost symmetric Toeplitz structure, a parallel algorithm, simple parallel prefix (SPP), is proposed. The SPP algorithm requires less memory than the conventional LU decomposition and is efficient on parallel machines. It consists of a prefix communication pattern and AXPY operations. Both the computation and the communication can be truncated without degrading the accuracy when the system is diagonally dominant. A formal accuracy study has been conducted to provide a simple truncation formula. Experimental results have been measured on a MasPar MP-1 SIMD machine and on a Cray 2 vector machine. Experimental results show that the simple parallel prefix algorithm is a good algorithm for symmetric, almost symmetric Toeplitz tridiagonal systems and for the compact scheme on high-performance computers.
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.)
Parallel peak pruning for scalable SMP contour tree computation
Energy Technology Data Exchange (ETDEWEB)
Carr, Hamish A. [Univ. of Leeds (United Kingdom); Weber, Gunther H. [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Univ. of California, Davis, CA (United States); Sewell, Christopher M. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Ahrens, James P. [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2017-03-09
As data sets grow to exascale, automated data analysis and visualisation are increasingly important, to intermediate human understanding and to reduce demands on disk storage via in situ analysis. Trends in architecture of high performance computing systems necessitate analysis algorithms to make effective use of combinations of massively multicore and distributed systems. One of the principal analytic tools is the contour tree, which analyses relationships between contours to identify features of more than local importance. Unfortunately, the predominant algorithms for computing the contour tree are explicitly serial, and founded on serial metaphors, which has limited the scalability of this form of analysis. While there is some work on distributed contour tree computation, and separately on hybrid GPU-CPU computation, there is no efficient algorithm with strong formal guarantees on performance allied with fast practical performance. Here in this paper, we report the first shared SMP algorithm for fully parallel contour tree computation, withfor-mal guarantees of O(lgnlgt) parallel steps and O(n lgn) work, and implementations with up to 10x parallel speed up in OpenMP and up to 50x speed up in NVIDIA Thrust.
A hybrid method for the parallel computation of Green's functions
DEFF Research Database (Denmark)
Petersen, Dan Erik; Li, Song; Stokbro, Kurt
2009-01-01
of the large number of times this calculation needs to be performed, this is computationally very expensive even on supercomputers. The classical approach is based on recurrence formulas which cannot be efficiently parallelized. This practically prevents the solution of large problems with hundreds...... of thousands of atoms. We propose new recurrences for a general class of sparse matrices to calculate Green's and lesser Green's function matrices which extend formulas derived by Takahashi and others. We show that these recurrences may lead to a dramatically reduced computational cost because they only...... require computing a small number of entries of the inverse matrix. Then. we propose a parallelization strategy for block tridiagonal matrices which involves a combination of Schur complement calculations and cyclic reduction. It achieves good scalability even on problems of modest size....
Parallel computing in genomic research: advances and applications.
Ocaña, Kary; de Oliveira, Daniel
2015-01-01
Today's genomic experiments have to process the so-called "biological big data" that is now reaching the size of Terabytes and Petabytes. To process this huge amount of data, scientists may require weeks or months if they use their own workstations. Parallelism techniques and high-performance computing (HPC) environments can be applied for reducing the total processing time and to ease the management, treatment, and analyses of this data. However, running bioinformatics experiments in HPC environments such as clouds, grids, clusters, and graphics processing unit requires the expertise from scientists to integrate computational, biological, and mathematical techniques and technologies. Several solutions have already been proposed to allow scientists for processing their genomic experiments using HPC capabilities and parallelism techniques. This article brings a systematic review of literature that surveys the most recently published research involving genomics and parallel computing. Our objective is to gather the main characteristics, benefits, and challenges that can be considered by scientists when running their genomic experiments to benefit from parallelism techniques and HPC capabilities.
Aggregating job exit statuses of a plurality of compute nodes executing a parallel application
Aho, Michael E.; Attinella, John E.; Gooding, Thomas M.; Mundy, Michael B.
2015-07-21
Aggregating job exit statuses of a plurality of compute nodes executing a parallel application, including: identifying a subset of compute nodes in the parallel computer to execute the parallel application; selecting one compute node in the subset of compute nodes in the parallel computer as a job leader compute node; initiating execution of the parallel application on the subset of compute nodes; receiving an exit status from each compute node in the subset of compute nodes, where the exit status for each compute node includes information describing execution of some portion of the parallel application by the compute node; aggregating each exit status from each compute node in the subset of compute nodes; and sending an aggregated exit status for the subset of compute nodes in the parallel computer.
Computing NLTE Opacities -- Node Level Parallel
Energy Technology Data Exchange (ETDEWEB)
Holladay, Daniel [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
2015-09-11
Presentation. The goal: to produce a robust library capable of computing reasonably accurate opacities inline with the assumption of LTE relaxed (non-LTE). Near term: demonstrate acceleration of non-LTE opacity computation. Far term (if funded): connect to application codes with in-line capability and compute opacities. Study science problems. Use efficient algorithms that expose many levels of parallelism and utilize good memory access patterns for use on advanced architectures. Portability to multiple types of hardware including multicore processors, manycore processors such as KNL, GPUs, etc. Easily coupled to radiation hydrodynamics and thermal radiative transfer codes.
High spatial resolution CT image reconstruction using parallel computing
International Nuclear Information System (INIS)
Yin Yin; Liu Li; Sun Gongxing
2003-01-01
Using the PC cluster system with 16 dual CPU nodes, we accelerate the FBP and OR-OSEM reconstruction of high spatial resolution image (2048 x 2048). Based on the number of projections, we rewrite the reconstruction algorithms into parallel format and dispatch the tasks to each CPU. By parallel computing, the speedup factor is roughly equal to the number of CPUs, which can be up to about 25 times when 25 CPUs used. This technique is very suitable for real-time high spatial resolution CT image reconstruction. (authors)
Construction of a digital elevation model: methods and parallelization
International Nuclear Information System (INIS)
Mazzoni, Christophe
1995-01-01
The aim of this work is to reduce the computation time needed to produce the Digital Elevation Models (DEM) by using a parallel machine. It is made in collaboration between the French 'Institut Geographique National' (IGN) and the Laboratoire d'Electronique de Technologie et d'Instrumentation (LETI) of the French Atomic Energy Commission (CEA). The IGN has developed a system which provides DEM that is used to produce topographic maps. The kernel of this system is the correlator, a software which automatically matches pairs of homologous points of a stereo-pair of photographs. Nevertheless the correlator is expensive In computing time. In order to reduce computation time and to produce the DEM with same accuracy that the actual system, we have parallelized the IGN's correlator on the OPENVISION system. This hardware solution uses a SIMD (Single Instruction Multiple Data) parallel machine SYMPATI-2, developed by the LETI that is involved in parallel architecture and image processing. Our analysis of the implementation has demonstrated the difficulty of efficient coupling between scalar and parallel structure. So we propose solutions to reinforce this coupling. In order to accelerate more the processing we evaluate SYMPHONIE, a SIMD calculator, successor of SYMPATI-2. On an other hand, we developed a multi-agent approach for what a MIMD (Multiple Instruction, Multiple Data) architecture is available. At last, we describe a Multi-SIMD architecture that conciliates our two approaches. This architecture offers a capacity to apprehend efficiently multi-level treatment image. It is flexible by its modularity, and its communication network supplies reliability that interest sensible systems. (author) [fr
A discrete ordinate response matrix method for massively parallel computers
International Nuclear Information System (INIS)
Hanebutte, U.R.; Lewis, E.E.
1991-01-01
A discrete ordinate response matrix method is formulated for the solution of neutron transport problems on massively parallel computers. The response matrix formulation eliminates iteration on the scattering source. The nodal matrices which result from the diamond-differenced equations are utilized in a factored form which minimizes memory requirements and significantly reduces the required number of algorithm utilizes massive parallelism by assigning each spatial node to a processor. The algorithm is accelerated effectively by a synthetic method in which the low-order diffusion equations are also solved by massively parallel red/black iterations. The method has been implemented on a 16k Connection Machine-2, and S 8 and S 16 solutions have been obtained for fixed-source benchmark problems in X--Y geometry
Distributed parallel computing in stochastic modeling of groundwater systems.
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.
Implementation of PHENIX trigger algorithms on massively parallel computers
International Nuclear Information System (INIS)
Petridis, A.N.; Wohn, F.K.
1995-01-01
The event selection requirements of contemporary high energy and nuclear physics experiments are met by the introduction of on-line trigger algorithms which identify potentially interesting events and reduce the data acquisition rate to levels that are manageable by the electronics. Such algorithms being parallel in nature can be simulated off-line using massively parallel computers. The PHENIX experiment intends to investigate the possible existence of a new phase of matter called the quark gluon plasma which has been theorized to have existed in very early stages of the evolution of the universe by studying collisions of heavy nuclei at ultra-relativistic energies. Such interactions can also reveal important information regarding the structure of the nucleus and mandate a thorough investigation of the simpler proton-nucleus collisions at the same energies. The complexity of PHENIX events and the need to analyze and also simulate them at rates similar to the data collection ones imposes enormous computation demands. This work is a first effort to implement PHENIX trigger algorithms on parallel computers and to study the feasibility of using such machines to run the complex programs necessary for the simulation of the PHENIX detector response. Fine and coarse grain approaches have been studied and evaluated. Depending on the application the performance of a massively parallel computer can be much better or much worse than that of a serial workstation. A comparison between single instruction and multiple instruction computers is also made and possible applications of the single instruction machines to high energy and nuclear physics experiments are outlined. copyright 1995 American Institute of Physics
Interaction sorting method for molecular dynamics on multi-core SIMD CPU architecture.
Matvienko, Sergey; Alemasov, Nikolay; Fomin, Eduard
2015-02-01
Molecular dynamics (MD) is widely used in computational biology for studying binding mechanisms of molecules, molecular transport, conformational transitions, protein folding, etc. The method is computationally expensive; thus, the demand for the development of novel, much more efficient algorithms is still high. Therefore, the new algorithm designed in 2007 and called interaction sorting (IS) clearly attracted interest, as it outperformed the most efficient MD algorithms. In this work, a new IS modification is proposed which allows the algorithm to utilize SIMD processor instructions. This paper shows that the improvement provides an additional gain in performance, 9% to 45% in comparison to the original IS method.
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
A Parallel Computational Model for Multichannel Phase Unwrapping Problem
Imperatore, Pasquale; Pepe, Antonio; Lanari, Riccardo
2015-05-01
In this paper, a parallel model for the solution of the computationally intensive multichannel phase unwrapping (MCh-PhU) problem is proposed. Firstly, the Extended Minimum Cost Flow (EMCF) algorithm for solving MCh-PhU problem is revised within the rigorous mathematical framework of the discrete calculus ; thus permitting to capture its topological structure in terms of meaningful discrete differential operators. Secondly, emphasis is placed on those methodological and practical aspects, which lead to a parallel reformulation of the EMCF algorithm. Thus, a novel dual-level parallel computational model, in which the parallelism is hierarchically implemented at two different (i.e., process and thread) levels, is presented. The validity of our approach has been demonstrated through a series of experiments that have revealed a significant speedup. Therefore, the attained high-performance prototype is suitable for the solution of large-scale phase unwrapping problems in reasonable time frames, with a significant impact on the systematic exploitation of the existing, and rapidly growing, large archives of SAR data.
Executing a gather operation on a parallel computer
Archer, Charles J [Rochester, MN; Ratterman, Joseph D [Rochester, MN
2012-03-20
Methods, apparatus, and computer program products are disclosed for executing a gather operation on a parallel computer according to embodiments of the present invention. Embodiments include configuring, by the logical root, a result buffer or the logical root, the result buffer having positions, each position corresponding to a ranked node in the operational group and for storing contribution data gathered from that ranked node. Embodiments also include repeatedly for each position in the result buffer: determining, by each compute node of an operational group, whether the current position in the result buffer corresponds with the rank of the compute node, if the current position in the result buffer corresponds with the rank of the compute node, contributing, by that compute node, the compute node's contribution data, if the current position in the result buffer does not correspond with the rank of the compute node, contributing, by that compute node, a value of zero for the contribution data, and storing, by the logical root in the current position in the result buffer, results of a bitwise OR operation of all the contribution data by all compute nodes of the operational group for the current position, the results received through the global combining network.
Fast Evaluation of Segmentation Quality with Parallel Computing
Directory of Open Access Journals (Sweden)
Henry Cruz
2017-01-01
Full Text Available In digital image processing and computer vision, a fairly frequent task is the performance comparison of different algorithms on enormous image databases. This task is usually time-consuming and tedious, such that any kind of tool to simplify this work is welcome. To achieve an efficient and more practical handling of a normally tedious evaluation, we implemented the automatic detection system, with the help of MATLAB®’s Parallel Computing Toolbox™. The key parts of the system have been parallelized to achieve simultaneous execution and analysis of segmentation algorithms on the one hand and the evaluation of detection accuracy for the nonforested regions, such as a study case, on the other hand. As a positive side effect, CPU usage was reduced and processing time was significantly decreased by 68.54% compared to sequential processing (i.e., executing the system with each algorithm one by one.
Final Report: Center for Programming Models for Scalable Parallel Computing
Energy Technology Data Exchange (ETDEWEB)
Mellor-Crummey, John [William Marsh Rice University
2011-09-13
As part of the Center for Programming Models for Scalable Parallel Computing, Rice University collaborated with project partners in the design, development and deployment of language, compiler, and runtime support for parallel programming models to support application development for the “leadership-class” computer systems at DOE national laboratories. Work over the course of this project has focused on the design, implementation, and evaluation of a second-generation version of Coarray Fortran. Research and development efforts of the project have focused on the CAF 2.0 language, compiler, runtime system, and supporting infrastructure. This has involved working with the teams that provide infrastructure for CAF that we rely on, implementing new language and runtime features, producing an open source compiler that enabled us to evaluate our ideas, and evaluating our design and implementation through the use of benchmarks. The report details the research, development, findings, and conclusions from this work.
Performing a local reduction operation on a parallel computer
Blocksome, Michael A.; Faraj, Daniel A.
2012-12-11
A parallel computer including compute nodes, each including two reduction processing cores, a network write processing core, and a network read processing core, each processing core assigned an input buffer. Copying, in interleaved chunks by the reduction processing cores, contents of the reduction processing cores' input buffers to an interleaved buffer in shared memory; copying, by one of the reduction processing cores, contents of the network write processing core's input buffer to shared memory; copying, by another of the reduction processing cores, contents of the network read processing core's input buffer to shared memory; and locally reducing in parallel by the reduction processing cores: the contents of the reduction processing core's input buffer; every other interleaved chunk of the interleaved buffer; the copied contents of the network write processing core's input buffer; and the copied contents of the network read processing core's input buffer.
Establishing a group of endpoints in a parallel computer
Archer, Charles J.; Blocksome, Michael A.; Ratterman, Joseph D.; Smith, Brian E.; Xue, Hanhong
2016-02-02
A parallel computer executes a number of tasks, each task includes a number of endpoints and the endpoints are configured to support collective operations. In such a parallel computer, establishing a group of endpoints receiving a user specification of a set of endpoints included in a global collection of endpoints, where the user specification defines the set in accordance with a predefined virtual representation of the endpoints, the predefined virtual representation is a data structure setting forth an organization of tasks and endpoints included in the global collection of endpoints and the user specification defines the set of endpoints without a user specification of a particular endpoint; and defining a group of endpoints in dependence upon the predefined virtual representation of the endpoints and the user specification.
Mechatronic Model Based Computed Torque Control of a Parallel Manipulator
Directory of Open Access Journals (Sweden)
Zhiyong Yang
2008-11-01
Full Text Available With high speed and accuracy the parallel manipulators have wide application in the industry, but there still exist many difficulties in the actual control process because of the time-varying and coupling. Unfortunately, the present-day commercial controlles cannot provide satisfying performance for its single axis linear control only. Therefore, aimed at a novel 2-DOF (Degree of Freedom parallel manipulator called Diamond 600, a motor-mechanism coupling dynamic model based control scheme employing the computed torque control algorithm are presented in this paper. First, the integrated dynamic coupling model is deduced, according to equivalent torques between the mechanical structure and the PM (Permanent Magnetism servomotor. Second, computed torque controller is described in detail for the above proposed model. At last, a series of numerical simulations and experiments are carried out to test the effectiveness of the system, and the results verify the favourable tracking ability and robustness.
Mechatronic Model Based Computed Torque Control of a Parallel Manipulator
Directory of Open Access Journals (Sweden)
Zhiyong Yang
2008-03-01
Full Text Available With high speed and accuracy the parallel manipulators have wide application in the industry, but there still exist many difficulties in the actual control process because of the time-varying and coupling. Unfortunately, the present-day commercial controlles cannot provide satisfying performance for its single axis linear control only. Therefore, aimed at a novel 2-DOF (Degree of Freedom parallel manipulator called Diamond 600, a motor-mechanism coupling dynamic model based control scheme employing the computed torque control algorithm are presented in this paper. First, the integrated dynamic coupling model is deduced, according to equivalent torques between the mechanical structure and the PM (Permanent Magnetism servomotor. Second, computed torque controller is described in detail for the above proposed model. At last, a series of numerical simulations and experiments are carried out to test the effectiveness of the system, and the results verify the favourable tracking ability and robustness.
A High-Performance Parallel FDTD Method Enhanced by Using SSE Instruction Set
Directory of Open Access Journals (Sweden)
Dau-Chyrh Chang
2012-01-01
Full Text Available We introduce a hardware acceleration technique for the parallel finite difference time domain (FDTD method using the SSE (streaming (single instruction multiple data SIMD extensions instruction set. The implementation of SSE instruction set to parallel FDTD method has achieved the significant improvement on the simulation performance. The benchmarks of the SSE acceleration on both the multi-CPU workstation and computer cluster have demonstrated the advantages of (vector arithmetic logic unit VALU acceleration over GPU acceleration. Several engineering applications are employed to demonstrate the performance of parallel FDTD method enhanced by SSE instruction set.
A scalable PC-based parallel computer for lattice QCD
International Nuclear Information System (INIS)
Fodor, Z.; Katz, S.D.; Pappa, G.
2003-01-01
A PC-based parallel computer for medium/large scale lattice QCD simulations is suggested. The Eoetvoes Univ., Inst. Theor. Phys. cluster consists of 137 Intel P4-1.7GHz nodes. Gigabit Ethernet cards are used for nearest neighbor communication in a two-dimensional mesh. The sustained performance for dynamical staggered (wilson) quarks on large lattices is around 70(110) GFlops. The exceptional price/performance ratio is below $1/Mflop
A scalable PC-based parallel computer for lattice QCD
International Nuclear Information System (INIS)
Fodor, Z.; Papp, G.
2002-09-01
A PC-based parallel computer for medium/large scale lattice QCD simulations is suggested. The Eoetvoes Univ., Inst. Theor. Phys. cluster consists of 137 Intel P4-1.7 GHz nodes. Gigabit Ethernet cards are used for nearest neighbor communication in a two-dimensional mesh. The sustained performance for dynamical staggered(wilson) quarks on large lattices is around 70(110) GFlops. The exceptional price/performance ratio is below $1/Mflop. (orig.)
Domain Decomposition: A Bridge between Nature and Parallel Computers
1992-09-01
B., "Domain Decomposition Algorithms for Indefinite Elliptic Problems," S"IAM Journal of S; cientific and Statistical (’omputing, Vol. 13, 1992, pp...AD-A256 575 NASA Contractor Report 189709 ICASE Report No. 92-44 ICASE DOMAIN DECOMPOSITION: A BRIDGE BETWEEN NATURE AND PARALLEL COMPUTERS DTIC dE...effectively implemented on dis- tributed memory multiprocessors. In 1990 (as reported in Ref. 38 using the tile algo- rithm), a 103,201-unknown 2D elliptic
Noise simulation in cone beam CT imaging with parallel computing
International Nuclear Information System (INIS)
Tu, S.-J.; Shaw, Chris C; Chen, Lingyun
2006-01-01
We developed a computer noise simulation model for cone beam computed tomography imaging using a general purpose PC cluster. This model uses a mono-energetic x-ray approximation and allows us to investigate three primary performance components, specifically quantum noise, detector blurring and additive system noise. A parallel random number generator based on the Weyl sequence was implemented in the noise simulation and a visualization technique was accordingly developed to validate the quality of the parallel random number generator. In our computer simulation model, three-dimensional (3D) phantoms were mathematically modelled and used to create 450 analytical projections, which were then sampled into digital image data. Quantum noise was simulated and added to the analytical projection image data, which were then filtered to incorporate flat panel detector blurring. Additive system noise was generated and added to form the final projection images. The Feldkamp algorithm was implemented and used to reconstruct the 3D images of the phantoms. A 24 dual-Xeon PC cluster was used to compute the projections and reconstructed images in parallel with each CPU processing 10 projection views for a total of 450 views. Based on this computer simulation system, simulated cone beam CT images were generated for various phantoms and technique settings. Noise power spectra for the flat panel x-ray detector and reconstructed images were then computed to characterize the noise properties. As an example among the potential applications of our noise simulation model, we showed that images of low contrast objects can be produced and used for image quality evaluation
Local rollback for fault-tolerance in parallel computing systems
Blumrich, Matthias A [Yorktown Heights, NY; Chen, Dong [Yorktown Heights, NY; Gara, Alan [Yorktown Heights, NY; Giampapa, Mark E [Yorktown Heights, NY; Heidelberger, Philip [Yorktown Heights, NY; Ohmacht, Martin [Yorktown Heights, NY; Steinmacher-Burow, Burkhard [Boeblingen, DE; Sugavanam, Krishnan [Yorktown Heights, NY
2012-01-24
A control logic device performs a local rollback in a parallel super computing system. The super computing system includes at least one cache memory device. The control logic device determines a local rollback interval. The control logic device runs at least one instruction in the local rollback interval. The control logic device evaluates whether an unrecoverable condition occurs while running the at least one instruction during the local rollback interval. The control logic device checks whether an error occurs during the local rollback. The control logic device restarts the local rollback interval if the error occurs and the unrecoverable condition does not occur during the local rollback interval.
An Alternative Algorithm for Computing Watersheds on Shared Memory Parallel Computers
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.
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
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.
Faraj, Daniel A
2013-07-16
Algorithm selection for data communications in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI composed of data communications endpoints, each endpoint including specifications of a client, a context, and a task, endpoints coupled for data communications through the PAMI, including associating in the PAMI data communications algorithms and bit masks; receiving in an origin endpoint of the PAMI a collective instruction, the instruction specifying transmission of a data communications message from the origin endpoint to a target endpoint; constructing a bit mask for the received collective instruction; selecting, from among the associated algorithms and bit masks, a data communications algorithm in dependence upon the constructed bit mask; and executing the collective instruction, transmitting, according to the selected data communications algorithm from the origin endpoint to the target endpoint, the data communications message.
Data communications in a parallel active messaging interface of a parallel computer
Davis, Kristan D; Faraj, Daniel A
2013-07-09
Algorithm selection for data communications in a parallel active messaging interface (`PAMI`) of a parallel computer, the PAMI composed of data communications endpoints, each endpoint including specifications of a client, a context, and a task, endpoints coupled for data communications through the PAMI, including associating in the PAMI data communications algorithms and ranges of message sizes so that each algorithm is associated with a separate range of message sizes; receiving in an origin endpoint of the PAMI a data communications instruction, the instruction specifying transmission of a data communications message from the origin endpoint to a target endpoint, the data communications message characterized by a message size; selecting, from among the associated algorithms and ranges, a data communications algorithm in dependence upon the message size; and transmitting, according to the selected data communications algorithm from the origin endpoint to the target endpoint, the data communications message.
Event parallelism: Distributed memory parallel computing for high energy physics experiments
International Nuclear Information System (INIS)
Nash, T.
1989-01-01
This paper describes the present and expected future development of distributed memory parallel computers for high energy physics experiments. It covers the use of event parallel microprocessor farms, particularly at Fermilab, including both ACP multiprocessors and farms of MicroVAXES. These systems have proven very cost effective in the past. A case is made for moving to the more open environment of UNIX and RISC processors. The 2nd Generation ACP Multiprocessor System, which is based on powerful RISC systems, is described. Given the promise of still more extraordinary increases in processor performance, a new emphasis on point to point, rather than bussed, communication will be required. Developments in this direction are described. (orig.)
Event parallelism: Distributed memory parallel computing for high energy physics experiments
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.
Performing an allreduce operation on a plurality of compute nodes of a parallel computer
Faraj, Ahmad [Rochester, MN
2012-04-17
Methods, apparatus, and products are disclosed for performing an allreduce operation on a plurality of compute nodes of a parallel computer. Each compute node includes at least two processing cores. Each processing core has contribution data for the allreduce operation. Performing an allreduce operation on a plurality of compute nodes of a parallel computer includes: establishing one or more logical rings among the compute nodes, each logical ring including at least one processing core from each compute node; performing, for each logical ring, a global allreduce operation using the contribution data for the processing cores included in that logical ring, yielding a global allreduce result for each processing core included in that logical ring; and performing, for each compute node, a local allreduce operation using the global allreduce results for each processing core on that compute node.
Development of real-time visualization system for Computational Fluid Dynamics on parallel computers
International Nuclear Information System (INIS)
Muramatsu, Kazuhiro; Otani, Takayuki; Matsumoto, Hideki; Takei, Toshifumi; Doi, Shun
1998-03-01
A real-time visualization system for computational fluid dynamics in a network connecting between a parallel computing server and the client terminal was developed. Using the system, a user can visualize the results of a CFD (Computational Fluid Dynamics) simulation on the parallel computer as a client terminal during the actual computation on a server. Using GUI (Graphical User Interface) on the client terminal, to user is also able to change parameters of the analysis and visualization during the real-time of the calculation. The system carries out both of CFD simulation and generation of a pixel image data on the parallel computer, and compresses the data. Therefore, the amount of data from the parallel computer to the client is so small in comparison with no compression that the user can enjoy the swift image appearance comfortably. Parallelization of image data generation is based on Owner Computation Rule. GUI on the client is built on Java applet. A real-time visualization is thus possible on the client PC only if Web browser is implemented on it. (author)
Semi-coarsening multigrid methods for parallel computing
Energy Technology Data Exchange (ETDEWEB)
Jones, J.E.
1996-12-31
Standard multigrid methods are not well suited for problems with anisotropic coefficients which can occur, for example, on grids that are stretched to resolve a boundary layer. There are several different modifications of the standard multigrid algorithm that yield efficient methods for anisotropic problems. In the paper, we investigate the parallel performance of these multigrid algorithms. Multigrid algorithms which work well for anisotropic problems are based on line relaxation and/or semi-coarsening. In semi-coarsening multigrid algorithms a grid is coarsened in only one of the coordinate directions unlike standard or full-coarsening multigrid algorithms where a grid is coarsened in each of the coordinate directions. When both semi-coarsening and line relaxation are used, the resulting multigrid algorithm is robust and automatic in that it requires no knowledge of the nature of the anisotropy. This is the basic multigrid algorithm whose parallel performance we investigate in the paper. The algorithm is currently being implemented on an IBM SP2 and its performance is being analyzed. In addition to looking at the parallel performance of the basic semi-coarsening algorithm, we present algorithmic modifications with potentially better parallel efficiency. One modification reduces the amount of computational work done in relaxation at the expense of using multiple coarse grids. This modification is also being implemented with the aim of comparing its performance to that of the basic semi-coarsening algorithm.
Dynamic stability calculations for power grids employing a parallel computer
Energy Technology Data Exchange (ETDEWEB)
Schmidt, K
1982-06-01
The aim of dynamic contingency calculations in power systems is to estimate the effects of assumed disturbances, such as loss of generation. Due to the large dimensions of the problem these simulations require considerable computing time and costs, to the effect that they are at present only used in a planning state but not for routine checks in power control stations. In view of the homogeneity of the problem, where a multitude of equal generator models, having different parameters, are to be integrated simultaneously, the use of a parallel computer looks very attractive. The results of this study employing a prototype parallel computer (SMS 201) are presented. It consists of up to 128 equal microcomputers bus-connected to a control computer. Each of the modules is programmed to simulate a node of the power grid. Generators with their associated control are represented by models of 13 states each. Passive nodes are complemented by 'phantom'-generators, so that the whole power grid is homogenous, thus removing the need for load-flow-iterations. Programming of microcomputers is essentially performed in FORTRAN.
Fast electrostatic force calculation on parallel computer clusters
International Nuclear Information System (INIS)
Kia, Amirali; Kim, Daejoong; Darve, Eric
2008-01-01
The fast multipole method (FMM) and smooth particle mesh Ewald (SPME) are well known fast algorithms to evaluate long range electrostatic interactions in molecular dynamics and other fields. FMM is a multi-scale method which reduces the computation cost by approximating the potential due to a group of particles at a large distance using few multipole functions. This algorithm scales like O(N) for N particles. SPME algorithm is an O(NlnN) method which is based on an interpolation of the Fourier space part of the Ewald sum and evaluating the resulting convolutions using fast Fourier transform (FFT). Those algorithms suffer from relatively poor efficiency on large parallel machines especially for mid-size problems around hundreds of thousands of atoms. A variation of the FMM, called PWA, based on plane wave expansions is presented in this paper. A new parallelization strategy for PWA, which takes advantage of the specific form of this expansion, is described. Its parallel efficiency is compared with SPME through detail time measurements on two different computer clusters
International Nuclear Information System (INIS)
Kimura, Toshiya.
1997-03-01
A two-dimensional explicit Euler solver has been implemented for five MIMD parallel computers of different machine architectures in Center for Promotion of Computational Science and Engineering of Japan Atomic Energy Research Institute. These parallel computers are Fujitsu VPP300, NEC SX-4, CRAY T94, IBM SP2, and Hitachi SR2201. The code was parallelized by several parallelization methods, and a typical compressible flow problem has been calculated for different grid sizes changing the number of processors. Their effective performances for parallel calculations, such as calculation speed, speed-up ratio and parallel efficiency, have been investigated and evaluated. The communication time among processors has been also measured and evaluated. As a result, the differences on the performance and the characteristics between vector-parallel and scalar-parallel computers can be pointed, and it will present the basic data for efficient use of parallel computers and for large scale CFD simulations on parallel computers. (author)
International Nuclear Information System (INIS)
Spencer, VN
2001-01-01
An investigation has been conducted regarding the ability of clustered personal computers to improve the performance of executing software simulations for solving engineering problems. The power and utility of personal computers continues to grow exponentially through advances in computing capabilities such as newer microprocessors, advances in microchip technologies, electronic packaging, and cost effective gigabyte-size hard drive capacity. Many engineering problems require significant computing power. Therefore, the computation has to be done by high-performance computer systems that cost millions of dollars and need gigabytes of memory to complete the task. Alternately, it is feasible to provide adequate computing in the form of clustered personal computers. This method cuts the cost and size by linking (clustering) personal computers together across a network. Clusters also have the advantage that they can be used as stand-alone computers when they are not operating as a parallel computer. Parallel computing software to exploit clusters is available for computer operating systems like Unix, Windows NT, or Linux. This project concentrates on the use of Windows NT, and the Parallel Virtual Machine (PVM) system to solve an engineering dynamics problem in Fortran
Overview of Parallel Platforms for Common High Performance Computing
Directory of Open Access Journals (Sweden)
T. Fryza
2012-04-01
Full Text Available The paper deals with various parallel platforms used for high performance computing in the signal processing domain. More precisely, the methods exploiting the multicores central processing units such as message passing interface and OpenMP are taken into account. The properties of the programming methods are experimentally proved in the application of a fast Fourier transform and a discrete cosine transform and they are compared with the possibilities of MATLAB's built-in functions and Texas Instruments digital signal processors with very long instruction word architectures. New FFT and DCT implementations were proposed and tested. The implementation phase was compared with CPU based computing methods and with possibilities of the Texas Instruments digital signal processing library on C6747 floating-point DSPs. The optimal combination of computing methods in the signal processing domain and new, fast routines' implementation is proposed as well.
Parallel computation of automatic differentiation applied to magnetic field calculations
International Nuclear Information System (INIS)
Hinkins, R.L.; Lawrence Berkeley Lab., CA
1994-09-01
The author presents a parallelization of an accelerator physics application to simulate magnetic field in three dimensions. The problem involves the evaluation of high order derivatives with respect to two variables of a multivariate function. Automatic differentiation software had been used with some success, but the computation time was prohibitive. The implementation runs on several platforms, including a network of workstations using PVM, a MasPar using MPFortran, and a CM-5 using CMFortran. A careful examination of the code led to several optimizations that improved its serial performance by a factor of 8.7. The parallelization produced further improvements, especially on the MasPar with a speedup factor of 620. As a result a problem that took six days on a SPARC 10/41 now runs in minutes on the MasPar, making it feasible for physicists at Lawrence Berkeley Laboratory to simulate larger magnets
Parallel computation of transverse wakes in linear colliders
International Nuclear Information System (INIS)
Zhan, Xiaowei; Ko, Kwok.
1996-11-01
SLAC has proposed the detuned structure (DS) as one possible design to control the emittance growth of long bunch trains due to transverse wakefields in the Next Linear Collider (NLC). The DS consists of 206 cells with tapering from cell to cell of the order of few microns to provide Gaussian detuning of the dipole modes. The decoherence of these modes leads to two orders of magnitude reduction in wakefield experienced by the trailing bunch. To model such a large heterogeneous structure realistically is impractical with finite-difference codes using structured grids. The authors have calculated the wakefield in the DS on a parallel computer with a finite-element code using an unstructured grid. The parallel implementation issues are presented along with simulation results that include contributions from higher dipole bands and wall dissipation
A scalable implementation of RI-SCF on parallel computers
International Nuclear Information System (INIS)
Fruechtl, H.A.; Kendall, R.A.; Harrison, R.J.
1996-01-01
In order to avoid the integral bottleneck of conventional SCF calculations, the Resolution of the Identity (RI) method is used to obtain an approximate solution to the Hartree-Fock equations. In this approximation only three-center integrals are needed to build the Fock matrix. It has been implemented as part of the NWChem package of portable and scalable ab initio programs for parallel computers. Utilizing the V-approximation, both the Coulomb and exchange contribution to the Fock matrix can be calculated from a transformed set of three-center integrals which have to be precalculated and stored. A distributed in-core method as well as a disk based implementation have been programmed. Details of the implementation as well as the parallel programming tools used are described. We also give results and timings from benchmark calculations
Eighth SIAM conference on parallel processing for scientific computing: Final program and abstracts
Energy Technology Data Exchange (ETDEWEB)
NONE
1997-12-31
This SIAM conference is the premier forum for developments in parallel numerical algorithms, a field that has seen very lively and fruitful developments over the past decade, and whose health is still robust. Themes for this conference were: combinatorial optimization; data-parallel languages; large-scale parallel applications; message-passing; molecular modeling; parallel I/O; parallel libraries; parallel software tools; parallel compilers; particle simulations; problem-solving environments; and sparse matrix computations.
International Nuclear Information System (INIS)
Nash, T.; Areti, H.; Atac, R.
1988-08-01
Fermilab's Advanced Computer Program (ACP) has been developing highly cost effective, yet practical, parallel computers for high energy physics since 1984. The ACP's latest developments are proceeding in two directions. A Second Generation ACP Multiprocessor System for experiments will include $3500 RISC processors each with performance over 15 VAX MIPS. To support such high performance, the new system allows parallel I/O, parallel interprocess communication, and parallel host processes. The ACP Multi-Array Processor, has been developed for theoretical physics. Each $4000 node is a FORTRAN or C programmable pipelined 20 MFlops (peak), 10 MByte single board computer. These are plugged into a 16 port crossbar switch crate which handles both inter and intra crate communication. The crates are connected in a hypercube. Site oriented applications like lattice gauge theory are supported by system software called CANOPY, which makes the hardware virtually transparent to users. A 256 node, 5 GFlop, system is under construction. 10 refs., 7 figs
Simulation of partially coherent light propagation using parallel computing devices
Magalhães, Tiago C.; Rebordão, José M.
2017-08-01
Light acquires or loses coherence and coherence is one of the few optical observables. Spectra can be derived from coherence functions and understanding any interferometric experiment is also relying upon coherence functions. Beyond the two limiting cases (full coherence or incoherence) the coherence of light is always partial and it changes with propagation. We have implemented a code to compute the propagation of partially coherent light from the source plane to the observation plane using parallel computing devices (PCDs). In this paper, we restrict the propagation in free space only. To this end, we used the Open Computing Language (OpenCL) and the open-source toolkit PyOpenCL, which gives access to OpenCL parallel computation through Python. To test our code, we chose two coherence source models: an incoherent source and a Gaussian Schell-model source. In the former case, we divided into two different source shapes: circular and rectangular. The results were compared to the theoretical values. Our implemented code allows one to choose between the PyOpenCL implementation and a standard one, i.e using the CPU only. To test the computation time for each implementation (PyOpenCL and standard), we used several computer systems with different CPUs and GPUs. We used powers of two for the dimensions of the cross-spectral density matrix (e.g. 324, 644) and a significant speed increase is observed in the PyOpenCL implementation when compared to the standard one. This can be an important tool for studying new source models.
Cluster implementation for parallel computation within MATLAB software environment
International Nuclear Information System (INIS)
Santana, Antonio O. de; Dantas, Carlos C.; Charamba, Luiz G. da R.; Souza Neto, Wilson F. de; Melo, Silvio B. Melo; Lima, Emerson A. de O.
2013-01-01
A cluster for parallel computation with MATLAB software the COCGT - Cluster for Optimizing Computing in Gamma ray Transmission methods, is implemented. The implementation correspond to creation of a local net of computers, facilities and configurations of software, as well as the accomplishment of cluster tests for determine and optimizing of performance in the data processing. The COCGT implementation was required by data computation from gamma transmission measurements applied to fluid dynamic and tomography reconstruction in a FCC-Fluid Catalytic Cracking cold pilot unity, and simulation data as well. As an initial test the determination of SVD - Singular Values Decomposition - of random matrix with dimension (n , n), n=1000, using the Girco's law modified, revealed that COCGT was faster in comparison to the literature [1] cluster, which is similar and operates at the same conditions. Solution of a system of linear equations provided a new test for the COCGT performance by processing a square matrix with n=10000, computing time was 27 s and for square matrix with n=12000, computation time was 45 s. For determination of the cluster behavior in relation to 'parfor' (parallel for-loop) and 'spmd' (single program multiple data), two codes were used containing those two commands and the same problem: determination of SVD of a square matrix with n= 1000. The execution of codes by means of COCGT proved: 1) for the code with 'parfor', the performance improved with the labs number from 1 to 8 labs; 2) for the code 'spmd', just 1 lab (core) was enough to process and give results in less than 1 s. In similar situation, with the difference that now the SVD will be determined from square matrix with n1500, for code with 'parfor', and n=7000, for code with 'spmd'. That results take to conclusions: 1) for the code with 'parfor', the behavior was the same already described above; 2) for code with 'spmd', the same besides having produced a larger performance, it supports a
Parallel computation of multigroup reactivity coefficient using iterative method
Susmikanti, Mike; Dewayatna, Winter
2013-09-01
One of the research activities to support the commercial radioisotope production program is a safety research target irradiation FPM (Fission Product Molybdenum). FPM targets form a tube made of stainless steel in which the nuclear degrees of superimposed high-enriched uranium. FPM irradiation tube is intended to obtain fission. The fission material widely used in the form of kits in the world of nuclear medicine. Irradiation FPM tube reactor core would interfere with performance. One of the disorders comes from changes in flux or reactivity. It is necessary to study a method for calculating safety terrace ongoing configuration changes during the life of the reactor, making the code faster became an absolute necessity. Neutron safety margin for the research reactor can be reused without modification to the calculation of the reactivity of the reactor, so that is an advantage of using perturbation method. The criticality and flux in multigroup diffusion model was calculate at various irradiation positions in some uranium content. This model has a complex computation. Several parallel algorithms with iterative method have been developed for the sparse and big matrix solution. The Black-Red Gauss Seidel Iteration and the power iteration parallel method can be used to solve multigroup diffusion equation system and calculated the criticality and reactivity coeficient. This research was developed code for reactivity calculation which used one of safety analysis with parallel processing. It can be done more quickly and efficiently by utilizing the parallel processing in the multicore computer. This code was applied for the safety limits calculation of irradiated targets FPM with increment Uranium.
SPINET: A Parallel Computing Approach to Spine Simulations
Directory of Open Access Journals (Sweden)
Peter G. Kropf
1996-01-01
Full Text Available Research in scientitic programming enables us to realize more and more complex applications, and on the other hand, application-driven demands on computing methods and power are continuously growing. Therefore, interdisciplinary approaches become more widely used. The interdisciplinary SPINET project presented in this article applies modern scientific computing tools to biomechanical simulations: parallel computing and symbolic and modern functional programming. The target application is the human spine. Simulations of the spine help us to investigate and better understand the mechanisms of back pain and spinal injury. Two approaches have been used: the first uses the finite element method for high-performance simulations of static biomechanical models, and the second generates a simulation developmenttool for experimenting with different dynamic models. A finite element program for static analysis has been parallelized for the MUSIC machine. To solve the sparse system of linear equations, a conjugate gradient solver (iterative method and a frontal solver (direct method have been implemented. The preprocessor required for the frontal solver is written in the modern functional programming language SML, the solver itself in C, thus exploiting the characteristic advantages of both functional and imperative programming. The speedup analysis of both solvers show very satisfactory results for this irregular problem. A mixed symbolic-numeric environment for rigid body system simulations is presented. It automatically generates C code from a problem specification expressed by the Lagrange formalism using Maple.
A hybrid method for the parallel computation of Green's functions
International Nuclear Information System (INIS)
Petersen, Dan Erik; Li Song; Stokbro, Kurt; Sorensen, Hans Henrik B.; Hansen, Per Christian; Skelboe, Stig; Darve, Eric
2009-01-01
Quantum transport models for nanodevices using the non-equilibrium Green's function method require the repeated calculation of the block tridiagonal part of the Green's and lesser Green's function matrices. This problem is related to the calculation of the inverse of a sparse matrix. Because of the large number of times this calculation needs to be performed, this is computationally very expensive even on supercomputers. The classical approach is based on recurrence formulas which cannot be efficiently parallelized. This practically prevents the solution of large problems with hundreds of thousands of atoms. We propose new recurrences for a general class of sparse matrices to calculate Green's and lesser Green's function matrices which extend formulas derived by Takahashi and others. We show that these recurrences may lead to a dramatically reduced computational cost because they only require computing a small number of entries of the inverse matrix. Then, we propose a parallelization strategy for block tridiagonal matrices which involves a combination of Schur complement calculations and cyclic reduction. It achieves good scalability even on problems of modest size.
Large-scale parallel genome assembler over cloud computing environment.
Das, Arghya Kusum; Koppa, Praveen Kumar; Goswami, Sayan; Platania, Richard; Park, Seung-Jong
2017-06-01
The size of high throughput DNA sequencing data has already reached the terabyte scale. To manage this huge volume of data, many downstream sequencing applications started using locality-based computing over different cloud infrastructures to take advantage of elastic (pay as you go) resources at a lower cost. However, the locality-based programming model (e.g. MapReduce) is relatively new. Consequently, developing scalable data-intensive bioinformatics applications using this model and understanding the hardware environment that these applications require for good performance, both require further research. In this paper, we present a de Bruijn graph oriented Parallel Giraph-based Genome Assembler (GiGA), as well as the hardware platform required for its optimal performance. GiGA uses the power of Hadoop (MapReduce) and Giraph (large-scale graph analysis) to achieve high scalability over hundreds of compute nodes by collocating the computation and data. GiGA achieves significantly higher scalability with competitive assembly quality compared to contemporary parallel assemblers (e.g. ABySS and Contrail) over traditional HPC cluster. Moreover, we show that the performance of GiGA is significantly improved by using an SSD-based private cloud infrastructure over traditional HPC cluster. We observe that the performance of GiGA on 256 cores of this SSD-based cloud infrastructure closely matches that of 512 cores of traditional HPC cluster.
Coupling SIMD and SIMT architectures to boost performance of a phylogeny-aware alignment kernel
Directory of Open Access Journals (Sweden)
Alachiotis Nikolaos
2012-08-01
Full Text Available Abstract Background Aligning short DNA reads to a reference sequence alignment is a prerequisite for detecting their biological origin and analyzing them in a phylogenetic context. With the PaPaRa tool we introduced a dedicated dynamic programming algorithm for simultaneously aligning short reads to reference alignments and corresponding evolutionary reference trees. The algorithm aligns short reads to phylogenetic profiles that correspond to the branches of such a reference tree. The algorithm needs to perform an immense number of pairwise alignments. Therefore, we explore vector intrinsics and GPUs to accelerate the PaPaRa alignment kernel. Results We optimized and parallelized PaPaRa on CPUs and GPUs. Via SSE 4.1 SIMD (Single Instruction, Multiple Data intrinsics for x86 SIMD architectures and multi-threading, we obtained a 9-fold acceleration on a single core as well as linear speedups with respect to the number of cores. The peak CPU performance amounts to 18.1 GCUPS (Giga Cell Updates per Second using all four physical cores on an Intel i7 2600 CPU running at 3.4 GHz. The average CPU performance (averaged over all test runs is 12.33 GCUPS. We also used OpenCL to execute PaPaRa on a GPU SIMT (Single Instruction, Multiple Threads architecture. A NVIDIA GeForce 560 GPU delivered peak and average performance of 22.1 and 18.4 GCUPS respectively. Finally, we combined the SIMD and SIMT implementations into a hybrid CPU-GPU system that achieved an accumulated peak performance of 33.8 GCUPS. Conclusions This accelerated version of PaPaRa (available at http://www.exelixis-lab.org/software.html provides a significant performance improvement that allows for analyzing larger datasets in less time. We observe that state-of-the-art SIMD and SIMT architectures deliver comparable performance for this dynamic programming kernel when the “competing programmer approach” is deployed. Finally, we show that overall performance can be substantially increased
CX: A Scalable, Robust Network for Parallel Computing
Directory of Open Access Journals (Sweden)
Peter Cappello
2002-01-01
Full Text Available CX, a network-based computational exchange, is presented. The system's design integrates variations of ideas from other researchers, such as work stealing, non-blocking tasks, eager scheduling, and space-based coordination. The object-oriented API is simple, compact, and cleanly separates application logic from the logic that supports interprocess communication and fault tolerance. Computations, of course, run to completion in the presence of computational hosts that join and leave the ongoing computation. Such hosts, or producers, use task caching and prefetching to overlap computation with interprocessor communication. To break a potential task server bottleneck, a network of task servers is presented. Even though task servers are envisioned as reliable, the self-organizing, scalable network of n- servers, described as a sibling-connected height-balanced fat tree, tolerates a sequence of n-1 server failures. Tasks are distributed throughout the server network via a simple "diffusion" process. CX is intended as a test bed for research on automated silent auctions, reputation services, authentication services, and bonding services. CX also provides a test bed for algorithm research into network-based parallel computation.
Exploring query execution strategies for JIT vectorization and SIMD
T.K. Gubner (Tim); P.A. Boncz (Peter)
2017-01-01
textabstractThis paper partially explores the design space for efficient query processors on future hardware that is rich in SIMD capabilities. It departs from two well-known approaches: (1) interpreted block-at-a-time execution (a.k.a. "vectorization") and (2) "data-centric" JIT compilation, as in
Routing performance analysis and optimization within a massively parallel computer
Archer, Charles Jens; Peters, Amanda; Pinnow, Kurt Walter; Swartz, Brent Allen
2013-04-16
An apparatus, program product and method optimize the operation of a massively parallel computer system by, in part, receiving actual performance data concerning an application executed by the plurality of interconnected nodes, and analyzing the actual performance data to identify an actual performance pattern. A desired performance pattern may be determined for the application, and an algorithm may be selected from among a plurality of algorithms stored within a memory, the algorithm being configured to achieve the desired performance pattern based on the actual performance data.
Particle orbit tracking on a parallel computer: Hypertrack
International Nuclear Information System (INIS)
Cole, B.; Bourianoff, G.; Pilat, F.; Talman, R.
1991-05-01
A program has been written which performs particle orbit tracking on the Intel iPSC/860 distributed memory parallel computer. The tracking is performed using a thin element approach. A brief description of the structure and performance of the code is presented, along with applications of the code to the analysis of accelerator lattices for the SSC. The concept of ''ensemble tracking'', i.e. the tracking of ensemble averages of noninteracting particles, such as the emittance, is presented. Preliminary results of such studies will be presented. 2 refs., 6 figs
Work-Efficient Parallel Skyline Computation for the GPU
DEFF Research Database (Denmark)
Bøgh, Kenneth Sejdenfaden; Chester, Sean; Assent, Ira
2015-01-01
offers the potential for parallelizing skyline computation across thousands of cores. However, attempts to port skyline algorithms to the GPU have prioritized throughput and failed to outperform sequential algorithms. In this paper, we introduce a new skyline algorithm, designed for the GPU, that uses...... a global, static partitioning scheme. With the partitioning, we can permit controlled branching to exploit transitive relationships and avoid most point-to-point comparisons. The result is a non-traditional GPU algorithm, SkyAlign, that prioritizes work-effciency and respectable throughput, rather than...
Moon, Hongsik
What is the impact of multicore and associated advanced technologies on computational software for science? Most researchers and students have multicore laptops or desktops for their research and they need computing power to run computational software packages. Computing power was initially derived from Central Processing Unit (CPU) clock speed. That changed when increases in clock speed became constrained by power requirements. Chip manufacturers turned to multicore CPU architectures and associated technological advancements to create the CPUs for the future. Most software applications benefited by the increased computing power the same way that increases in clock speed helped applications run faster. However, for Computational ElectroMagnetics (CEM) software developers, this change was not an obvious benefit - it appeared to be a detriment. Developers were challenged to find a way to correctly utilize the advancements in hardware so that their codes could benefit. The solution was parallelization and this dissertation details the investigation to address these challenges. Prior to multicore CPUs, advanced computer technologies were compared with the performance using benchmark software and the metric was FLoting-point Operations Per Seconds (FLOPS) which indicates system performance for scientific applications that make heavy use of floating-point calculations. Is FLOPS an effective metric for parallelized CEM simulation tools on new multicore system? Parallel CEM software needs to be benchmarked not only by FLOPS but also by the performance of other parameters related to type and utilization of the hardware, such as CPU, Random Access Memory (RAM), hard disk, network, etc. The codes need to be optimized for more than just FLOPs and new parameters must be included in benchmarking. In this dissertation, the parallel CEM software named High Order Basis Based Integral Equation Solver (HOBBIES) is introduced. This code was developed to address the needs of the
Representing and computing regular languages on massively parallel networks
Energy Technology Data Exchange (ETDEWEB)
Miller, M.I.; O' Sullivan, J.A. (Electronic Systems and Research Lab., of Electrical Engineering, Washington Univ., St. Louis, MO (US)); Boysam, B. (Dept. of Electrical, Computer and Systems Engineering, Rensselaer Polytechnic Inst., Troy, NY (US)); Smith, K.R. (Dept. of Electrical Engineering, Southern Illinois Univ., Edwardsville, IL (US))
1991-01-01
This paper proposes a general method for incorporating rule-based constraints corresponding to regular languages into stochastic inference problems, thereby allowing for a unified representation of stochastic and syntactic pattern constraints. The authors' approach first established the formal connection of rules to Chomsky grammars, and generalizes the original work of Shannon on the encoding of rule-based channel sequences to Markov chains of maximum entropy. This maximum entropy probabilistic view leads to Gibb's representations with potentials which have their number of minima growing at precisely the exponential rate that the language of deterministically constrained sequences grow. These representations are coupled to stochastic diffusion algorithms, which sample the language-constrained sequences by visiting the energy minima according to the underlying Gibbs' probability law. The coupling to stochastic search methods yields the all-important practical result that fully parallel stochastic cellular automata may be derived to generate samples from the rule-based constraint sets. The production rules and neighborhood state structure of the language of sequences directly determines the necessary connection structures of the required parallel computing surface. Representations of this type have been mapped to the DAP-510 massively-parallel processor consisting of 1024 mesh-connected bit-serial processing elements for performing automated segmentation of electron-micrograph images.
Parallel Computer System for 3D Visualization Stereo on GPU
Al-Oraiqat, Anas M.; Zori, Sergii A.
2018-03-01
This paper proposes the organization of a parallel computer system based on Graphic Processors Unit (GPU) for 3D stereo image synthesis. The development is based on the modified ray tracing method developed by the authors for fast search of tracing rays intersections with scene objects. The system allows significant increase in the productivity for the 3D stereo synthesis of photorealistic quality. The generalized procedure of 3D stereo image synthesis on the Graphics Processing Unit/Graphics Processing Clusters (GPU/GPC) is proposed. The efficiency of the proposed solutions by GPU implementation is compared with single-threaded and multithreaded implementations on the CPU. The achieved average acceleration in multi-thread implementation on the test GPU and CPU is about 7.5 and 1.6 times, respectively. Studying the influence of choosing the size and configuration of the computational Compute Unified Device Archi-tecture (CUDA) network on the computational speed shows the importance of their correct selection. The obtained experimental estimations can be significantly improved by new GPUs with a large number of processing cores and multiprocessors, as well as optimized configuration of the computing CUDA network.
Parallel computing and molecular dynamics of biological membranes
International Nuclear Information System (INIS)
La Penna, G.; Letardi, S.; Minicozzi, V.; Morante, S.; Rossi, G.C.; Salina, G.
1998-01-01
In this talk I discuss the general question of the portability of molecular dynamics codes for diffusive systems on parallel computers of the APE family. The intrinsic single precision of the today available platforms does not seem to affect the numerical accuracy of the simulations, while the absence of integer addressing from CPU to individual nodes puts strong constraints on possible programming strategies. Liquids can be satisfactorily simulated using the ''systolic'' method. For more complex systems, like the biological ones at which we are ultimately interested in, the ''domain decomposition'' approach is best suited to beat the quadratic growth of the inter-molecular computational time with the number of atoms of the system. The promising perspectives of using this strategy for extensive simulations of lipid bilayers are briefly reviewed. (orig.)
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.
Concurrent computation of attribute filters on shared memory parallel machines
Wilkinson, Michael H.F.; Gao, Hui; Hesselink, Wim H.; Jonker, Jan-Eppo; Meijster, Arnold
2008-01-01
Morphological attribute filters have not previously been parallelized mainly because they are both global and nonseparable. We propose a parallel algorithm that achieves efficient parallelism for a large class of attribute filters, including attribute openings, closings, thinnings, and thickenings,
Parallel Computation of Unsteady Flows on a Network of Workstations
1997-01-01
Parallel computation of unsteady flows requires significant computational resources. The utilization of a network of workstations seems an efficient solution to the problem where large problems can be treated at a reasonable cost. This approach requires the solution of several problems: 1) the partitioning and distribution of the problem over a network of workstation, 2) efficient communication tools, 3) managing the system efficiently for a given problem. Of course, there is the question of the efficiency of any given numerical algorithm to such a computing system. NPARC code was chosen as a sample for the application. For the explicit version of the NPARC code both two- and three-dimensional problems were studied. Again both steady and unsteady problems were investigated. The issues studied as a part of the research program were: 1) how to distribute the data between the workstations, 2) how to compute and how to communicate at each node efficiently, 3) how to balance the load distribution. In the following, a summary of these activities is presented. Details of the work have been presented and published as referenced.
Simple, parallel, high-performance virtual machines for extreme computations
International Nuclear Information System (INIS)
Chokoufe Nejad, Bijan; Ohl, Thorsten; Reuter, Jurgen
2014-11-01
We introduce a high-performance virtual machine (VM) written in a numerically fast language like Fortran or C to evaluate very large expressions. We discuss the general concept of how to perform computations in terms of a VM and present specifically a VM that is able to compute tree-level cross sections for any number of external legs, given the corresponding byte code from the optimal matrix element generator, O'Mega. Furthermore, this approach allows to formulate the parallel computation of a single phase space point in a simple and obvious way. We analyze hereby the scaling behaviour with multiple threads as well as the benefits and drawbacks that are introduced with this method. Our implementation of a VM can run faster than the corresponding native, compiled code for certain processes and compilers, especially for very high multiplicities, and has in general runtimes in the same order of magnitude. By avoiding the tedious compile and link steps, which may fail for source code files of gigabyte sizes, new processes or complex higher order corrections that are currently out of reach could be evaluated with a VM given enough computing power.
Parallel processing using an optical delay-based reservoir computer
Van der Sande, Guy; Nguimdo, Romain Modeste; Verschaffelt, Guy
2016-04-01
Delay systems subject to delayed optical feedback have recently shown great potential in solving computationally hard tasks. By implementing a neuro-inspired computational scheme relying on the transient response to optical data injection, high processing speeds have been demonstrated. However, reservoir computing systems based on delay dynamics discussed in the literature are designed by coupling many different stand-alone components which lead to bulky, lack of long-term stability, non-monolithic systems. Here we numerically investigate the possibility of implementing reservoir computing schemes based on semiconductor ring lasers. Semiconductor ring lasers are semiconductor lasers where the laser cavity consists of a ring-shaped waveguide. SRLs are highly integrable and scalable, making them ideal candidates for key components in photonic integrated circuits. SRLs can generate light in two counterpropagating directions between which bistability has been demonstrated. We demonstrate that two independent machine learning tasks , even with different nature of inputs with different input data signals can be simultaneously computed using a single photonic nonlinear node relying on the parallelism offered by photonics. We illustrate the performance on simultaneous chaotic time series prediction and a classification of the Nonlinear Channel Equalization. We take advantage of different directional modes to process individual tasks. Each directional mode processes one individual task to mitigate possible crosstalk between the tasks. Our results indicate that prediction/classification with errors comparable to the state-of-the-art performance can be obtained even with noise despite the two tasks being computed simultaneously. We also find that a good performance is obtained for both tasks for a broad range of the parameters. The results are discussed in detail in [Nguimdo et al., IEEE Trans. Neural Netw. Learn. Syst. 26, pp. 3301-3307, 2015
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.
Pacing a data transfer operation between compute nodes on a parallel computer
Blocksome, Michael A [Rochester, MN
2011-09-13
Methods, systems, and products are disclosed for pacing a data transfer between compute nodes on a parallel computer that include: transferring, by an origin compute node, a chunk of an application message to a target compute node; sending, by the origin compute node, a pacing request to a target direct memory access (`DMA`) engine on the target compute node using a remote get DMA operation; determining, by the origin compute node, whether a pacing response to the pacing request has been received from the target DMA engine; and transferring, by the origin compute node, a next chunk of the application message if the pacing response to the pacing request has been received from the target DMA engine.
Nordic Summer School on Parallel Computing in Optimization
Pardalos, Panos; Storøy, Sverre
1997-01-01
During the last three decades, breakthroughs in computer technology have made a tremendous impact on optimization. In particular, parallel computing has made it possible to solve larger and computationally more difficult prob lems. This volume contains mainly lecture notes from a Nordic Summer School held at the Linkoping Institute of Technology, Sweden in August 1995. In order to make the book more complete, a few authors were invited to contribute chapters that were not part of the course on this first occasion. The purpose of this Nordic course in advanced studies was three-fold. One goal was to introduce the students to the new achievements in a new and very active field, bring them close to world leading researchers, and strengthen their competence in an area with internationally explosive rate of growth. A second goal was to strengthen the bonds between students from different Nordic countries, and to encourage collaboration and joint research ventures over the borders. In this respect, the course bui...
Efficient relaxed-Jacobi smoothers for multigrid on parallel computers
Yang, Xiang; Mittal, Rajat
2017-03-01
In this Technical Note, we present a family of Jacobi-based multigrid smoothers suitable for the solution of discretized elliptic equations. These smoothers are based on the idea of scheduled-relaxation Jacobi proposed recently by Yang & Mittal (2014) [18] and employ two or three successive relaxed Jacobi iterations with relaxation factors derived so as to maximize the smoothing property of these iterations. The performance of these new smoothers measured in terms of convergence acceleration and computational workload, is assessed for multi-domain implementations typical of parallelized solvers, and compared to the lexicographic point Gauss-Seidel smoother. The tests include the geometric multigrid method on structured grids as well as the algebraic grid method on unstructured grids. The tests demonstrate that unlike Gauss-Seidel, the convergence of these Jacobi-based smoothers is unaffected by domain decomposition, and furthermore, they outperform the lexicographic Gauss-Seidel by factors that increase with domain partition count.
Optimized collectives using a DMA on a parallel computer
Chen, Dong [Croton On Hudson, NY; Gabor, Dozsa [Ardsley, NY; Giampapa, Mark E [Irvington, NY; Heidelberger,; Phillip, [Cortlandt Manor, NY
2011-02-08
Optimizing collective operations using direct memory access controller on a parallel computer, in one aspect, may comprise establishing a byte counter associated with a direct memory access controller for each submessage in a message. The byte counter includes at least a base address of memory and a byte count associated with a submessage. A byte counter associated with a submessage is monitored to determine whether at least a block of data of the submessage has been received. The block of data has a predetermined size, for example, a number of bytes. The block is processed when the block has been fully received, for example, when the byte count indicates all bytes of the block have been received. The monitoring and processing may continue for all blocks in all submessages in the message.
Ford, Eric B.; Dindar, Saleh; Peters, Jorg
2015-08-01
The realism of astrophysical simulations and statistical analyses of astronomical data are set by the available computational resources. Thus, astronomers and astrophysicists are constantly pushing the limits of computational capabilities. For decades, astronomers benefited from massive improvements in computational power that were driven primarily by increasing clock speeds and required relatively little attention to details of the computational hardware. For nearly a decade, increases in computational capabilities have come primarily from increasing the degree of parallelism, rather than increasing clock speeds. Further increases in computational capabilities will likely be led by many-core architectures such as Graphical Processing Units (GPUs) and Intel Xeon Phi. Successfully harnessing these new architectures, requires significantly more understanding of the hardware architecture, cache hierarchy, compiler capabilities and network network characteristics.I will provide an astronomer's overview of the opportunities and challenges provided by modern many-core architectures and elastic cloud computing. The primary goal is to help an astronomical audience understand what types of problems are likely to yield more than order of magnitude speed-ups and which problems are unlikely to parallelize sufficiently efficiently to be worth the development time and/or costs.I will draw on my experience leading a team in developing the Swarm-NG library for parallel integration of large ensembles of small n-body systems on GPUs, as well as several smaller software projects. I will share lessons learned from collaborating with computer scientists, including both technical and soft skills. Finally, I will discuss the challenges of training the next generation of astronomers to be proficient in this new era of high-performance computing, drawing on experience teaching a graduate class on High-Performance Scientific Computing for Astrophysics and organizing a 2014 advanced summer
An Accurate liver segmentation method using parallel computing algorithm
International Nuclear Information System (INIS)
Elbasher, Eiman Mohammed Khalied
2014-12-01
Computed Tomography (CT or CAT scan) is a noninvasive diagnostic imaging procedure that uses a combination of X-rays and computer technology to produce horizontal, or axial, images (often called slices) of the body. A CT scan shows detailed images of any part of the body, including the bones muscles, fat and organs CT scans are more detailed than standard x-rays. CT scans may be done with or without "contrast Contrast refers to a substance taken by mouth and/ or injected into an intravenous (IV) line that causes the particular organ or tissue under study to be seen more clearly. CT scan of the liver and biliary tract are used in the diagnosis of many diseases in the abdomen structures, particularly when another type of examination, such as X-rays, physical examination, and ultra sound is not conclusive. Unfortunately, the presence of noise and artifact in the edges and fine details in the CT images limit the contrast resolution and make diagnostic procedure more difficult. This experimental study was conducted at the College of Medical Radiological Science, Sudan University of Science and Technology and Fidel Specialist Hospital. The sample of study was included 50 patients. The main objective of this research was to study an accurate liver segmentation method using a parallel computing algorithm, and to segment liver and adjacent organs using image processing technique. The main technique of segmentation used in this study was watershed transform. The scope of image processing and analysis applied to medical application is to improve the quality of the acquired image and extract quantitative information from medical image data in an efficient and accurate way. The results of this technique agreed wit the results of Jarritt et al, (2010), Kratchwil et al, (2010), Jover et al, (2011), Yomamoto et al, (1996), Cai et al (1999), Saudha and Jayashree (2010) who used different segmentation filtering based on the methods of enhancing the computed tomography images. Anther
Shen, Wenfeng; Wei, Daming; Xu, Weimin; Zhu, Xin; Yuan, Shizhong
2010-10-01
Biological computations like electrocardiological modelling and simulation usually require high-performance computing environments. This paper introduces an implementation of parallel computation for computer simulation of electrocardiograms (ECGs) in a personal computer environment with an Intel CPU of Core (TM) 2 Quad Q6600 and a GPU of Geforce 8800GT, with software support by OpenMP and CUDA. It was tested in three parallelization device setups: (a) a four-core CPU without a general-purpose GPU, (b) a general-purpose GPU plus 1 core of CPU, and (c) a four-core CPU plus a general-purpose GPU. To effectively take advantage of a multi-core CPU and a general-purpose GPU, an algorithm based on load-prediction dynamic scheduling was developed and applied to setting (c). In the simulation with 1600 time steps, the speedup of the parallel computation as compared to the serial computation was 3.9 in setting (a), 16.8 in setting (b), and 20.0 in setting (c). This study demonstrates that a current PC with a multi-core CPU and a general-purpose GPU provides a good environment for parallel computations in biological modelling and simulation studies. Copyright 2010 Elsevier Ireland Ltd. All rights reserved.
Iterative algorithms for large sparse linear systems on parallel computers
Adams, L. M.
1982-01-01
Algorithms for assembling in parallel the sparse system of linear equations that result from finite difference or finite element discretizations of elliptic partial differential equations, such as those that arise in structural engineering are developed. Parallel linear stationary iterative algorithms and parallel preconditioned conjugate gradient algorithms are developed for solving these systems. In addition, a model for comparing parallel algorithms on array architectures is developed and results of this model for the algorithms are given.
2009-01-01
At the 19th Annual Conference on Parallel Computational Fluid Dynamics held in Antalya, Turkey, in May 2007, the most recent developments and implementations of large-scale and grid computing were presented. This book, comprised of the invited and selected papers of this conference, details those advances, which are of particular interest to CFD and CFD-related communities. It also offers the results related to applications of various scientific and engineering problems involving flows and flow-related topics. Intended for CFD researchers and graduate students, this book is a state-of-the-art presentation of the relevant methodology and implementation techniques of large-scale computing.
A class of parallel algorithms for computation of the manipulator inertia matrix
Fijany, Amir; Bejczy, Antal K.
1989-01-01
Parallel and parallel/pipeline algorithms for computation of the manipulator inertia matrix are presented. An algorithm based on composite rigid-body spatial inertia method, which provides better features for parallelization, is used for the computation of the inertia matrix. Two parallel algorithms are developed which achieve the time lower bound in computation. Also described is the mapping of these algorithms with topological variation on a two-dimensional processor array, with nearest-neighbor connection, and with cardinality variation on a linear processor array. An efficient parallel/pipeline algorithm for the linear array was also developed, but at significantly higher efficiency.
Parallel In Situ Indexing for Data-intensive Computing
Energy Technology Data Exchange (ETDEWEB)
Kim, Jinoh; Abbasi, Hasan; Chacon, Luis; Docan, Ciprian; Klasky, Scott; Liu, Qing; Podhorszki, Norbert; Shoshani, Arie; Wu, Kesheng
2011-09-09
As computing power increases exponentially, vast amount of data is created by many scientific re- search activities. However, the bandwidth for storing the data to disks and reading the data from disks has been improving at a much slower pace. These two trends produce an ever-widening data access gap. Our work brings together two distinct technologies to address this data access issue: indexing and in situ processing. From decades of database research literature, we know that indexing is an effective way to address the data access issue, particularly for accessing relatively small fraction of data records. As data sets increase in sizes, more and more analysts need to use selective data access, which makes indexing an even more important for improving data access. The challenge is that most implementations of in- dexing technology are embedded in large database management systems (DBMS), but most scientific datasets are not managed by any DBMS. In this work, we choose to include indexes with the scientific data instead of requiring the data to be loaded into a DBMS. We use compressed bitmap indexes from the FastBit software which are known to be highly effective for query-intensive workloads common to scientific data analysis. To use the indexes, we need to build them first. The index building procedure needs to access the whole data set and may also require a significant amount of compute time. In this work, we adapt the in situ processing technology to generate the indexes, thus removing the need of read- ing data from disks and to build indexes in parallel. The in situ data processing system used is ADIOS, a middleware for high-performance I/O. Our experimental results show that the indexes can improve the data access time up to 200 times depending on the fraction of data selected, and using in situ data processing system can effectively reduce the time needed to create the indexes, up to 10 times with our in situ technique when using identical parallel settings.
Identifying logical planes formed of compute nodes of a subcommunicator in a parallel computer
Davis, Kristan D.; Faraj, Daniel A.
2016-03-01
In a parallel computer, a plurality of logical planes formed of compute nodes of a subcommunicator may be identified by: for each compute node of the subcommunicator and for a number of dimensions beginning with a first dimension: establishing, by a plane building node, in a positive direction of the first dimension, all logical planes that include the plane building node and compute nodes of the subcommunicator in a positive direction of a second dimension, where the second dimension is orthogonal to the first dimension; and establishing, by the plane building node, in a negative direction of the first dimension, all logical planes that include the plane building node and compute nodes of the subcommunicator in the positive direction of the second dimension.
Parallel multiphysics algorithms and software for computational nuclear engineering
International Nuclear Information System (INIS)
Gaston, D; Hansen, G; Kadioglu, S; Knoll, D A; Newman, C; Park, H; Permann, C; Taitano, W
2009-01-01
There is a growing trend in nuclear reactor simulation to consider multiphysics problems. This can be seen in reactor analysis where analysts are interested in coupled flow, heat transfer and neutronics, and in fuel performance simulation where analysts are interested in thermomechanics with contact coupled to species transport and chemistry. These more ambitious simulations usually motivate some level of parallel computing. Many of the coupling efforts to date utilize simple code coupling or first-order operator splitting, often referred to as loose coupling. While these approaches can produce answers, they usually leave questions of accuracy and stability unanswered. Additionally, the different physics often reside on separate grids which are coupled via simple interpolation, again leaving open questions of stability and accuracy. Utilizing state of the art mathematics and software development techniques we are deploying next generation tools for nuclear engineering applications. The Jacobian-free Newton-Krylov (JFNK) method combined with physics-based preconditioning provide the underlying mathematical structure for our tools. JFNK is understood to be a modern multiphysics algorithm, but we are also utilizing its unique properties as a scale bridging algorithm. To facilitate rapid development of multiphysics applications we have developed the Multiphysics Object-Oriented Simulation Environment (MOOSE). Examples from two MOOSE-based applications: PRONGHORN, our multiphysics gas cooled reactor simulation tool and BISON, our multiphysics, multiscale fuel performance simulation tool will be presented.
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.
Parallel Monte Carlo reactor neutronics
International Nuclear Information System (INIS)
Blomquist, R.N.; Brown, F.B.
1994-01-01
The issues affecting implementation of parallel algorithms for large-scale engineering Monte Carlo neutron transport simulations are discussed. For nuclear reactor calculations, these include load balancing, recoding effort, reproducibility, domain decomposition techniques, I/O minimization, and strategies for different parallel architectures. Two codes were parallelized and tested for performance. The architectures employed include SIMD, MIMD-distributed memory, and workstation network with uneven interactive load. Speedups linear with the number of nodes were achieved
Parallel computing of a climate model on the dawn 1000 by domain decomposition method
Bi, Xunqiang
1997-12-01
In this paper the parallel computing of a grid-point nine-level atmospheric general circulation model on the Dawn 1000 is introduced. The model was developed by the Institute of Atmospheric Physics (IAP), Chinese Academy of Sciences (CAS). The Dawn 1000 is a MIMD massive parallel computer made by National Research Center for Intelligent Computer (NCIC), CAS. A two-dimensional domain decomposition method is adopted to perform the parallel computing. The potential ways to increase the speed-up ratio and exploit more resources of future massively parallel supercomputation are also discussed.
Parallel computing for data science with examples in R, C++ and CUDA
Matloff, Norman
2015-01-01
Parallel Computing for Data Science: With Examples in R, C++ and CUDA is one of the first parallel computing books to concentrate exclusively on parallel data structures, algorithms, software tools, and applications in data science. It includes examples not only from the classic ""n observations, p variables"" matrix format but also from time series, network graph models, and numerous other structures common in data science. The examples illustrate the range of issues encountered in parallel programming.With the main focus on computation, the book shows how to compute on three types of platfor
Archer, Charles J; Blocksome, Michael A; Cernohous, Bob R; Ratterman, Joseph D; Smith, Brian E
2014-11-11
Endpoint-based parallel data processing with non-blocking collective instructions in a PAMI of a parallel computer is disclosed. The PAMI is composed of data communications endpoints, each including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task. The compute nodes are coupled for data communications through the PAMI. The parallel application establishes a data communications geometry specifying a set of endpoints that are used in collective operations of the PAMI by associating with the geometry a list of collective algorithms valid for use with the endpoints of the geometry; registering in each endpoint in the geometry a dispatch callback function for a collective operation; and executing without blocking, through a single one of the endpoints in the geometry, an instruction for the collective operation.
Introduction to massively-parallel computing in high-energy physics
AUTHOR|(CDS)2083520
1993-01-01
Ever since computers were first used for scientific and numerical work, there has existed an "arms race" between the technical development of faster computing hardware, and the desires of scientists to solve larger problems in shorter time-scales. However, the vast leaps in processor performance achieved through advances in semi-conductor science have reached a hiatus as the technology comes up against the physical limits of the speed of light and quantum effects. This has lead all high performance computer manufacturers to turn towards a parallel architecture for their new machines. In these lectures we will introduce the history and concepts behind parallel computing, and review the various parallel architectures and software environments currently available. We will then introduce programming methodologies that allow efficient exploitation of parallel machines, and present case studies of the parallelization of typical High Energy Physics codes for the two main classes of parallel computing architecture (S...
Parallel Computation of the Jacobian Matrix for Nonlinear Equation Solvers Using MATLAB
Rose, Geoffrey K.; Nguyen, Duc T.; Newman, Brett A.
2017-01-01
Demonstrating speedup for parallel code on a multicore shared memory PC can be challenging in MATLAB due to underlying parallel operations that are often opaque to the user. This can limit potential for improvement of serial code even for the so-called embarrassingly parallel applications. One such application is the computation of the Jacobian matrix inherent to most nonlinear equation solvers. Computation of this matrix represents the primary bottleneck in nonlinear solver speed such that commercial finite element (FE) and multi-body-dynamic (MBD) codes attempt to minimize computations. A timing study using MATLAB's Parallel Computing Toolbox was performed for numerical computation of the Jacobian. Several approaches for implementing parallel code were investigated while only the single program multiple data (spmd) method using composite objects provided positive results. Parallel code speedup is demonstrated but the goal of linear speedup through the addition of processors was not achieved due to PC architecture.
Faster Smith-Waterman database searches with inter-sequence SIMD parallelisation
Directory of Open Access Journals (Sweden)
Rognes Torbjørn
2011-06-01
Full Text Available Abstract Background The Smith-Waterman algorithm for local sequence alignment is more sensitive than heuristic methods for database searching, but also more time-consuming. The fastest approach to parallelisation with SIMD technology has previously been described by Farrar in 2007. The aim of this study was to explore whether further speed could be gained by other approaches to parallelisation. Results A faster approach and implementation is described and benchmarked. In the new tool SWIPE, residues from sixteen different database sequences are compared in parallel to one query residue. Using a 375 residue query sequence a speed of 106 billion cell updates per second (GCUPS was achieved on a dual Intel Xeon X5650 six-core processor system, which is over six times more rapid than software based on Farrar's 'striped' approach. SWIPE was about 2.5 times faster when the programs used only a single thread. For shorter queries, the increase in speed was larger. SWIPE was about twice as fast as BLAST when using the BLOSUM50 score matrix, while BLAST was about twice as fast as SWIPE for the BLOSUM62 matrix. The software is designed for 64 bit Linux on processors with SSSE3. Source code is available from http://dna.uio.no/swipe/ under the GNU Affero General Public License. Conclusions Efficient parallelisation using SIMD on standard hardware makes it possible to run Smith-Waterman database searches more than six times faster than before. The approach described here could significantly widen the potential application of Smith-Waterman searches. Other applications that require optimal local alignment scores could also benefit from improved performance.
Faster Smith-Waterman database searches with inter-sequence SIMD parallelisation.
Rognes, Torbjørn
2011-06-01
The Smith-Waterman algorithm for local sequence alignment is more sensitive than heuristic methods for database searching, but also more time-consuming. The fastest approach to parallelisation with SIMD technology has previously been described by Farrar in 2007. The aim of this study was to explore whether further speed could be gained by other approaches to parallelisation. A faster approach and implementation is described and benchmarked. In the new tool SWIPE, residues from sixteen different database sequences are compared in parallel to one query residue. Using a 375 residue query sequence a speed of 106 billion cell updates per second (GCUPS) was achieved on a dual Intel Xeon X5650 six-core processor system, which is over six times more rapid than software based on Farrar's 'striped' approach. SWIPE was about 2.5 times faster when the programs used only a single thread. For shorter queries, the increase in speed was larger. SWIPE was about twice as fast as BLAST when using the BLOSUM50 score matrix, while BLAST was about twice as fast as SWIPE for the BLOSUM62 matrix. The software is designed for 64 bit Linux on processors with SSSE3. Source code is available from http://dna.uio.no/swipe/ under the GNU Affero General Public License. Efficient parallelisation using SIMD on standard hardware makes it possible to run Smith-Waterman database searches more than six times faster than before. The approach described here could significantly widen the potential application of Smith-Waterman searches. Other applications that require optimal local alignment scores could also benefit from improved performance.
Energy Technology Data Exchange (ETDEWEB)
Lober, R.R.; Tautges, T.J.; Vaughan, C.T.
1997-03-01
Paving is an automated mesh generation algorithm which produces all-quadrilateral elements. It can additionally generate these elements in varying sizes such that the resulting mesh adapts to a function distribution, such as an error function. While powerful, conventional paving is a very serial algorithm in its operation. Parallel paving is the extension of serial paving into parallel environments to perform the same meshing functions as conventional paving only on distributed, discretized models. This extension allows large, adaptive, parallel finite element simulations to take advantage of paving`s meshing capabilities for h-remap remeshing. A significantly modified version of the CUBIT mesh generation code has been developed to host the parallel paving algorithm and demonstrate its capabilities on both two dimensional and three dimensional surface geometries and compare the resulting parallel produced meshes to conventionally paved meshes for mesh quality and algorithm performance. Sandia`s {open_quotes}tiling{close_quotes} dynamic load balancing code has also been extended to work with the paving algorithm to retain parallel efficiency as subdomains undergo iterative mesh refinement.
An object-oriented programming paradigm for parallelization of computational fluid dynamics
International Nuclear Information System (INIS)
Ohta, Takashi.
1997-03-01
We propose an object-oriented programming paradigm for parallelization of scientific computing programs, and show that the approach can be a very useful strategy. Generally, parallelization of scientific programs tends to be complicated and unportable due to the specific requirements of each parallel computer or compiler. In this paper, we show that the object-oriented programming design, which separates the parallel processing parts from the solver of the applications, can achieve the large improvement in the maintenance of the codes, as well as the high portability. We design the program for the two-dimensional Euler equations according to the paradigm, and evaluate the parallel performance on IBM SP2. (author)
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)
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.
International Nuclear Information System (INIS)
Rajagopalan, S.; Jethra, A.; Khare, A.N.; Ghodgaonkar, M.D.; Srivenkateshan, R.; Menon, S.V.G.
1990-01-01
Issues relating to implementing iterative procedures, for numerical solution of elliptic partial differential equations, on a distributed parallel computing system are discussed. Preliminary investigations show that a speed-up of about 3.85 is achievable on a four transputer pipeline network. (author). 2 figs., 3 a ppendixes., 7 refs
How to Build an AppleSeed: A Parallel Macintosh Cluster for Numerically Intensive Computing
Decyk, V. K.; Dauger, D. E.
We have constructed a parallel cluster consisting of a mixture of Apple Macintosh G3 and G4 computers running the Mac OS, and have achieved very good performance on numerically intensive, parallel plasma particle-incell simulations. A subset of the MPI message-passing library was implemented in Fortran77 and C. This library enabled us to port code, without modification, from other parallel processors to the Macintosh cluster. Unlike Unix-based clusters, no special expertise in operating systems is required to build and run the cluster. This enables us to move parallel computing from the realm of experts to the main stream of computing.
OpenCL code generation for low energy wide SIMD architectures with explicit datapath.
She, D.; He, Y.; Waeijen, L.J.W.; Corporaal, H.; Jeschke, H.; Silvén, O.
2013-01-01
Energy efficiency is one of the most important aspects in designing embedded processors. The use of a wide SIMD processor architecture is a promising approach to build energy-efficient high performance embedded processors. In this paper, we propose a configurable wide SIMD architecture that utilizes
Simulation of a two-dimensional dipolar system on a APE100/quadrics SIMD architecture
International Nuclear Information System (INIS)
Bruno, A.; Pisacane, F.; Rosato, V.
1997-01-01
The temperature behavior of a system of dipoles with long-range interactions has been simulated via a two-dimensional lattice Monte Carlo on a massively (SIMD) platform (Quadrics/APE100). Thermodynamic quantities have been evaluated in order to locate and to characterize the phase transition in absence of applied field. Emphasis is given to the code implementation on the SIMD architecture and to the relevant features which have been used to improve code capabilities and performances. The probability of simultaneous occurrence of at least k spanning clusters has been studied by Monte Carlo simulations on the 2D square lattice with free boundaries at the bond percolation threshold p c = 1/2. It is found that the probability of k and more Incipient Spanning Clusters (ISC) have the values P(k > 1) ∼ 0.00658(3) and P(k > 2) ∼ 0.00000148(21) provided that the limit of these probabilities for infinite lattices exists. The probability P(k > 3) of more than three ISC could be estimated to be of the order of 10 -11 and is beyond the possibility to compute such a value by nowadays computers. So, it is impossible to check in simulations the Aizenman law for the probabilities when k much-gt 1. We have detected a single sample with four ISC in a total number of about 1010 samples investigated. The probability of this single event is 1/10 for that number of samples. The influence of boundary conditions is discussed in the last section
DIMACS Workshop on Interconnection Networks and Mapping, and Scheduling Parallel Computations
Rosenberg, Arnold L; Sotteau, Dominique; NSF Science and Technology Center in Discrete Mathematics and Theoretical Computer Science; Interconnection networks and mapping and scheduling parallel computations
1995-01-01
The interconnection network is one of the most basic components of a massively parallel computer system. Such systems consist of hundreds or thousands of processors interconnected to work cooperatively on computations. One of the central problems in parallel computing is the task of mapping a collection of processes onto the processors and routing network of a parallel machine. Once this mapping is done, it is critical to schedule computations within and communication among processor from universities and laboratories, as well as practitioners involved in the design, implementation, and application of massively parallel systems. Focusing on interconnection networks of parallel architectures of today and of the near future , the book includes topics such as network topologies,network properties, message routing, network embeddings, network emulation, mappings, and efficient scheduling. inputs for a process are available where and when the process is scheduled to be computed. This book contains the refereed pro...
Stampi: a message passing library for distributed parallel computing. User's guide
International Nuclear Information System (INIS)
Imamura, Toshiyuki; Koide, Hiroshi; Takemiya, Hiroshi
1998-11-01
A new message passing library, Stampi, has been developed to realize a computation with different kind of parallel computers arbitrarily and making MPI (Message Passing Interface) as an unique interface for communication. Stampi is based on MPI2 specification. It realizes dynamic process creation to different machines and communication between spawned one within the scope of MPI semantics. Vender implemented MPI as a closed system in one parallel machine and did not support both functions; process creation and communication to external machines. Stampi supports both functions and enables us distributed parallel computing. Currently Stampi has been implemented on COMPACS (COMplex PArallel Computer System) introduced in CCSE, five parallel computers and one graphic workstation, and any communication on them can be processed on. (author)
A method of paralleling computer calculation for two-dimensional kinetic plasma model
International Nuclear Information System (INIS)
Brazhnik, V.A.; Demchenko, V.V.; Dem'yanov, V.G.; D'yakov, V.E.; Ol'shanskij, V.V.; Panchenko, V.I.
1987-01-01
A method for parallel computer calculation and OSIRIS program complex realizing it and designed for numerical plasma simulation by the macroparticle method are described. The calculation can be carried out either with one or simultaneously with two computers BESM-6, that is provided by some package of interacting programs functioning in every computer. Program interaction in every computer is based on event techniques realized in OS DISPAK. Parallel computer calculation with two BESM-6 computers allows to accelerate the computation 1.5 times
Cooperative storage of shared files in a parallel computing system with dynamic block size
Bent, John M.; Faibish, Sorin; Grider, Gary
2015-11-10
Improved techniques are provided for parallel writing of data to a shared object in a parallel computing system. A method is provided for storing data generated by a plurality of parallel processes to a shared object in a parallel computing system. The method is performed by at least one of the processes and comprises: dynamically determining a block size for storing the data; exchanging a determined amount of the data with at least one additional process to achieve a block of the data having the dynamically determined block size; and writing the block of the data having the dynamically determined block size to a file system. The determined block size comprises, e.g., a total amount of the data to be stored divided by the number of parallel processes. The file system comprises, for example, a log structured virtual parallel file system, such as a Parallel Log-Structured File System (PLFS).
The specification of Stampi, a message passing library for distributed parallel computing
International Nuclear Information System (INIS)
Imamura, Toshiyuki; Takemiya, Hiroshi; Koide, Hiroshi
2000-03-01
At CCSE, Center for Promotion of Computational Science and Engineering, a new message passing library for heterogeneous and distributed parallel computing has been developed, and it is called as Stampi. Stampi enables us to communicate between any combination of parallel computers as well as workstations. Currently, a Stampi system is constructed from Stampi library and Stampi/Java. It provides functions to connect a Stampi application with not only those on COMPACS, COMplex Parallel Computer System, but also applets which work on WWW browsers. This report summarizes the specifications of Stampi and details the development of its system. (author)
Quealy, Angela; Cole, Gary L.; Blech, Richard A.
1993-01-01
The Application Portable Parallel Library (APPL) is a subroutine-based library of communication primitives that is callable from applications written in FORTRAN or C. APPL provides a consistent programmer interface to a variety of distributed and shared-memory multiprocessor MIMD machines. The objective of APPL is to minimize the effort required to move parallel applications from one machine to another, or to a network of homogeneous machines. APPL encompasses many of the message-passing primitives that are currently available on commercial multiprocessor systems. This paper describes APPL (version 2.3.1) and its usage, reports the status of the APPL project, and indicates possible directions for the future. Several applications using APPL are discussed, as well as performance and overhead results.
Event Based Simulator for Parallel Computing over the Wide Area Network for Real Time Visualization
Sundararajan, Elankovan; Harwood, Aaron; Kotagiri, Ramamohanarao; Satria Prabuwono, Anton
As the computational requirement of applications in computational science continues to grow tremendously, the use of computational resources distributed across the Wide Area Network (WAN) becomes advantageous. However, not all applications can be executed over the WAN due to communication overhead that can drastically slowdown the computation. In this paper, we introduce an event based simulator to investigate the performance of parallel algorithms executed over the WAN. The event based simulator known as SIMPAR (SIMulator for PARallel computation), simulates the actual computations and communications involved in parallel computation over the WAN using time stamps. Visualization of real time applications require steady stream of processed data flow for visualization purposes. Hence, SIMPAR may prove to be a valuable tool to investigate types of applications and computing resource requirements to provide uninterrupted flow of processed data for real time visualization purposes. The results obtained from the simulation show concurrence with the expected performance using the L-BSP model.
A Parallel and Distributed Surrogate Model Implementation for Computational Steering
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
Using parallel computing in modeling and optimization of mineral ...
African Journals Online (AJOL)
Then to solve ultimate pit limit problem it is required to find such a sub graph in a graph whose sum of weights will be maximal. One of the possible solutions of this problem is using genetic algorithms. We use a ... Details of implementation parallel genetic algorithm for searching open pit limits are provided. Comparison with ...
Computation of watersheds based on parallel graph algorithms
Meijster, A.; Roerdink, J.B.T.M.; Maragos, P; Schafer, RW; Butt, MA
1996-01-01
In this paper the implementation of a parallel watershed algorithm is described. The algorithm has been implemented on a Cray J932, which is a shared memory architecture with 32 processors. The watershed transform has generally been considered to be inherently sequential, but recently a few research
Locating hardware faults in a data communications network of a parallel computer
Archer, Charles J.; Megerian, Mark G.; Ratterman, Joseph D.; Smith, Brian E.
2010-01-12
Hardware faults location in a data communications network of a parallel computer. Such a parallel computer includes a plurality of compute nodes and a data communications network that couples the compute nodes for data communications and organizes the compute node as a tree. Locating hardware faults includes identifying a next compute node as a parent node and a root of a parent test tree, identifying for each child compute node of the parent node a child test tree having the child compute node as root, running a same test suite on the parent test tree and each child test tree, and identifying the parent compute node as having a defective link connected from the parent compute node to a child compute node if the test suite fails on the parent test tree and succeeds on all the child test trees.
Byun, Chansup; Guruswamy, Guru P.; Kutler, Paul (Technical Monitor)
1994-01-01
In recent years significant advances have been made for parallel computers in both hardware and software. Now parallel computers have become viable tools in computational mechanics. Many application codes developed on conventional computers have been modified to benefit from parallel computers. Significant speedups in some areas have been achieved by parallel computations. For single-discipline use of both fluid dynamics and structural dynamics, computations have been made on wing-body configurations using parallel computers. However, only a limited amount of work has been completed in combining these two disciplines for multidisciplinary applications. The prime reason is the increased level of complication associated with a multidisciplinary approach. In this work, procedures to compute aeroelasticity on parallel computers using direct coupling of fluid and structural equations will be investigated for wing-body configurations. The parallel computer selected for computations is an Intel iPSC/860 computer which is a distributed-memory, multiple-instruction, multiple data (MIMD) computer with 128 processors. In this study, the computational efficiency issues of parallel integration of both fluid and structural equations will be investigated in detail. The fluid and structural domains will be modeled using finite-difference and finite-element approaches, respectively. Results from the parallel computer will be compared with those from the conventional computers using a single processor. This study will provide an efficient computational tool for the aeroelastic analysis of wing-body structures on MIMD type parallel computers.
A parallel finite-difference method for computational aerodynamics
International Nuclear Information System (INIS)
Swisshelm, J.M.
1989-01-01
A finite-difference scheme for solving complex three-dimensional aerodynamic flow on parallel-processing supercomputers is presented. The method consists of a basic flow solver with multigrid convergence acceleration, embedded grid refinements, and a zonal equation scheme. Multitasking and vectorization have been incorporated into the algorithm. Results obtained include multiprocessed flow simulations from the Cray X-MP and Cray-2. Speedups as high as 3.3 for the two-dimensional case and 3.5 for segments of the three-dimensional case have been achieved on the Cray-2. The entire solver attained a factor of 2.7 improvement over its unitasked version on the Cray-2. The performance of the parallel algorithm on each machine is analyzed. 14 refs
Parallel Computational Intelligence-Based Multi-Camera Surveillance System
Orts-Escolano, Sergio; Garcia-Rodriguez, Jose; Morell, Vicente; Cazorla, Miguel; Azorin-Lopez, Jorge; García-Chamizo, Juan Manuel
2014-01-01
In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mob...
Directory of Open Access Journals (Sweden)
Ling Kang
2017-03-01
Full Text Available Compared to the hydrostatic hydrodynamic model, the non-hydrostatic hydrodynamic model can accurately simulate flows that feature vertical accelerations. The model’s low computational efficiency severely restricts its wider application. This paper proposes a non-hydrostatic hydrodynamic model based on a multithreading parallel computing method. The horizontal momentum equation is obtained by integrating the Navier–Stokes equations from the bottom to the free surface. The vertical momentum equation is approximated by the Keller-box scheme. A two-step method is used to solve the model equations. A parallel strategy based on block decomposition computation is utilized. The original computational domain is subdivided into two subdomains that are physically connected via a virtual boundary technique. Two sub-threads are created and tasked with the computation of the two subdomains. The producer–consumer model and the thread lock technique are used to achieve synchronous communication between sub-threads. The validity of the model was verified by solitary wave propagation experiments over a flat bottom and slope, followed by two sinusoidal wave propagation experiments over submerged breakwater. The parallel computing method proposed here was found to effectively enhance computational efficiency and save 20%–40% computation time compared to serial computing. The parallel acceleration rate and acceleration efficiency are approximately 1.45% and 72%, respectively. The parallel computing method makes a contribution to the popularization of non-hydrostatic models.
Lee, Wei-Po; Hsiao, Yu-Ting; Hwang, Wei-Che
2014-01-16
To improve the tedious task of reconstructing gene networks through testing experimentally the possible interactions between genes, it becomes a trend to adopt the automated reverse engineering procedure instead. Some evolutionary algorithms have been suggested for deriving network parameters. However, to infer large networks by the evolutionary algorithm, it is necessary to address two important issues: premature convergence and high computational cost. To tackle the former problem and to enhance the performance of traditional evolutionary algorithms, it is advisable to use parallel model evolutionary algorithms. To overcome the latter and to speed up the computation, it is advocated to adopt the mechanism of cloud computing as a promising solution: most popular is the method of MapReduce programming model, a fault-tolerant framework to implement parallel algorithms for inferring large gene networks. This work presents a practical framework to infer large gene networks, by developing and parallelizing a hybrid GA-PSO optimization method. Our parallel method is extended to work with the Hadoop MapReduce programming model and is executed in different cloud computing environments. To evaluate the proposed approach, we use a well-known open-source software GeneNetWeaver to create several yeast S. cerevisiae sub-networks and use them to produce gene profiles. Experiments have been conducted and the results have been analyzed. They show that our parallel approach can be successfully used to infer networks with desired behaviors and the computation time can be largely reduced. Parallel population-based algorithms can effectively determine network parameters and they perform better than the widely-used sequential algorithms in gene network inference. These parallel algorithms can be distributed to the cloud computing environment to speed up the computation. By coupling the parallel model population-based optimization method and the parallel computational framework, high
MEDUSA - An overset grid flow solver for network-based parallel computer systems
Smith, Merritt H.; Pallis, Jani M.
1993-01-01
Continuing improvement in processing speed has made it feasible to solve the Reynolds-Averaged Navier-Stokes equations for simple three-dimensional flows on advanced workstations. Combining multiple workstations into a network-based heterogeneous parallel computer allows the application of programming principles learned on MIMD (Multiple Instruction Multiple Data) distributed memory parallel computers to the solution of larger problems. An overset-grid flow solution code has been developed which uses a cluster of workstations as a network-based parallel computer. Inter-process communication is provided by the Parallel Virtual Machine (PVM) software. Solution speed equivalent to one-third of a Cray-YMP processor has been achieved from a cluster of nine commonly used engineering workstation processors. Load imbalance and communication overhead are the principal impediments to parallel efficiency in this application.
COMPSs-Mobile: parallel programming for mobile-cloud computing
Lordan Gomis, Francesc-Josep; Badia Sala, Rosa Maria
2016-01-01
The advent of Cloud and the popularization of mobile devices have led us to a shift in computing access. Computing users will have an interaction display while the real computation will be performed remotely, in the Cloud. COMPSs-Mobile is a framework that aims to ease the development of energy-efficient and high-performing applications for this environment. The framework provides an infrastructure-unaware programming model that allows developers to code regular Android applications that, ...
Yim, Keun Soo
This dissertation summarizes experimental validation and co-design studies conducted to optimize the fault detection capabilities and overheads in hybrid computer systems (e.g., using CPUs and Graphics Processing Units, or GPUs), and consequently to improve the scalability of parallel computer systems using computational accelerators. The experimental validation studies were conducted to help us understand the failure characteristics of CPU-GPU hybrid computer systems under various types of hardware faults. The main characterization targets were faults that are difficult to detect and/or recover from, e.g., faults that cause long latency failures (Ch. 3), faults in dynamically allocated resources (Ch. 4), faults in GPUs (Ch. 5), faults in MPI programs (Ch. 6), and microarchitecture-level faults with specific timing features (Ch. 7). The co-design studies were based on the characterization results. One of the co-designed systems has a set of source-to-source translators that customize and strategically place error detectors in the source code of target GPU programs (Ch. 5). Another co-designed system uses an extension card to learn the normal behavioral and semantic execution patterns of message-passing processes executing on CPUs, and to detect abnormal behaviors of those parallel processes (Ch. 6). The third co-designed system is a co-processor that has a set of new instructions in order to support software-implemented fault detection techniques (Ch. 7). The work described in this dissertation gains more importance because heterogeneous processors have become an essential component of state-of-the-art supercomputers. GPUs were used in three of the five fastest supercomputers that were operating in 2011. Our work included comprehensive fault characterization studies in CPU-GPU hybrid computers. In CPUs, we monitored the target systems for a long period of time after injecting faults (a temporally comprehensive experiment), and injected faults into various types of
Energy Technology Data Exchange (ETDEWEB)
Lamarcq, J. [Service de Physique Theorique, CEA Centre d`Etudes de Saclay, 91 - Gif-sur-Yvette (France)
1998-07-10
Numerical simulation allows the theorists to convince themselves about the validity of the models they use. Particularly by simulating the spin lattices one can judge about the validity of a conjecture. Simulating a system defined by a large number of degrees of freedom requires highly sophisticated machines. This study deals with modelling the magnetic interactions between the ions of a crystal. Many exact results have been found for spin 1/2 systems but not for systems of other spins for which many simulation have been carried out. The interest for simulations has been renewed by the Haldane`s conjecture stipulating the existence of a energy gap between the ground state and the first excited states of a spin 1 lattice. The existence of this gap has been experimentally demonstrated. This report contains the following four chapters: 1. Spin systems; 2. Calculation of eigenvalues; 3. Programming; 4. Parallel calculation 14 refs., 6 figs.
A kind of video image digitizing circuit based on computer parallel port
International Nuclear Information System (INIS)
Wang Yi; Tang Le; Cheng Jianping; Li Yuanjing; Zhang Binquan
2003-01-01
A kind of video images digitizing circuit based on parallel port was developed to digitize the flash x ray images in our Multi-Channel Digital Flash X ray Imaging System. The circuit can digitize the video images and store in static memory. The digital images can be transferred to computer through parallel port and can be displayed, processed and stored. (authors)
Directory of Open Access Journals (Sweden)
Alexander B. Bakulev
2012-11-01
Full Text Available This article deals with mathematical models and algorithms, providing mobility of sequential programs parallel representation on the high-level language, presents formal model of operation environment processes management, based on the proposed model of programs parallel representation, presenting computation process on the base of multi-core processors.
National Research Council Canada - National Science Library
Hisley, Dixie
1999-01-01
.... The goals of this report are: (1) to investigate the performance of message passing and loop level parallelization techniques, as they were implemented in the computational fluid dynamics (CFD...
Massively Parallel Computing at Sandia and Its Application to National Defense
National Research Council Canada - National Science Library
Dosanjh, Sudip
1991-01-01
Two years ago, researchers at Sandia National Laboratories showed that a massively parallel computer with 1024 processors could solve scientific problems more than 1000 times faster than a single processor...
Computational cost of isogeometric multi-frontal solvers on parallel distributed memory machines
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
Computer model of a reverberant and parallel circuit coupling
Kalil, Camila de Andrade; de Castro, Maria Clícia Stelling; Cortez, Célia Martins
2017-11-01
The objective of the present study was to deepen the knowledge about the functioning of the neural circuits by implementing a signal transmission model using the Graph Theory in a small network of neurons composed of an interconnected reverberant and parallel circuit, in order to investigate the processing of the signals in each of them and the effects on the output of the network. For this, a program was developed in C language and simulations were done using neurophysiological data obtained in the literature.
Paging memory from random access memory to backing storage in a parallel computer
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.
P-SPARSLIB: A parallel sparse iterative solution package
Energy Technology Data Exchange (ETDEWEB)
Saad, Y. [Univ. of Minnesota, Minneapolis, MN (United States)
1994-12-31
Iterative methods are gaining popularity in engineering and sciences at a time where the computational environment is changing rapidly. P-SPARSLIB is a project to build a software library for sparse matrix computations on parallel computers. The emphasis is on iterative methods and the use of distributed sparse matrices, an extension of the domain decomposition approach to general sparse matrices. One of the goals of this project is to develop a software package geared towards specific applications. For example, the author will test the performance and usefulness of P-SPARSLIB modules on linear systems arising from CFD applications. Equally important is the goal of portability. In the long run, the author wishes to ensure that this package is portable on a variety of platforms, including SIMD environments and shared memory environments.
Applications of parallel computer architectures to the real-time simulation of nuclear power systems
International Nuclear Information System (INIS)
Doster, J.M.; Sills, E.D.
1988-01-01
In this paper the authors report on efforts to utilize parallel computer architectures for the thermal-hydraulic simulation of nuclear power systems and current research efforts toward the development of advanced reactor operator aids and control systems based on this new technology. Many aspects of reactor thermal-hydraulic calculations are inherently parallel, and the computationally intensive portions of these calculations can be effectively implemented on modern computers. Timing studies indicate faster-than-real-time, high-fidelity physics models can be developed when the computational algorithms are designed to take advantage of the computer's architecture. These capabilities allow for the development of novel control systems and advanced reactor operator aids. Coupled with an integral real-time data acquisition system, evolving parallel computer architectures can provide operators and control room designers improved control and protection capabilities. Current research efforts are currently under way in this area
TME (Task Mapping Editor): tool for executing distributed parallel computing. TME user's manual
International Nuclear Information System (INIS)
Takemiya, Hiroshi; Yamagishi, Nobuhiro; Imamura, Toshiyuki
2000-03-01
At the Center for Promotion of Computational Science and Engineering, a software environment PPExe has been developed to support scientific computing on a parallel computer cluster (distributed parallel scientific computing). TME (Task Mapping Editor) is one of components of the PPExe and provides a visual programming environment for distributed parallel scientific computing. Users can specify data dependence among tasks (programs) visually as a data flow diagram and map these tasks onto computers interactively through GUI of TME. The specified tasks are processed by other components of PPExe such as Meta-scheduler, RIM (Resource Information Monitor), and EMS (Execution Management System) according to the execution order of these tasks determined by TME. In this report, we describe the usage of TME. (author)
Archer, Charles J [Rochester, MN; Blocksome, Michael A [Rochester, MN; Peters, Amanda E [Cambridge, MA; Ratterman, Joseph D [Rochester, MN; Smith, Brian E [Rochester, MN
2012-04-17
Methods, apparatus, and products are disclosed for reducing power consumption while synchronizing a plurality of compute nodes during execution of a parallel application that include: beginning, by each compute node, performance of a blocking operation specified by the parallel application, each compute node beginning the blocking operation asynchronously with respect to the other compute nodes; reducing, for each compute node, power to one or more hardware components of that compute node in response to that compute node beginning the performance of the blocking operation; and restoring, for each compute node, the power to the hardware components having power reduced in response to all of the compute nodes beginning the performance of the blocking operation.
Archer, Charles J [Rochester, MN; Blocksome, Michael A [Rochester, MN; Peters, Amanda A [Rochester, MN; Ratterman, Joseph D [Rochester, MN; Smith, Brian E [Rochester, MN
2012-01-10
Methods, apparatus, and products are disclosed for reducing power consumption while synchronizing a plurality of compute nodes during execution of a parallel application that include: beginning, by each compute node, performance of a blocking operation specified by the parallel application, each compute node beginning the blocking operation asynchronously with respect to the other compute nodes; reducing, for each compute node, power to one or more hardware components of that compute node in response to that compute node beginning the performance of the blocking operation; and restoring, for each compute node, the power to the hardware components having power reduced in response to all of the compute nodes beginning the performance of the blocking operation.
Line-plane broadcasting in a data communications network of a parallel computer
Archer, Charles J.; Berg, Jeremy E.; Blocksome, Michael A.; Smith, Brian E.
2010-06-08
Methods, apparatus, and products are disclosed for line-plane broadcasting in a data communications network of a parallel computer, the parallel computer comprising a plurality of compute nodes connected together through the network, the network optimized for point to point data communications and characterized by at least a first dimension, a second dimension, and a third dimension, that include: initiating, by a broadcasting compute node, a broadcast operation, including sending a message to all of the compute nodes along an axis of the first dimension for the network; sending, by each compute node along the axis of the first dimension, the message to all of the compute nodes along an axis of the second dimension for the network; and sending, by each compute node along the axis of the second dimension, the message to all of the compute nodes along an axis of the third dimension for the network.
Ocean Modeling and Visualization on Massively Parallel Computer
Chao, Yi; Li, P. Peggy; Wang, Ping; Katz, Daniel S.; Cheng, Benny N.
1997-01-01
Climate modeling is one of the grand challenges of computational science, and ocean modeling plays an important role in both understanding the current climatic conditions and predicting future climate change.
Parallel Computational Intelligence-Based Multi-Camera Surveillance System
Directory of Open Access Journals (Sweden)
Sergio Orts-Escolano
2014-04-01
Full Text Available In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units. It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.
Valasek, Lukas; Glasa, Jan
2017-12-01
Current fire simulation systems are capable to utilize advantages of high-performance computer (HPC) platforms available and to model fires efficiently in parallel. In this paper, efficiency of a corridor fire simulation on a HPC computer cluster is discussed. The parallel MPI version of Fire Dynamics Simulator is used for testing efficiency of selected strategies of allocation of computational resources of the cluster using a greater number of computational cores. Simulation results indicate that if the number of cores used is not equal to a multiple of the total number of cluster node cores there are allocation strategies which provide more efficient calculations.
Parallel diffusion calculation for the PHAETON on-line multiprocessor computer
International Nuclear Information System (INIS)
Collart, J.M.; Fedon-Magnaud, C.; Lautard, J.J.
1987-04-01
The aim of the PHAETON project is the design of an on-line computer in order to increase the immediate knowledge of the main operating and safety parameters in power plants. A significant stage is the computation of the three dimensional flux distribution. For cost and safety reason a computer based on a parallel microprocessor architecture has been studied. This paper presents a first approach to parallelized three dimensional diffusion calculation. A computing software has been written and built in a four processors demonstrator. We present the realization in progress, concerning the final equipment. 8 refs
Blocksome, Michael A.; Mamidala, Amith R.
2015-07-07
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 a deterministic data communications network 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 the deterministic data communications network; 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.
Chen, Ying; Balla, Apuroop; Rayford II, Cleveland E; Zhou, Weihua; Fang, Jian; Cong, Linlin
2010-01-01
Digital tomosynthesis is a novel technology that has been developed for various clinical applications. Parallel imaging configuration is utilised in a few tomosynthesis imaging areas such as digital chest tomosynthesis. Recently, parallel imaging configuration for breast tomosynthesis began to appear too. In this paper, we present the investigation on computational analysis of impulse response characterisation as the start point of our important research efforts to optimise the parallel imaging configurations. Results suggest that impulse response computational analysis is an effective method to compare and optimise imaging configurations.
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
Parallel computation for blood cell classification in medical hyperspectral imagery
International Nuclear Information System (INIS)
Li, Wei; Wu, Lucheng; Qiu, Xianbo; Ran, Qiong; Xie, Xiaoming
2016-01-01
With the advantage of fine spectral resolution, hyperspectral imagery provides great potential for cell classification. This paper provides a promising classification system including the following three stages: (1) band selection for a subset of spectral bands with distinctive and informative features, (2) spectral-spatial feature extraction, such as local binary patterns (LBP), and (3) followed by an effective classifier. Moreover, these three steps are further implemented on graphics processing units (GPU) respectively, which makes the system real-time and more practical. The GPU parallel implementation is compared with the serial implementation on central processing units (CPU). Experimental results based on real medical hyperspectral data demonstrate that the proposed system is able to offer high accuracy and fast speed, which are appealing for cell classification in medical hyperspectral imagery. (paper)
Vector and parallel processors in computational science. Proceedings
Energy Technology Data Exchange (ETDEWEB)
Duff, I S; Reid, J K
1985-01-01
This volume contains papers from most of the invited talks and from several of the contributed talks and poster sessions presented at VAPP II. The contents present an extensive coverage of all important aspects of vector and parallel processors, including hardware, languages, numerical algorithms and applications. The topics covered include descriptions of new machines (both research and commercial machines), languages and software aids, and general discussions of whole classes of machines and their uses. Numerical methods papers include Monte Carlo algorithms, iterative and direct methods for solving large systems, finite elements, optimization, random number generation and mathematical software. The specific applications covered include neutron diffusion calculations, molecular dynamics, weather forecasting, lattice gauge calculations, fluid dynamics, flight simulation, cartography, image processing and cryptography. Most machines and architecture types are being used for these applications. many refs.
A Parallel and Distributed Surrogate Model Implementation for Computational Steering
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.
Managing internode data communications for an uninitialized process in a parallel computer
Archer, Charles J; Blocksome, Michael A; Miller, Douglas R; Parker, Jeffrey J; Ratterman, Joseph D; Smith, Brian E
2014-05-20
A parallel computer includes nodes, each having main memory and a messaging unit (MU). Each MU includes computer memory, which in turn includes, MU message buffers. Each MU message buffer is associated with an uninitialized process on the compute node. In the parallel computer, managing internode data communications for an uninitialized process includes: receiving, by an MU of a compute node, one or more data communications messages in an MU message buffer associated with an uninitialized process on the compute node; determining, by an application agent, that the MU message buffer associated with the uninitialized process is full prior to initialization of the uninitialized process; establishing, by the application agent, a temporary message buffer for the uninitialized process in main computer memory; and moving, by the application agent, data communications messages from the MU message buffer associated with the uninitialized process to the temporary message buffer in main computer memory.
Multiscale Methods, Parallel Computation, and Neural Networks for Real-Time Computer Vision.
Battiti, Roberto
1990-01-01
This thesis presents new algorithms for low and intermediate level computer vision. The guiding ideas in the presented approach are those of hierarchical and adaptive processing, concurrent computation, and supervised learning. Processing of the visual data at different resolutions is used not only to reduce the amount of computation necessary to reach the fixed point, but also to produce a more accurate estimation of the desired parameters. The presented adaptive multiple scale technique is applied to the problem of motion field estimation. Different parts of the image are analyzed at a resolution that is chosen in order to minimize the error in the coefficients of the differential equations to be solved. Tests with video-acquired images show that velocity estimation is more accurate over a wide range of motion with respect to the homogeneous scheme. In some cases introduction of explicit discontinuities coupled to the continuous variables can be used to avoid propagation of visual information from areas corresponding to objects with different physical and/or kinematic properties. The human visual system uses concurrent computation in order to process the vast amount of visual data in "real -time." Although with different technological constraints, parallel computation can be used efficiently for computer vision. All the presented algorithms have been implemented on medium grain distributed memory multicomputers with a speed-up approximately proportional to the number of processors used. A simple two-dimensional domain decomposition assigns regions of the multiresolution pyramid to the different processors. The inter-processor communication needed during the solution process is proportional to the linear dimension of the assigned domain, so that efficiency is close to 100% if a large region is assigned to each processor. Finally, learning algorithms are shown to be a viable technique to engineer computer vision systems for different applications starting from
Scalable Parallelization of Skyline Computation for Multi-core Processors
DEFF Research Database (Denmark)
Chester, Sean; Sidlauskas, Darius; Assent, Ira
2015-01-01
The skyline is an important query operator for multi-criteria decision making. It reduces a dataset to only those points that offer optimal trade-offs of dimensions. In general, it is very expensive to compute. Recently, multi-core CPU algorithms have been proposed to accelerate the computation...... of the skyline. However, they do not sufficiently minimize dominance tests and so are not competitive with state-of-the-art sequential algorithms. In this paper, we introduce a novel multi-core skyline algorithm, Hybrid, which processes points in blocks. It maintains a shared, global skyline among all threads...
Parallel distributed computing in modeling of the nanomaterials production technologies
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
Monte Carlo calculations on a parallel computer using MORSE-C.G
International Nuclear Information System (INIS)
Wood, J.
1995-01-01
The general purpose particle transport Monte Carlo code, MORSE-C.G., is implemented on a parallel computing transputer-based system having MIMD architecture. Example problems are solved which are representative of the 3-principal types of problem that can be solved by the original serial code, namely, fixed source, eigenvalue (k-eff) and time-dependent. The results from the parallelized version of the code are compared in tables with the serial code run on a mainframe serial computer, and with an independent, deterministic transport code. The performance of the parallel computer as the number of processors is varied is shown graphically. For the parallel strategy used, the loss of efficiency as the number of processors is increased, is investigated. (author)
International Nuclear Information System (INIS)
Park, Min Jae; Lee, Jae Sung; Kim, Soo Mee; Kang, Ji Yeon; Lee, Dong Soo; Park, Kwang Suk
2009-01-01
Conventional image reconstruction uses simplified physical models of projection. However, real physics, for example 3D reconstruction, takes too long time to process all the data in clinic and is unable in a common reconstruction machine because of the large memory for complex physical models. We suggest the realistic distributed memory model of fast-reconstruction using parallel processing on personal computers to enable large-scale technologies. The preliminary tests for the possibility on virtual machines and various performance test on commercial super computer, Tachyon were performed. Expectation maximization algorithm with common 2D projection and realistic 3D line of response were tested. Since the process time was getting slower (max 6 times) after a certain iteration, optimization for compiler was performed to maximize the efficiency of parallelization. Parallel processing of a program on multiple computers was available on Linux with MPICH and NFS. We verified that differences between parallel processed image and single processed image at the same iterations were under the significant digits of floating point number, about 6 bit. Double processors showed good efficiency (1.96 times) of parallel computing. Delay phenomenon was solved by vectorization method using SSE. Through the study, realistic parallel computing system in clinic was established to be able to reconstruct by plenty of memory using the realistic physical models which was impossible to simplify
Stampi: a message passing library for distributed parallel computing. User's guide, second edition
International Nuclear Information System (INIS)
Imamura, Toshiyuki; Koide, Hiroshi; Takemiya, Hiroshi
2000-02-01
A new message passing library, Stampi, has been developed to realize a computation with different kind of parallel computers arbitrarily and making MPI (Message Passing Interface) as an unique interface for communication. Stampi is based on the MPI2 specification, and it realizes dynamic process creation to different machines and communication between spawned one within the scope of MPI semantics. Main features of Stampi are summarized as follows: (i) an automatic switch function between external- and internal communications, (ii) a message routing/relaying with a routing module, (iii) a dynamic process creation, (iv) a support of two types of connection, Master/Slave and Client/Server, (v) a support of a communication with Java applets. Indeed vendors implemented MPI libraries as a closed system in one parallel machine or their systems, and did not support both functions; process creation and communication to external machines. Stampi supports both functions and enables us distributed parallel computing. Currently Stampi has been implemented on COMPACS (COMplex PArallel Computer System) introduced in CCSE, five parallel computers and one graphic workstation, moreover on eight kinds of parallel machines, totally fourteen systems. Stampi provides us MPI communication functionality on them. This report describes mainly the usage of Stampi. (author)
Parallel processing algorithms for hydrocodes on a computer with MIMD architecture (DENELCOR's HEP)
International Nuclear Information System (INIS)
Hicks, D.L.
1983-11-01
In real time simulation/prediction of complex systems such as water-cooled nuclear reactors, if reactor operators had fast simulator/predictors to check the consequences of their operations before implementing them, events such as the incident at Three Mile Island might be avoided. However, existing simulator/predictors such as RELAP run slower than real time on serial computers. It appears that the only way to overcome the barrier to higher computing rates is to use computers with architectures that allow concurrent computations or parallel processing. The computer architecture with the greatest degree of parallelism is labeled Multiple Instruction Stream, Multiple Data Stream (MIMD). An example of a machine of this type is the HEP computer by DENELCOR. It appears that hydrocodes are very well suited for parallelization on the HEP. It is a straightforward exercise to parallelize explicit, one-dimensional Lagrangean hydrocodes in a zone-by-zone parallelization. Similarly, implicit schemes can be parallelized in a zone-by-zone fashion via an a priori, symbolic inversion of the tridiagonal matrix that arises in an implicit scheme. These techniques are extended to Eulerian hydrocodes by using Harlow's rezone technique. The extension from single-phase Eulerian to two-phase Eulerian is straightforward. This step-by-step extension leads to hydrocodes with zone-by-zone parallelization that are capable of two-phase flow simulation. Extensions to two and three spatial dimensions can be achieved by operator splitting. It appears that a zone-by-zone parallelization is the best way to utilize the capabilities of an MIMD machine. 40 references
International Nuclear Information System (INIS)
Laurent, C.; Chassery, J.M.; Peyrin, F.; Girerd, C.
1996-01-01
This paper deals with the parallel implementations of reconstruction methods in 3D tomography. 3D tomography requires voluminous data and long computation times. Parallel computing, on MIMD computers, seems to be a good approach to manage this problem. In this study, we present the different steps of the parallelization on an abstract parallel computer. Depending on the method, we use two main approaches to parallelize the algorithms: the local approach and the global approach. Experimental results on MIMD computers are presented. Two 3D images reconstructed from realistic data are showed
Implementation of QR up- and downdating on a massively parallel |computer
DEFF Research Database (Denmark)
Bendtsen, Claus; Hansen, Per Christian; Madsen, Kaj
1995-01-01
We describe an implementation of QR up- and downdating on a massively parallel computer (the Connection Machine CM-200) and show that the algorithm maps well onto the computer. In particular, we show how the use of corrected semi-normal equations for downdating can be efficiently implemented. We...... also illustrate the use of our algorithms in a new LP algorithm....
Software Alchemy: Turning Complex Statistical Computations into Embarrassingly-Parallel Ones
Directory of Open Access Journals (Sweden)
Norman Matloff
2016-07-01
Full Text Available The growth in the use of computationally intensive statistical procedures, especially with big data, has necessitated the usage of parallel computation on diverse platforms such as multicore, GPUs, clusters and clouds. However, slowdown due to interprocess communication costs typically limits such methods to "embarrassingly parallel" (EP algorithms, especially on non-shared memory platforms. This paper develops a broadlyapplicable method for converting many non-EP algorithms into statistically equivalent EP ones. The method is shown to yield excellent levels of speedup for a variety of statistical computations. It also overcomes certain problems of memory limitations.
Accelerating Neuroimage Registration through Parallel Computation of Similarity Metric.
Directory of Open Access Journals (Sweden)
Yun-Gang Luo
Full Text Available Neuroimage registration is crucial for brain morphometric analysis and treatment efficacy evaluation. However, existing advanced registration algorithms such as FLIRT and ANTs are not efficient enough for clinical use. In this paper, a GPU implementation of FLIRT with the correlation ratio (CR as the similarity metric and a GPU accelerated correlation coefficient (CC calculation for the symmetric diffeomorphic registration of ANTs have been developed. The comparison with their corresponding original tools shows that our accelerated algorithms can greatly outperform the original algorithm in terms of computational efficiency. This paper demonstrates the great potential of applying these registration tools in clinical applications.
Directory of Open Access Journals (Sweden)
Schmidt Bertil
2010-04-01
Full Text Available Abstract Background Due to its high sensitivity, the Smith-Waterman algorithm is widely used for biological database searches. Unfortunately, the quadratic time complexity of this algorithm makes it highly time-consuming. The exponential growth of biological databases further deteriorates the situation. To accelerate this algorithm, many efforts have been made to develop techniques in high performance architectures, especially the recently emerging many-core architectures and their associated programming models. Findings This paper describes the latest release of the CUDASW++ software, CUDASW++ 2.0, which makes new contributions to Smith-Waterman protein database searches using compute unified device architecture (CUDA. A parallel Smith-Waterman algorithm is proposed to further optimize the performance of CUDASW++ 1.0 based on the single instruction, multiple thread (SIMT abstraction. For the first time, we have investigated a partitioned vectorized Smith-Waterman algorithm using CUDA based on the virtualized single instruction, multiple data (SIMD abstraction. The optimized SIMT and the partitioned vectorized algorithms were benchmarked, and remarkably, have similar performance characteristics. CUDASW++ 2.0 achieves performance improvement over CUDASW++ 1.0 as much as 1.74 (1.72 times using the optimized SIMT algorithm and up to 1.77 (1.66 times using the partitioned vectorized algorithm, with a performance of up to 17 (30 billion cells update per second (GCUPS on a single-GPU GeForce GTX 280 (dual-GPU GeForce GTX 295 graphics card. Conclusions CUDASW++ 2.0 is publicly available open-source software, written in CUDA and C++ programming languages. It obtains significant performance improvement over CUDASW++ 1.0 using either the optimized SIMT algorithm or the partitioned vectorized algorithm for Smith-Waterman protein database searches by fully exploiting the compute capability of commonly used CUDA-enabled low-cost GPUs.
Programming a massively parallel, computation universal system: static behavior
Energy Technology Data Exchange (ETDEWEB)
Lapedes, A.; Farber, R.
1986-01-01
In previous work by the authors, the ''optimum finding'' properties of Hopfield neural nets were applied to the nets themselves to create a ''neural compiler.'' This was done in such a way that the problem of programming the attractors of one neural net (called the Slave net) was expressed as an optimization problem that was in turn solved by a second neural net (the Master net). In this series of papers that approach is extended to programming nets that contain interneurons (sometimes called ''hidden neurons''), and thus deals with nets capable of universal computation. 22 refs.
Weighted Local Active Pixel Pattern (WLAPP for Face Recognition in Parallel Computation Environment
Directory of Open Access Journals (Sweden)
Gundavarapu Mallikarjuna Rao
2013-10-01
Full Text Available Abstract - The availability of multi-core technology resulted totally new computational era. Researchers are keen to explore available potential in state of art-machines for breaking the bearer imposed by serial computation. Face Recognition is one of the challenging applications on so ever computational environment. The main difficulty of traditional Face Recognition algorithms is lack of the scalability. In this paper Weighted Local Active Pixel Pattern (WLAPP, a new scalable Face Recognition Algorithm suitable for parallel environment is proposed. Local Active Pixel Pattern (LAPP is found to be simple and computational inexpensive compare to Local Binary Patterns (LBP. WLAPP is developed based on concept of LAPP. The experimentation is performed on FG-Net Aging Database with deliberately introduced 20% distortion and the results are encouraging. Keywords — Active pixels, Face Recognition, Local Binary Pattern (LBP, Local Active Pixel Pattern (LAPP, Pattern computing, parallel workers, template, weight computation.
10th International Workshop on Parallel Tools for High Performance Computing
Gracia, José; Hilbrich, Tobias; Knüpfer, Andreas; Resch, Michael; Nagel, Wolfgang
2017-01-01
This book presents the proceedings of the 10th International Parallel Tools Workshop, held October 4-5, 2016 in Stuttgart, Germany – a forum to discuss the latest advances in parallel tools. High-performance computing plays an increasingly important role for numerical simulation and modelling in academic and industrial research. At the same time, using large-scale parallel systems efficiently is becoming more difficult. A number of tools addressing parallel program development and analysis have emerged from the high-performance computing community over the last decade, and what may have started as collection of small helper script has now matured to production-grade frameworks. Powerful user interfaces and an extensive body of documentation allow easy usage by non-specialists.
Parallel computation with molecular-motor-propelled agents in nanofabricated networks.
Nicolau, Dan V; Lard, Mercy; Korten, Till; van Delft, Falco C M J M; Persson, Malin; Bengtsson, Elina; Månsson, Alf; Diez, Stefan; Linke, Heiner; Nicolau, Dan V
2016-03-08
The combinatorial nature of many important mathematical problems, including nondeterministic-polynomial-time (NP)-complete problems, places a severe limitation on the problem size that can be solved with conventional, sequentially operating electronic computers. There have been significant efforts in conceiving parallel-computation approaches in the past, for example: DNA computation, quantum computation, and microfluidics-based computation. However, these approaches have not proven, so far, to be scalable and practical from a fabrication and operational perspective. Here, we report the foundations of an alternative parallel-computation system in which a given combinatorial problem is encoded into a graphical, modular network that is embedded in a nanofabricated planar device. Exploring the network in a parallel fashion using a large number of independent, molecular-motor-propelled agents then solves the mathematical problem. This approach uses orders of magnitude less energy than conventional computers, thus addressing issues related to power consumption and heat dissipation. We provide a proof-of-concept demonstration of such a device by solving, in a parallel fashion, the small instance {2, 5, 9} of the subset sum problem, which is a benchmark NP-complete problem. Finally, we discuss the technical advances necessary to make our system scalable with presently available technology.
Teaching Scientific Computing: A Model-Centered Approach to Pipeline and Parallel Programming with C
Directory of Open Access Journals (Sweden)
Vladimiras Dolgopolovas
2015-01-01
Full Text Available The aim of this study is to present an approach to the introduction into pipeline and parallel computing, using a model of the multiphase queueing system. Pipeline computing, including software pipelines, is among the key concepts in modern computing and electronics engineering. The modern computer science and engineering education requires a comprehensive curriculum, so the introduction to pipeline and parallel computing is the essential topic to be included in the curriculum. At the same time, the topic is among the most motivating tasks due to the comprehensive multidisciplinary and technical requirements. To enhance the educational process, the paper proposes a novel model-centered framework and develops the relevant learning objects. It allows implementing an educational platform of constructivist learning process, thus enabling learners’ experimentation with the provided programming models, obtaining learners’ competences of the modern scientific research and computational thinking, and capturing the relevant technical knowledge. It also provides an integral platform that allows a simultaneous and comparative introduction to pipelining and parallel computing. The programming language C for developing programming models and message passing interface (MPI and OpenMP parallelization tools have been chosen for implementation.
International Nuclear Information System (INIS)
Bellucci, V.J.
1990-01-01
This paper describes IBM's approach to parallel computing using the IBM ES/3090 computer. Parallel processing concepts were discussed including its advantages, potential performance improvements and limitations. Particular applications and capabilities for the IBM ES/3090 were presented along with preliminary results from some utilities in the application of parallel processing to simulation of system reliability, air pollution models, and power network dynamics
CUDA/GPU Technology : Parallel Programming For High Performance Scientific Computing
YUHENDRA; KUZE, Hiroaki; JOSAPHAT, Tetuko Sri Sumantyo
2009-01-01
[ABSTRACT]Graphics processing units (GP Us) originally designed for computer video cards have emerged as the most powerful chip in a high-performance workstation. In the high performance computation capabilities, graphic processing units (GPU) lead to much more powerful performance than conventional CPUs by means of parallel processing. In 2007, the birth of Compute Unified Device Architecture (CUDA) and CUDA-enabled GPUs by NVIDIA Corporation brought a revolution in the general purpose GPU a...
Distributed and cloud computing from parallel processing to the Internet of Things
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
Massively parallel computation of PARASOL code on the Origin 3800 system
International Nuclear Information System (INIS)
Hosokawa, Masanari; Takizuka, Tomonori
2001-10-01
The divertor particle simulation code named PARASOL simulates open-field plasmas between divertor walls self-consistently by using an electrostatic PIC method and a binary collision Monte Carlo model. The PARASOL parallelized with MPI-1.1 for scalar parallel computer worked on Intel Paragon XP/S system. A system SGI Origin 3800 was newly installed (May, 2001). The parallel programming was improved at this switchover. As a result of the high-performance new hardware and this improvement, the PARASOL is speeded up by about 60 times with the same number of processors. (author)
Lashkin, S. V.; Kozelkov, A. S.; Yalozo, A. V.; Gerasimov, V. Yu.; Zelensky, D. K.
2017-12-01
This paper describes the details of the parallel implementation of the SIMPLE algorithm for numerical solution of the Navier-Stokes system of equations on arbitrary unstructured grids. The iteration schemes for the serial and parallel versions of the SIMPLE algorithm are implemented. In the description of the parallel implementation, special attention is paid to computational data exchange among processors under the condition of the grid model decomposition using fictitious cells. We discuss the specific features for the storage of distributed matrices and implementation of vector-matrix operations in parallel mode. It is shown that the proposed way of matrix storage reduces the number of interprocessor exchanges. A series of numerical experiments illustrates the effect of the multigrid SLAE solver tuning on the general efficiency of the algorithm; the tuning involves the types of the cycles used (V, W, and F), the number of iterations of a smoothing operator, and the number of cells for coarsening. Two ways (direct and indirect) of efficiency evaluation for parallelization of the numerical algorithm are demonstrated. The paper presents the results of solving some internal and external flow problems with the evaluation of parallelization efficiency by two algorithms. It is shown that the proposed parallel implementation enables efficient computations for the problems on a thousand processors. Based on the results obtained, some general recommendations are made for the optimal tuning of the multigrid solver, as well as for selecting the optimal number of cells per processor.
Modeling the Fracture of Ice Sheets on Parallel Computers
Energy Technology Data Exchange (ETDEWEB)
Waisman, Haim [Columbia Univ., New York, NY (United States); Tuminaro, Ray [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
2013-10-10
The objective of this project was to investigate the complex fracture of ice and understand its role within larger ice sheet simulations and global climate change. This objective was achieved by developing novel physics based models for ice, novel numerical tools to enable the modeling of the physics and by collaboration with the ice community experts. At the present time, ice fracture is not explicitly considered within ice sheet models due in part to large computational costs associated with the accurate modeling of this complex phenomena. However, fracture not only plays an extremely important role in regional behavior but also influences ice dynamics over much larger zones in ways that are currently not well understood. To this end, our research findings through this project offers significant advancement to the field and closes a large gap of knowledge in understanding and modeling the fracture of ice sheets in the polar regions. Thus, we believe that our objective has been achieved and our research accomplishments are significant. This is corroborated through a set of published papers, posters and presentations at technical conferences in the field. In particular significant progress has been made in the mechanics of ice, fracture of ice sheets and ice shelves in polar regions and sophisticated numerical methods that enable the solution of the physics in an efficient way.
Parallel Object-Oriented Computation Applied to a Finite Element Problem
Directory of Open Access Journals (Sweden)
Jon B. Weissman
1993-01-01
Full Text Available The conventional wisdom in the scientific computing community is that the best way to solve large-scale numerically intensive scientific problems on today's parallel MIMD computers is to use Fortran or C programmed in a data-parallel style using low-level message-passing primitives. This approach inevitably leads to nonportable codes and extensive development time, and restricts parallel programming to the domain of the expert programmer. We believe that these problems are not inherent to parallel computing but are the result of the programming tools used. We will show that comparable performance can be achieved with little effort if better tools that present higher level abstractions are used. The vehicle for our demonstration is a 2D electromagnetic finite element scattering code we have implemented in Mentat, an object-oriented parallel processing system. We briefly describe the application. Mentat, the implementation, and present performance results for both a Mentat and a hand-coded parallel Fortran version.
Storing files in a parallel computing system based on user-specified parser function
Faibish, Sorin; Bent, John M; Tzelnic, Percy; Grider, Gary; Manzanares, Adam; Torres, Aaron
2014-10-21
Techniques are provided for storing files in a parallel computing system based on a user-specified parser function. A plurality of files generated by a distributed application in a parallel computing system are stored by obtaining a parser from the distributed application for processing the plurality of files prior to storage; and storing one or more of the plurality of files in one or more storage nodes of the parallel computing system based on the processing by the parser. The plurality of files comprise one or more of a plurality of complete files and a plurality of sub-files. The parser can optionally store only those files that satisfy one or more semantic requirements of the parser. The parser can also extract metadata from one or more of the files and the extracted metadata can be stored with one or more of the plurality of files and used for searching for files.
Parallel computing simulation of fluid flow in the unsaturated zone of Yucca Mountain, Nevada
International Nuclear Information System (INIS)
Zhang, Keni; Wu, Yu-Shu; Bodvarsson, G.S.
2001-01-01
This paper presents the application of parallel computing techniques to large-scale modeling of fluid flow in the unsaturated zone (UZ) at Yucca Mountain, Nevada. In this study, parallel computing techniques, as implemented into the TOUGH2 code, are applied in large-scale numerical simulations on a distributed-memory parallel computer. The modeling study has been conducted using an over-one-million-cell three-dimensional numerical model, which incorporates a wide variety of field data for the highly heterogeneous fractured formation at Yucca Mountain. The objective of this study is to analyze the impact of various surface infiltration scenarios (under current and possible future climates) on flow through the UZ system, using various hydrogeological conceptual models with refined grids. The results indicate that the one-million-cell models produce better resolution results and reveal some flow patterns that cannot be obtained using coarse-grid modeling models
Breast Cancer Image Segmentation Using K-Means Clustering Based on GPU Cuda Parallel Computing
Directory of Open Access Journals (Sweden)
Andika Elok Amalia
2018-02-01
Full Text Available Image processing technology is now widely used in the health area, one example is to help the radiologist to analyze the result of MRI (Magnetic Resonance Imaging, CT Scan and Mammography. Image segmentation is a process which is intended to obtain the objects contained in the image by dividing the image into several areas that have similarity attributes on an object with the aim of facilitating the analysis process. The increasing amount of patient data and larger image size are new challenges in segmentation process to use time efficiently while still keeping the process quality. Research on the segmentation of medical images have been done but still few that combine with parallel computing. In this research, K-Means clustering on the image of mammography result is implemented using two-way computation which are serial and parallel. The result shows that parallel computing gives faster average performance execution up to twofold.
8th International Workshop on Parallel Tools for High Performance Computing
Gracia, José; Knüpfer, Andreas; Resch, Michael; Nagel, Wolfgang
2015-01-01
Numerical simulation and modelling using High Performance Computing has evolved into an established technique in academic and industrial research. At the same time, the High Performance Computing infrastructure is becoming ever more complex. For instance, most of the current top systems around the world use thousands of nodes in which classical CPUs are combined with accelerator cards in order to enhance their compute power and energy efficiency. This complexity can only be mastered with adequate development and optimization tools. Key topics addressed by these tools include parallelization on heterogeneous systems, performance optimization for CPUs and accelerators, debugging of increasingly complex scientific applications, and optimization of energy usage in the spirit of green IT. This book represents the proceedings of the 8th International Parallel Tools Workshop, held October 1-2, 2014 in Stuttgart, Germany – which is a forum to discuss the latest advancements in the parallel tools.
Fluid/Structure Interaction Studies of Aircraft Using High Fidelity Equations on Parallel Computers
Guruswamy, Guru; VanDalsem, William (Technical Monitor)
1994-01-01
Abstract Aeroelasticity which involves strong coupling of fluids, structures and controls is an important element in designing an aircraft. Computational aeroelasticity using low fidelity methods such as the linear aerodynamic flow equations coupled with the modal structural equations are well advanced. Though these low fidelity approaches are computationally less intensive, they are not adequate for the analysis of modern aircraft such as High Speed Civil Transport (HSCT) and Advanced Subsonic Transport (AST) which can experience complex flow/structure interactions. HSCT can experience vortex induced aeroelastic oscillations whereas AST can experience transonic buffet associated structural oscillations. Both aircraft may experience a dip in the flutter speed at the transonic regime. For accurate aeroelastic computations at these complex fluid/structure interaction situations, high fidelity equations such as the Navier-Stokes for fluids and the finite-elements for structures are needed. Computations using these high fidelity equations require large computational resources both in memory and speed. Current conventional super computers have reached their limitations both in memory and speed. As a result, parallel computers have evolved to overcome the limitations of conventional computers. This paper will address the transition that is taking place in computational aeroelasticity from conventional computers to parallel computers. The paper will address special techniques needed to take advantage of the architecture of new parallel computers. Results will be illustrated from computations made on iPSC/860 and IBM SP2 computer by using ENSAERO code that directly couples the Euler/Navier-Stokes flow equations with high resolution finite-element structural equations.
Parallel, distributed and GPU computing technologies in single-particle electron microscopy.
Schmeisser, Martin; Heisen, Burkhard C; Luettich, Mario; Busche, Boris; Hauer, Florian; Koske, Tobias; Knauber, Karl-Heinz; Stark, Holger
2009-07-01
Most known methods for the determination of the structure of macromolecular complexes are limited or at least restricted at some point by their computational demands. Recent developments in information technology such as multicore, parallel and GPU processing can be used to overcome these limitations. In particular, graphics processing units (GPUs), which were originally developed for rendering real-time effects in computer games, are now ubiquitous and provide unprecedented computational power for scientific applications. Each parallel-processing paradigm alone can improve overall performance; the increased computational performance obtained by combining all paradigms, unleashing the full power of today's technology, makes certain applications feasible that were previously virtually impossible. In this article, state-of-the-art paradigms are introduced, the tools and infrastructure needed to apply these paradigms are presented and a state-of-the-art infrastructure and solution strategy for moving scientific applications to the next generation of computer hardware is outlined.
Yu, Leiming; Nina-Paravecino, Fanny; Kaeli, David; Fang, Qianqian
2018-01-01
We present a highly scalable Monte Carlo (MC) three-dimensional photon transport simulation platform designed for heterogeneous computing systems. Through the development of a massively parallel MC algorithm using the Open Computing Language framework, this research extends our existing graphics processing unit (GPU)-accelerated MC technique to a highly scalable vendor-independent heterogeneous computing environment, achieving significantly improved performance and software portability. A number of parallel computing techniques are investigated to achieve portable performance over a wide range of computing hardware. Furthermore, multiple thread-level and device-level load-balancing strategies are developed to obtain efficient simulations using multiple central processing units and GPUs. (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).
Heterogeneous Hardware Parallelism Review of the IN2P3 2016 Computing School
Lafage, Vincent
2017-11-01
Parallel and hybrid Monte Carlo computation. The Monte Carlo method is the main workhorse for computation of particle physics observables. This paper provides an overview of various HPC technologies that can be used today: multicore (OpenMP, HPX), manycore (OpenCL). The rewrite of a twenty years old Fortran 77 Monte Carlo will illustrate the various programming paradigms in use beyond language implementation. The problem of parallel random number generator will be addressed. We will give a short report of the one week school dedicated to these recent approaches, that took place in École Polytechnique in May 2016.
Herrera, I.; Herrera, G. S.
2015-12-01
Most geophysical systems are macroscopic physical systems. The behavior prediction of such systems is carried out by means of computational models whose basic models are partial differential equations (PDEs) [1]. Due to the enormous size of the discretized version of such PDEs it is necessary to apply highly parallelized super-computers. For them, at present, the most efficient software is based on non-overlapping domain decomposition methods (DDM). However, a limiting feature of the present state-of-the-art techniques is due to the kind of discretizations used in them. Recently, I. Herrera and co-workers using 'non-overlapping discretizations' have produced the DVS-Software which overcomes this limitation [2]. The DVS-software can be applied to a great variety of geophysical problems and achieves very high parallel efficiencies (90%, or so [3]). It is therefore very suitable for effectively applying the most advanced parallel supercomputers available at present. In a parallel talk, in this AGU Fall Meeting, Graciela Herrera Z. will present how this software is being applied to advance MOD-FLOW. Key Words: Parallel Software for Geophysics, High Performance Computing, HPC, Parallel Computing, Domain Decomposition Methods (DDM)REFERENCES [1]. Herrera Ismael and George F. Pinder, Mathematical Modelling in Science and Engineering: An axiomatic approach", John Wiley, 243p., 2012. [2]. Herrera, I., de la Cruz L.M. and Rosas-Medina A. "Non Overlapping Discretization Methods for Partial, Differential Equations". NUMER METH PART D E, 30: 1427-1454, 2014, DOI 10.1002/num 21852. (Open source) [3]. Herrera, I., & Contreras Iván "An Innovative Tool for Effectively Applying Highly Parallelized Software To Problems of Elasticity". Geofísica Internacional, 2015 (In press)
Tanikawa, Ataru; Yoshikawa, Kohji; Okamoto, Takashi; Nitadori, Keigo
2012-02-01
We present a high-performance N-body code for self-gravitating collisional systems accelerated with the aid of a new SIMD instruction set extension of the x86 architecture: Advanced Vector eXtensions (AVX), an enhanced version of the Streaming SIMD Extensions (SSE). With one processor core of Intel Core i7-2600 processor (8 MB cache and 3.40 GHz) based on Sandy Bridge micro-architecture, we implemented a fourth-order Hermite scheme with individual timestep scheme ( Makino and Aarseth, 1992), and achieved the performance of ˜20 giga floating point number operations per second (GFLOPS) for double-precision accuracy, which is two times and five times higher than that of the previously developed code implemented with the SSE instructions ( Nitadori et al., 2006b), and that of a code implemented without any explicit use of SIMD instructions with the same processor core, respectively. We have parallelized the code by using so-called NINJA scheme ( Nitadori et al., 2006a), and achieved ˜90 GFLOPS for a system containing more than N = 8192 particles with 8 MPI processes on four cores. We expect to achieve about 10 tera FLOPS (TFLOPS) for a self-gravitating collisional system with N ˜ 10 5 on massively parallel systems with at most 800 cores with Sandy Bridge micro-architecture. This performance will be comparable to that of Graphic Processing Unit (GPU) cluster systems, such as the one with about 200 Tesla C1070 GPUs ( Spurzem et al., 2010). This paper offers an alternative to collisional N-body simulations with GRAPEs and GPUs.
Application of parallel computing to seismic damage process simulation of an arch dam
International Nuclear Information System (INIS)
Zhong Hong; Lin Gao; Li Jianbo
2010-01-01
The simulation of damage process of high arch dam subjected to strong earthquake shocks is significant to the evaluation of its performance and seismic safety, considering the catastrophic effect of dam failure. However, such numerical simulation requires rigorous computational capacity. Conventional serial computing falls short of that and parallel computing is a fairly promising solution to this problem. The parallel finite element code PDPAD was developed for the damage prediction of arch dams utilizing the damage model with inheterogeneity of concrete considered. Developed with programming language Fortran, the code uses a master/slave mode for programming, domain decomposition method for allocation of tasks, MPI (Message Passing Interface) for communication and solvers from AZTEC library for solution of large-scale equations. Speedup test showed that the performance of PDPAD was quite satisfactory. The code was employed to study the damage process of a being-built arch dam on a 4-node PC Cluster, with more than one million degrees of freedom considered. The obtained damage mode was quite similar to that of shaking table test, indicating that the proposed procedure and parallel code PDPAD has a good potential in simulating seismic damage mode of arch dams. With the rapidly growing need for massive computation emerged from engineering problems, parallel computing will find more and more applications in pertinent areas.
International Nuclear Information System (INIS)
Heo, Jaeseok; Kim, Kyung Doo
2015-01-01
Highlights: • We developed an interface between an engineering simulation code and statistical analysis software. • Multiple packages of the sensitivity analysis, uncertainty quantification, and parameter estimation algorithms are implemented in the framework. • Parallel computing algorithms are also implemented in the framework to solve multiple computational problems simultaneously. - Abstract: This paper introduces a statistical data analysis toolkit, PAPIRUS, designed to perform the model calibration, uncertainty propagation, Chi-square linearity test, and sensitivity analysis for both linear and nonlinear problems. The PAPIRUS was developed by implementing multiple packages of methodologies, and building an interface between an engineering simulation code and the statistical analysis algorithms. A parallel computing framework is implemented in the PAPIRUS with multiple computing resources and proper communications between the server and the clients of each processor. It was shown that even though a large amount of data is considered for the engineering calculation, the distributions of the model parameters and the calculation results can be quantified accurately with significant reductions in computational effort. A general description about the PAPIRUS with a graphical user interface is presented in Section 2. Sections 2.1–2.5 present the methodologies of data assimilation, uncertainty propagation, Chi-square linearity test, and sensitivity analysis implemented in the toolkit with some results obtained by each module of the software. Parallel computing algorithms adopted in the framework to solve multiple computational problems simultaneously are also summarized in the paper
Energy Technology Data Exchange (ETDEWEB)
Heo, Jaeseok, E-mail: jheo@kaeri.re.kr; Kim, Kyung Doo, E-mail: kdkim@kaeri.re.kr
2015-10-15
Highlights: • We developed an interface between an engineering simulation code and statistical analysis software. • Multiple packages of the sensitivity analysis, uncertainty quantification, and parameter estimation algorithms are implemented in the framework. • Parallel computing algorithms are also implemented in the framework to solve multiple computational problems simultaneously. - Abstract: This paper introduces a statistical data analysis toolkit, PAPIRUS, designed to perform the model calibration, uncertainty propagation, Chi-square linearity test, and sensitivity analysis for both linear and nonlinear problems. The PAPIRUS was developed by implementing multiple packages of methodologies, and building an interface between an engineering simulation code and the statistical analysis algorithms. A parallel computing framework is implemented in the PAPIRUS with multiple computing resources and proper communications between the server and the clients of each processor. It was shown that even though a large amount of data is considered for the engineering calculation, the distributions of the model parameters and the calculation results can be quantified accurately with significant reductions in computational effort. A general description about the PAPIRUS with a graphical user interface is presented in Section 2. Sections 2.1–2.5 present the methodologies of data assimilation, uncertainty propagation, Chi-square linearity test, and sensitivity analysis implemented in the toolkit with some results obtained by each module of the software. Parallel computing algorithms adopted in the framework to solve multiple computational problems simultaneously are also summarized in the paper.
Parallel computing in cluster of GPU applied to a problem of nuclear engineering
International Nuclear Information System (INIS)
Moraes, Sergio Ricardo S.; Heimlich, Adino; Resende, Pedro
2013-01-01
Cluster computing has been widely used as a low cost alternative for parallel processing in scientific applications. With the use of Message-Passing Interface (MPI) protocol development became even more accessible and widespread in the scientific community. A more recent trend is the use of Graphic Processing Unit (GPU), which is a powerful co-processor able to perform hundreds of instructions in parallel, reaching a capacity of hundreds of times the processing of a CPU. However, a standard PC does not allow, in general, more than two GPUs. Hence, it is proposed in this work development and evaluation of a hybrid low cost parallel approach to the solution to a nuclear engineering typical problem. The idea is to use clusters parallelism technology (MPI) together with GPU programming techniques (CUDA - Compute Unified Device Architecture) to simulate neutron transport through a slab using Monte Carlo method. By using a cluster comprised by four quad-core computers with 2 GPU each, it has been developed programs using MPI and CUDA technologies. Experiments, applying different configurations, from 1 to 8 GPUs has been performed and results were compared with the sequential (non-parallel) version. A speed up of about 2.000 times has been observed when comparing the 8-GPU with the sequential version. Results here presented are discussed and analyzed with the objective of outlining gains and possible limitations of the proposed approach. (author)
Speed up of MCACE, a Monte Carlo code for evaluation of shielding safety, by parallel computer, (3)
International Nuclear Information System (INIS)
Takano, Makoto; Masukawa, Fumihiro; Naito, Yoshitaka; Onodera, Emi; Imawaka, Tsuneyuki; Yoda, Yoshihisa.
1993-07-01
The parallel computing of the MCACE code has been studied on two platforms; 1) Shared Memory Type Vector-Parallel Computer Monte-4 and 2) Networked Several Workstations. On the Monte-4, a disk-file has been allocated to collect all results computed by 4 CPUs in parallel, executing the copy of the MCACE code on each CPU. On the workstations under network environment, two parallel models have been evaluated; 1) a host-node model and 2) the model used on the Monte-4 where no software for parallelization has been employed but only standard FORTRAN language. The measurement of computing times has showed that speed up of about 3 times has been achieved by using 4 CPUs of the Monte-4. Further, connecting 4 workstations by network, the computing speed by parallelization has achieved faster than our scalar main frame computer, FACOM M-780. (author)
With enhanced data availability, distributed watershed models for large areas with high spatial and temporal resolution are increasingly used to understand water budgets and examine effects of human activities and climate change/variability on water resources. Developing parallel computing software...
Directory of Open Access Journals (Sweden)
Xing Cai
2005-01-01
Full Text Available This article addresses the performance of scientific applications that use the Python programming language. First, we investigate several techniques for improving the computational efficiency of serial Python codes. Then, we discuss the basic programming techniques in Python for parallelizing serial scientific applications. It is shown that an efficient implementation of the array-related operations is essential for achieving good parallel performance, as for the serial case. Once the array-related operations are efficiently implemented, probably using a mixed-language implementation, good serial and parallel performance become achievable. This is confirmed by a set of numerical experiments. Python is also shown to be well suited for writing high-level parallel programs.
Fast parallel algorithms that compute transitive closure of a fuzzy relation
Kreinovich, Vladik YA.
1993-01-01
The notion of a transitive closure of a fuzzy relation is very useful for clustering in pattern recognition, for fuzzy databases, etc. The original algorithm proposed by L. Zadeh (1971) requires the computation time O(n(sup 4)), where n is the number of elements in the relation. In 1974, J. C. Dunn proposed a O(n(sup 2)) algorithm. Since we must compute n(n-1)/2 different values s(a, b) (a not equal to b) that represent the fuzzy relation, and we need at least one computational step to compute each of these values, we cannot compute all of them in less than O(n(sup 2)) steps. So, Dunn's algorithm is in this sense optimal. For small n, it is ok. However, for big n (e.g., for big databases), it is still a lot, so it would be desirable to decrease the computation time (this problem was formulated by J. Bezdek). Since this decrease cannot be done on a sequential computer, the only way to do it is to use a computer with several processors working in parallel. We show that on a parallel computer, transitive closure can be computed in time O((log(sub 2)(n))2).
Effecting a broadcast with an allreduce operation on a parallel computer
Almasi, Gheorghe; Archer, Charles J.; Ratterman, Joseph D.; Smith, Brian E.
2010-11-02
A parallel computer comprises a plurality of compute nodes organized into at least one operational group for collective parallel operations. Each compute node is assigned a unique rank and is coupled for data communications through a global combining network. One compute node is assigned to be a logical root. A send buffer and a receive buffer is configured. Each element of a contribution of the logical root in the send buffer is contributed. One or more zeros corresponding to a size of the element are injected. An allreduce operation with a bitwise OR using the element and the injected zeros is performed. And the result for the allreduce operation is determined and stored in each receive buffer.
Parallelization of the preconditioned IDR solver for modern multicore computer systems
Bessonov, O. A.; Fedoseyev, A. I.
2012-10-01
This paper present the analysis, parallelization and optimization approach for the large sparse matrix solver CNSPACK for modern multicore microprocessors. CNSPACK is an advanced solver successfully used for coupled solution of stiff problems arising in multiphysics applications such as CFD, semiconductor transport, kinetic and quantum problems. It employs iterative IDR algorithm with ILU preconditioning (user chosen ILU preconditioning order). CNSPACK has been successfully used during last decade for solving problems in several application areas, including fluid dynamics and semiconductor device simulation. However, there was a dramatic change in processor architectures and computer system organization in recent years. Due to this, performance criteria and methods have been revisited, together with involving the parallelization of the solver and preconditioner using Open MP environment. Results of the successful implementation for efficient parallelization are presented for the most advances computer system (Intel Core i7-9xx or two-processor Xeon 55xx/56xx).
Fast parallel molecular algorithms for DNA-based computation: factoring integers.
Chang, Weng-Long; Guo, Minyi; Ho, Michael Shan-Hui
2005-06-01
The RSA public-key cryptosystem is an algorithm that converts input data to an unrecognizable encryption and converts the unrecognizable data back into its original decryption form. The security of the RSA public-key cryptosystem is based on the difficulty of factoring the product of two large prime numbers. This paper demonstrates to factor the product of two large prime numbers, and is a breakthrough in basic biological operations using a molecular computer. In order to achieve this, we propose three DNA-based algorithms for parallel subtractor, parallel comparator, and parallel modular arithmetic that formally verify our designed molecular solutions for factoring the product of two large prime numbers. Furthermore, this work indicates that the cryptosystems using public-key are perhaps insecure and also presents clear evidence of the ability of molecular computing to perform complicated mathematical operations.
A review of parallel computing for large-scale remote sensing image mosaicking
Chen, Lajiao; Ma, Yan; Liu, Peng; Wei, Jingbo; Jie, Wei; He, Jijun
2015-01-01
Interest in image mosaicking has been spurred by a wide variety of research and management needs. However, for large-scale applications, remote sensing image mosaicking usually requires significant computational capabilities. Several studies have attempted to apply parallel computing to improve image mosaicking algorithms and to speed up calculation process. The state of the art of this field has not yet been summarized, which is, however, essential for a better understanding and for further ...
Leamy, Michael J.; Springer, Adam C.
In this research we report parallel implementation of a Cellular Automata-based simulation tool for computing elastodynamic response on complex, two-dimensional domains. Elastodynamic simulation using Cellular Automata (CA) has recently been presented as an alternative, inherently object-oriented technique for accurately and efficiently computing linear and nonlinear wave propagation in arbitrarily-shaped geometries. The local, autonomous nature of the method should lead to straight-forward and efficient parallelization. We address this notion on symmetric multiprocessor (SMP) hardware using a Java-based object-oriented CA code implementing triangular state machines (i.e., automata) and the MPI bindings written in Java (MPJ Express). We use MPJ Express to reconfigure our existing CA code to distribute a domain's automata to cores present on a dual quad-core shared-memory system (eight total processors). We note that this message passing parallelization strategy is directly applicable to computer clustered computing, which will be the focus of follow-on research. Results on the shared memory platform indicate nearly-ideal, linear speed-up. We conclude that the CA-based elastodynamic simulator is easily configured to run in parallel, and yields excellent speed-up on SMP hardware.
Nugteren, C.; Corporaal, H.
2012-01-01
Multi-core and many-core were already major trends for the past six years, and are expected to continue for the next decades. With these trends of parallel computing, it becomes increasingly difficult to decide on which architecture to run a given application. In this work, we use an algorithm
Nugteren, C.; Corporaal, H.
2012-01-01
Multi-core and many-core were already major trends for the past six years and are expected to continue for the next decade. With these trends of parallel computing, it becomes increasingly difficult to decide on which processor to run a given application, mainly because the programming of these
Parallel Structures of Computer-Assisted Signature Pedagogy: The Case of Integrated Spreadsheets
Abramovich, Sergei; Easton, Jonathan; Hayes, Victoria O.
2012-01-01
This article was motivated by the authors' work on a project with a group of 2nd-grade students in a computer lab of a rural school in upstate New York. From this project, one goal of which was to provide a capstone experience for a teacher candidate in teaching application-oriented mathematics with technology, the ideas about parallel structures…
Energy Technology Data Exchange (ETDEWEB)
Koniges, A.
1996-02-09
This project is a package of 11 individual CRADA`s plus hardware. This innovative project established a three-year multi-party collaboration that is significantly accelerating the availability of commercial massively parallel processing computing software technology to U.S. government, academic, and industrial end-users. This report contains individual presentations from nine principal investigators along with overall program information.
Chen, Hsinchun; Martinez, Joanne; Kirchhoff, Amy; Ng, Tobun D.; Schatz, Bruce R.
1998-01-01
Grounded on object filtering, automatic indexing, and co-occurrence analysis, an experiment was performed using a parallel supercomputer to analyze over 400,000 abstracts in an INSPEC computer engineering collection. A user evaluation revealed that system-generated thesauri were better than the human-generated INSPEC subject thesaurus in concept…
Use of massively parallel computing to improve modelling accuracy within the nuclear sector
Directory of Open Access Journals (Sweden)
L M Evans
2016-06-01
This work presents recent advancements in three techniques: Uncertainty quantification (UQ; Cellular automata finite element (CAFE; Image based finite element methods (IBFEM. Case studies are presented demonstrating their suitability for use in nuclear engineering made possible by advancements in parallel computing hardware that is projected to be available for industry within the next decade costing of the order of $100k.
International Nuclear Information System (INIS)
Chen Jian-Lin; Li Lei; Wang Lin-Yuan; Cai Ai-Long; Xi Xiao-Qi; Zhang Han-Ming; Li Jian-Xin; Yan Bin
2015-01-01
The projection matrix model is used to describe the physical relationship between reconstructed object and projection. Such a model has a strong influence on projection and backprojection, two vital operations in iterative computed tomographic reconstruction. The distance-driven model (DDM) is a state-of-the-art technology that simulates forward and back projections. This model has a low computational complexity and a relatively high spatial resolution; however, it includes only a few methods in a parallel operation with a matched model scheme. This study introduces a fast and parallelizable algorithm to improve the traditional DDM for computing the parallel projection and backprojection operations. Our proposed model has been implemented on a GPU (graphic processing unit) platform and has achieved satisfactory computational efficiency with no approximation. The runtime for the projection and backprojection operations with our model is approximately 4.5 s and 10.5 s per loop, respectively, with an image size of 256×256×256 and 360 projections with a size of 512×512. We compare several general algorithms that have been proposed for maximizing GPU efficiency by using the unmatched projection/backprojection models in a parallel computation. The imaging resolution is not sacrificed and remains accurate during computed tomographic reconstruction. (paper)
Fast Simulation of Large-Scale Floods Based on GPU Parallel Computing
Directory of Open Access Journals (Sweden)
Qiang Liu
2018-05-01
Full Text Available Computing speed is a significant issue of large-scale flood simulations for real-time response to disaster prevention and mitigation. Even today, most of the large-scale flood simulations are generally run on supercomputers due to the massive amounts of data and computations necessary. In this work, a two-dimensional shallow water model based on an unstructured Godunov-type finite volume scheme was proposed for flood simulation. To realize a fast simulation of large-scale floods on a personal computer, a Graphics Processing Unit (GPU-based, high-performance computing method using the OpenACC application was adopted to parallelize the shallow water model. An unstructured data management method was presented to control the data transportation between the GPU and CPU (Central Processing Unit with minimum overhead, and then both computation and data were offloaded from the CPU to the GPU, which exploited the computational capability of the GPU as much as possible. The parallel model was validated using various benchmarks and real-world case studies. The results demonstrate that speed-ups of up to one order of magnitude can be achieved in comparison with the serial model. The proposed parallel model provides a fast and reliable tool with which to quickly assess flood hazards in large-scale areas and, thus, has a bright application prospect for dynamic inundation risk identification and disaster assessment.
International Nuclear Information System (INIS)
Pang, Kar Mun; Ng, Hoon Kiat; Gan, Suyin
2012-01-01
Highlights: ► A performance benchmarking exercise is conducted for diesel combustion simulations. ► The reduced chemical mechanism shows its advantages over base and skeletal models. ► High efficiency and great reduction of CPU runtime are achieved through 4-node solver. ► Increasing ISAT memory from 0.1 to 2 GB reduces the CPU runtime by almost 35%. ► Combustion and soot processes are predicted well with minimal computational cost. - Abstract: In the present study, in-cylinder diesel combustion simulation was performed with parallel processing on an Intel Xeon Quad-Core platform to allow both fluid dynamics and chemical kinetics of the surrogate diesel fuel model to be solved simultaneously on multiple processors. Here, Cartesian Z-Coordinate was selected as the most appropriate partitioning algorithm since it computationally bisects the domain such that the dynamic load associated with fuel particle tracking was evenly distributed during parallel computations. Other variables examined included number of compute nodes, chemistry sizes and in situ adaptive tabulation (ISAT) parameters. Based on the performance benchmarking test conducted, parallel configuration of 4-compute node was found to reduce the computational runtime most efficiently whereby a parallel efficiency of up to 75.4% was achieved. The simulation results also indicated that accuracy level was insensitive to the number of partitions or the partitioning algorithms. The effect of reducing the number of species on computational runtime was observed to be more significant than reducing the number of reactions. Besides, the study showed that an increase in the ISAT maximum storage of up to 2 GB reduced the computational runtime by 50%. Also, the ISAT error tolerance of 10 −3 was chosen to strike a balance between results accuracy and computational runtime. The optimised parameters in parallel processing and ISAT, as well as the use of the in-house reduced chemistry model allowed accurate
International Nuclear Information System (INIS)
Woodruff, S.B.
1992-01-01
The Transient Reactor Analysis Code (TRAC), which features a two- fluid treatment of thermal-hydraulics, is designed to model transients in water reactors and related facilities. One of the major computational costs associated with TRAC and similar codes is calculating constitutive coefficients. Although the formulations for these coefficients are local the costs are flow-regime- or data-dependent; i.e., the computations needed for a given spatial node often vary widely as a function of time. Consequently, poor load balancing will degrade efficiency on either vector or data parallel architectures when the data are organized according to spatial location. Unfortunately, a general automatic solution to the load-balancing problem associated with data-dependent computations is not yet available for massively parallel architectures. This document discusses why developers algorithms, such as a neural net representation, that do not exhibit algorithms, such as a neural net representation, that do not exhibit load-balancing problems
Just-in-Time Compilation-Inspired Methodology for Parallelization of Compute Intensive Java Code
Directory of Open Access Journals (Sweden)
GHULAM MUSTAFA
2017-01-01
Full Text Available Compute intensive programs generally consume significant fraction of execution time in a small amount of repetitive code. Such repetitive code is commonly known as hotspot code. We observed that compute intensive hotspots often possess exploitable loop level parallelism. A JIT (Just-in-Time compiler profiles a running program to identify its hotspots. Hotspots are then translated into native code, for efficient execution. Using similar approach, we propose a methodology to identify hotspots and exploit their parallelization potential on multicore systems. Proposed methodology selects and parallelizes each DOALL loop that is either contained in a hotspot method or calls a hotspot method. The methodology could be integrated in front-end of a JIT compiler to parallelize sequential code, just before native translation. However, compilation to native code is out of scope of this work. As a case study, we analyze eighteen JGF (Java Grande Forum benchmarks to determine parallelization potential of hotspots. Eight benchmarks demonstrate a speedup of up to 7.6x on an 8-core system
Just-in-time compilation-inspired methodology for parallelization of compute intensive java code
International Nuclear Information System (INIS)
Mustafa, G.; Ghani, M.U.
2017-01-01
Compute intensive programs generally consume significant fraction of execution time in a small amount of repetitive code. Such repetitive code is commonly known as hotspot code. We observed that compute intensive hotspots often possess exploitable loop level parallelism. A JIT (Just-in-Time) compiler profiles a running program to identify its hotspots. Hotspots are then translated into native code, for efficient execution. Using similar approach, we propose a methodology to identify hotspots and exploit their parallelization potential on multicore systems. Proposed methodology selects and parallelizes each DOALL loop that is either contained in a hotspot method or calls a hotspot method. The methodology could be integrated in front-end of a JIT compiler to parallelize sequential code, just before native translation. However, compilation to native code is out of scope of this work. As a case study, we analyze eighteen JGF (Java Grande Forum) benchmarks to determine parallelization potential of hotspots. Eight benchmarks demonstrate a speedup of up to 7.6x on an 8-core system. (author)
A parallel simulated annealing algorithm for standard cell placement on a hypercube computer
Jones, Mark Howard
1987-01-01
A parallel version of a simulated annealing algorithm is presented which is targeted to run on a hypercube computer. A strategy for mapping the cells in a two dimensional area of a chip onto processors in an n-dimensional hypercube is proposed such that both small and large distance moves can be applied. Two types of moves are allowed: cell exchanges and cell displacements. The computation of the cost function in parallel among all the processors in the hypercube is described along with a distributed data structure that needs to be stored in the hypercube to support parallel cost evaluation. A novel tree broadcasting strategy is used extensively in the algorithm for updating cell locations in the parallel environment. Studies on the performance of the algorithm on example industrial circuits show that it is faster and gives better final placement results than the uniprocessor simulated annealing algorithms. An improved uniprocessor algorithm is proposed which is based on the improved results obtained from parallelization of the simulated annealing algorithm.
A learnable parallel processing architecture towards unity of memory and computing.
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.
A conceptual design of multidisciplinary-integrated C.F.D. simulation on parallel computers
International Nuclear Information System (INIS)
Onishi, Ryoichi; Ohta, Takashi; Kimura, Toshiya.
1996-11-01
A design of a parallel aeroelastic code for aircraft integrated simulations is conducted. The method for integrating aerodynamics and structural dynamics software on parallel computers is devised by using the Euler/Navier-Stokes equations coupled with wing-box finite element structures. A synthesis of modern aircraft requires the optimizations of aerodynamics, structures, controls, operabilities, or other design disciplines, and the R and D efforts to implement Multidisciplinary Design Optimization environments using high performance computers are made especially among the U.S. aerospace industries. This report describes a Multiple Program Multiple Data (MPMD) parallelization of aerodynamics and structural dynamics codes with a dynamic deformation grid. A three-dimensional computation of a flowfield with dynamic deformation caused by a structural deformation is performed, and a pressure data calculated is used for a computation of the structural deformation which is input again to a fluid dynamics code. This process is repeated exchanging the computed data of pressures and deformations between flowfield grids and structural elements. It enables to simulate the structure movements which take into account of the interaction of fluid and structure. The conceptual design for achieving the aforementioned various functions is reported. Also the future extensions to incorporate control systems, which enable to simulate a realistic aircraft configuration to be a major tool for Aircraft Integrated Simulation, are investigated. (author)
A learnable parallel processing architecture towards unity of memory and computing
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.
Janetzke, D. C.; Murthy, D. V.
1991-01-01
Aeroelastic analysis is mult-disciplinary and computationally expensive. Hence, it can greatly benefit from parallel processing. As part of an effort to develop an aeroelastic analysis capability on a distributed-memory transputer network, a parallel algorithm for the computation of aerodynamic influence coefficients is implemented on a network of 32 transputers. The aerodynamic influence coefficients are calculated using a three-dimensional unsteady aerodynamic model and a panel discretization. Efficiencies up to 85 percent are demonstrated using 32 processors. The effects of subtask ordering, problem size and network topology are presented. A comparison to results on a shared-memory computer indicates that higher speedup is achieved on the distributed-memory system.
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
Treinish, Lloyd A.; Gough, Michael L.; Wildenhain, W. David
1987-01-01
The capability was developed of rapidly producing visual representations of large, complex, multi-dimensional space and earth sciences data sets via the implementation of computer graphics modeling techniques on the Massively Parallel Processor (MPP) by employing techniques recently developed for typically non-scientific applications. Such capabilities can provide a new and valuable tool for the understanding of complex scientific data, and a new application of parallel computing via the MPP. A prototype system with such capabilities was developed and integrated into the National Space Science Data Center's (NSSDC) Pilot Climate Data System (PCDS) data-independent environment for computer graphics data display to provide easy access to users. While developing these capabilities, several problems had to be solved independently of the actual use of the MPP, all of which are outlined.
3-D electromagnetic plasma particle simulations on the Intel Delta parallel computer
International Nuclear Information System (INIS)
Wang, J.; Liewer, P.C.
1994-01-01
A three-dimensional electromagnetic PIC code has been developed on the 512 node Intel Touchstone Delta MIMD parallel computer. This code is based on the General Concurrent PIC algorithm which uses a domain decomposition to divide the computation among the processors. The 3D simulation domain can be partitioned into 1-, 2-, or 3-dimensional sub-domains. Particles must be exchanged between processors as they move among the subdomains. The Intel Delta allows one to use this code for very-large-scale simulations (i.e. over 10 8 particles and 10 6 grid cells). The parallel efficiency of this code is measured, and the overall code performance on the Delta is compared with that on Cray supercomputers. It is shown that their code runs with a high parallel efficiency of ≥ 95% for large size problems. The particle push time achieved is 115 nsecs/particle/time step for 162 million particles on 512 nodes. Comparing with the performance on a single processor Cray C90, this represents a factor of 58 speedup. The code uses a finite-difference leap frog method for field solve which is significantly more efficient than fast fourier transforms on parallel computers. The performance of this code on the 128 node Cray T3D will also be discussed
SequenceL: Automated Parallel Algorithms Derived from CSP-NT Computational Laws
Cooke, Daniel; Rushton, Nelson
2013-01-01
With the introduction of new parallel architectures like the cell and multicore chips from IBM, Intel, AMD, and ARM, as well as the petascale processing available for highend computing, a larger number of programmers will need to write parallel codes. Adding the parallel control structure to the sequence, selection, and iterative control constructs increases the complexity of code development, which often results in increased development costs and decreased reliability. SequenceL is a high-level programming language that is, a programming language that is closer to a human s way of thinking than to a machine s. Historically, high-level languages have resulted in decreased development costs and increased reliability, at the expense of performance. In recent applications at JSC and in industry, SequenceL has demonstrated the usual advantages of high-level programming in terms of low cost and high reliability. SequenceL programs, however, have run at speeds typically comparable with, and in many cases faster than, their counterparts written in C and C++ when run on single-core processors. Moreover, SequenceL is able to generate parallel executables automatically for multicore hardware, gaining parallel speedups without any extra effort from the programmer beyond what is required to write the sequen tial/singlecore code. A SequenceL-to-C++ translator has been developed that automatically renders readable multithreaded C++ from a combination of a SequenceL program and sample data input. The SequenceL language is based on two fundamental computational laws, Consume-Simplify- Produce (CSP) and Normalize-Trans - pose (NT), which enable it to automate the creation of parallel algorithms from high-level code that has no annotations of parallelism whatsoever. In our anecdotal experience, SequenceL development has been in every case less costly than development of the same algorithm in sequential (that is, single-core, single process) C or C++, and an order of magnitude less
Parallel Monte Carlo simulations on an ARC-enabled computing grid
International Nuclear Information System (INIS)
Nilsen, Jon K; Samset, Bjørn H
2011-01-01
Grid computing opens new possibilities for running heavy Monte Carlo simulations of physical systems in parallel. The presentation gives an overview of GaMPI, a system for running an MPI-based random walker simulation on grid resources. Integrating the ARC middleware and the new storage system Chelonia with the Ganga grid job submission and control system, we show that MPI jobs can be run on a world-wide computing grid with good performance and promising scaling properties. Results for relatively communication-heavy Monte Carlo simulations run on multiple heterogeneous, ARC-enabled computing clusters in several countries are presented.
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
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
Parallel computations of molecular dynamics trajectories using the stochastic path approach
Zaloj, Veaceslav; Elber, Ron
2000-06-01
A novel protocol to parallelize molecular dynamics trajectories is discussed and tested on a cluster of PCs running the NT operating system. The new technique does not propagate the solution in small time steps, but uses instead a global optimization of a functional of the whole trajectory. The new approach is especially attractive for parallel and distributed computing and its advantages (and disadvantages) are presented. Two numerical examples are discussed: (a) A conformational transition in a solvated dipeptide, and (b) The R→T conformational transition in solvated hemoglobin.
Acceleration of Radiance for Lighting Simulation by Using Parallel Computing with OpenCL
Energy Technology Data Exchange (ETDEWEB)
Zuo, Wangda; McNeil, Andrew; Wetter, Michael; Lee, Eleanor
2011-09-06
We report on the acceleration of annual daylighting simulations for fenestration systems in the Radiance ray-tracing program. The algorithm was optimized to reduce both the redundant data input/output operations and the floating-point operations. To further accelerate the simulation speed, the calculation for matrix multiplications was implemented using parallel computing on a graphics processing unit. We used OpenCL, which is a cross-platform parallel programming language. Numerical experiments show that the combination of the above measures can speed up the annual daylighting simulations 101.7 times or 28.6 times when the sky vector has 146 or 2306 elements, respectively.
Application of parallel computing techniques to a large-scale reservoir simulation
International Nuclear Information System (INIS)
Zhang, Keni; Wu, Yu-Shu; Ding, Chris; Pruess, Karsten
2001-01-01
Even with the continual advances made in both computational algorithms and computer hardware used in reservoir modeling studies, large-scale simulation of fluid and heat flow in heterogeneous reservoirs remains a challenge. The problem commonly arises from intensive computational requirement for detailed modeling investigations of real-world reservoirs. This paper presents the application of a massive parallel-computing version of the TOUGH2 code developed for performing large-scale field simulations. As an application example, the parallelized TOUGH2 code is applied to develop a three-dimensional unsaturated-zone numerical model simulating flow of moisture, gas, and heat in the unsaturated zone of Yucca Mountain, Nevada, a potential repository for high-level radioactive waste. The modeling approach employs refined spatial discretization to represent the heterogeneous fractured tuffs of the system, using more than a million 3-D gridblocks. The problem of two-phase flow and heat transfer within the model domain leads to a total of 3,226,566 linear equations to be solved per Newton iteration. The simulation is conducted on a Cray T3E-900, a distributed-memory massively parallel computer. Simulation results indicate that the parallel computing technique, as implemented in the TOUGH2 code, is very efficient. The reliability and accuracy of the model results have been demonstrated by comparing them to those of small-scale (coarse-grid) models. These comparisons show that simulation results obtained with the refined grid provide more detailed predictions of the future flow conditions at the site, aiding in the assessment of proposed repository performance
Parallel Computing Characteristics of CUPID code under MPI and Hybrid environment
Energy Technology Data Exchange (ETDEWEB)
Lee, Jae Ryong; Yoon, Han Young [Korea Atomic Energy Research Institute, Daejeon (Korea, Republic of); Jeon, Byoung Jin; Choi, Hyoung Gwon [Seoul National Univ. of Science and Technology, Seoul (Korea, Republic of)
2014-05-15
In this paper, a characteristic of parallel algorithm is presented for solving an elliptic type equation of CUPID via domain decomposition method using the MPI and the parallel performance is estimated in terms of a scalability which shows the speedup ratio. In addition, the time-consuming pattern of major subroutines is studied. Two different grid systems are taken into account: 40,000 meshes for coarse system and 320,000 meshes for fine system. Since the matrix of the CUPID code differs according to whether the flow is single-phase or two-phase, the effect of matrix shape is evaluated. Finally, the effect of the preconditioner for matrix solver is also investigated. Finally, the hybrid (OpenMP+MPI) parallel algorithm is introduced and discussed in detail for solving pressure solver. Component-scale thermal-hydraulics code, CUPID has been developed for two-phase flow analysis, which adopts a three-dimensional, transient, three-field model, and parallelized to fulfill a recent demand for long-transient and highly resolved multi-phase flow behavior. In this study, the parallel performance of the CUPID code was investigated in terms of scalability. The CUPID code was parallelized with domain decomposition method. The MPI library was adopted to communicate the information at the neighboring domain. For managing the sparse matrix effectively, the CSR storage format is used. To take into account the characteristics of the pressure matrix which turns to be asymmetric for two-phase flow, both single-phase and two-phase calculations were run. In addition, the effect of the matrix size and preconditioning was also investigated. The fine mesh calculation shows better scalability than the coarse mesh because the number of coarse mesh does not need to decompose the computational domain excessively. The fine mesh can be present good scalability when dividing geometry with considering the ratio between computation and communication time. For a given mesh, single-phase flow
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).
Concurrent particle-in-cell plasma simulation on a multi-transputer parallel computer
International Nuclear Information System (INIS)
Khare, A.N.; Jethra, A.; Patel, Kartik
1992-01-01
This report describes the parallelization of a Particle-in-Cell (PIC) plasma simulation code on a multi-transputer parallel computer. The algorithm used in the parallelization of the PIC method is described. The decomposition schemes related to the distribution of the particles among the processors are discussed. The implementation of the algorithm on a transputer network connected as a torus is presented. The solutions of the problems related to global communication of data are presented in the form of a set of generalized communication functions. The performance of the program as a function of data size and the number of transputers show that the implementation is scalable and represents an effective way of achieving high performance at acceptable cost. (author). 11 refs., 4 figs., 2 tabs., appendices
7th International Workshop on Parallel Tools for High Performance Computing
Gracia, José; Nagel, Wolfgang; Resch, Michael
2014-01-01
Current advances in High Performance Computing (HPC) increasingly impact efficient software development workflows. Programmers for HPC applications need to consider trends such as increased core counts, multiple levels of parallelism, reduced memory per core, and I/O system challenges in order to derive well performing and highly scalable codes. At the same time, the increasing complexity adds further sources of program defects. While novel programming paradigms and advanced system libraries provide solutions for some of these challenges, appropriate supporting tools are indispensable. Such tools aid application developers in debugging, performance analysis, or code optimization and therefore make a major contribution to the development of robust and efficient parallel software. This book introduces a selection of the tools presented and discussed at the 7th International Parallel Tools Workshop, held in Dresden, Germany, September 3-4, 2013.
International Nuclear Information System (INIS)
Samatova, Nagiza F; Branstetter, Marcia; Ganguly, Auroop R; Hettich, Robert; Khan, Shiraj; Kora, Guruprasad; Li, Jiangtian; Ma, Xiaosong; Pan, Chongle; Shoshani, Arie; Yoginath, Srikanth
2006-01-01
Ultrascale computing and high-throughput experimental technologies have enabled the production of scientific data about complex natural phenomena. With this opportunity, comes a new problem - the massive quantities of data so produced. Answers to fundamental questions about the nature of those phenomena remain largely hidden in the produced data. The goal of this work is to provide a scalable high performance statistical data analysis framework to help scientists perform interactive analyses of these raw data to extract knowledge. Towards this goal we have been developing an open source parallel statistical analysis package, called Parallel R, that lets scientists employ a wide range of statistical analysis routines on high performance shared and distributed memory architectures without having to deal with the intricacies of parallelizing these routines
Parallel computing in experimental mechanics and optical measurement: A review (II)
Wang, Tianyi; Kemao, Qian
2018-05-01
With advantages such as non-destructiveness, high sensitivity and high accuracy, optical techniques have successfully integrated into various important physical quantities in experimental mechanics (EM) and optical measurement (OM). However, in pursuit of higher image resolutions for higher accuracy, the computation burden of optical techniques has become much heavier. Therefore, in recent years, heterogeneous platforms composing of hardware such as CPUs and GPUs, have been widely employed to accelerate these techniques due to their cost-effectiveness, short development cycle, easy portability, and high scalability. In this paper, we analyze various works by first illustrating their different architectures, followed by introducing their various parallel patterns for high speed computation. Next, we review the effects of CPU and GPU parallel computing specifically in EM & OM applications in a broad scope, which include digital image/volume correlation, fringe pattern analysis, tomography, hyperspectral imaging, computer-generated holograms, and integral imaging. In our survey, we have found that high parallelism can always be exploited in such applications for the development of high-performance systems.
International Nuclear Information System (INIS)
Kirk, B.L.; Azmy, Y.Y.
1992-01-01
In this paper the one-group, steady-state neutron diffusion equation in two-dimensional Cartesian geometry is solved using the nodal integral method. The discrete variable equations comprise loosely coupled sets of equations representing the nodal balance of neutrons, as well as neutron current continuity along rows or columns of computational cells. An iterative algorithm that is more suitable for solving large problems concurrently is derived based on the decomposition of the spatial domain and is accelerated using successive overrelaxation. This algorithm is very well suited for parallel computers, especially since the spatial domain decomposition occurs naturally, so that the number of iterations required for convergence does not depend on the number of processors participating in the calculation. Implementation of the authors' algorithm on the Intel iPSC/2 hypercube and Sequent Balance 8000 parallel computer is presented, and measured speedup and efficiency for test problems are reported. The results suggest that the efficiency of the hypercube quickly deteriorates when many processors are used, while the Sequent Balance retains very high efficiency for a comparable number of participating processors. This leads to the conjecture that message-passing parallel computers are not as well suited for this algorithm as shared-memory machines
High performance parallel computing of flows in complex geometries: I. Methods
International Nuclear Information System (INIS)
Gourdain, N; Gicquel, L; Montagnac, M; Vermorel, O; Staffelbach, G; Garcia, M; Boussuge, J-F; Gazaix, M; Poinsot, T
2009-01-01
Efficient numerical tools coupled with high-performance computers, have become a key element of the design process in the fields of energy supply and transportation. However flow phenomena that occur in complex systems such as gas turbines and aircrafts are still not understood mainly because of the models that are needed. In fact, most computational fluid dynamics (CFD) predictions as found today in industry focus on a reduced or simplified version of the real system (such as a periodic sector) and are usually solved with a steady-state assumption. This paper shows how to overcome such barriers and how such a new challenge can be addressed by developing flow solvers running on high-end computing platforms, using thousands of computing cores. Parallel strategies used by modern flow solvers are discussed with particular emphases on mesh-partitioning, load balancing and communication. Two examples are used to illustrate these concepts: a multi-block structured code and an unstructured code. Parallel computing strategies used with both flow solvers are detailed and compared. This comparison indicates that mesh-partitioning and load balancing are more straightforward with unstructured grids than with multi-block structured meshes. However, the mesh-partitioning stage can be challenging for unstructured grids, mainly due to memory limitations of the newly developed massively parallel architectures. Finally, detailed investigations show that the impact of mesh-partitioning on the numerical CFD solutions, due to rounding errors and block splitting, may be of importance and should be accurately addressed before qualifying massively parallel CFD tools for a routine industrial use.
Energy Technology Data Exchange (ETDEWEB)
Joubert, W. [Los Alamos National Lab., NM (United States); Carey, G.F. [Univ. of Texas, Austin, TX (United States)
1994-12-31
A great need exists for high performance numerical software libraries transportable across parallel machines. This talk concerns the PCG package, which solves systems of linear equations by iterative methods on parallel computers. The features of the package are discussed, as well as techniques used to obtain high performance as well as transportability across architectures. Representative numerical results are presented for several machines including the Connection Machine CM-5, Intel Paragon and Cray T3D parallel computers.
Domain decomposition parallel computing for transient two-phase flow of nuclear reactors
Energy Technology Data Exchange (ETDEWEB)
Lee, Jae Ryong; Yoon, Han Young [KAERI, Daejeon (Korea, Republic of); Choi, Hyoung Gwon [Seoul National University, Seoul (Korea, Republic of)
2016-05-15
KAERI (Korea Atomic Energy Research Institute) has been developing a multi-dimensional two-phase flow code named CUPID for multi-physics and multi-scale thermal hydraulics analysis of Light water reactors (LWRs). The CUPID code has been validated against a set of conceptual problems and experimental data. In this work, the CUPID code has been parallelized based on the domain decomposition method with Message passing interface (MPI) library. For domain decomposition, the CUPID code provides both manual and automatic methods with METIS library. For the effective memory management, the Compressed sparse row (CSR) format is adopted, which is one of the methods to represent the sparse asymmetric matrix. CSR format saves only non-zero value and its position (row and column). By performing the verification for the fundamental problem set, the parallelization of the CUPID has been successfully confirmed. Since the scalability of a parallel simulation is generally known to be better for fine mesh system, three different scales of mesh system are considered: 40000 meshes for coarse mesh system, 320000 meshes for mid-size mesh system, and 2560000 meshes for fine mesh system. In the given geometry, both single- and two-phase calculations were conducted. In addition, two types of preconditioners for a matrix solver were compared: Diagonal and incomplete LU preconditioner. In terms of enhancement of the parallel performance, the OpenMP and MPI hybrid parallel computing for a pressure solver was examined. It is revealed that the scalability of hybrid calculation was enhanced for the multi-core parallel computation.
PLAST: parallel local alignment search tool for database comparison
Directory of Open Access Journals (Sweden)
Lavenier Dominique
2009-10-01
Full Text Available Abstract Background Sequence similarity searching is an important and challenging task in molecular biology and next-generation sequencing should further strengthen the need for faster algorithms to process such vast amounts of data. At the same time, the internal architecture of current microprocessors is tending towards more parallelism, leading to the use of chips with two, four and more cores integrated on the same die. The main purpose of this work was to design an effective algorithm to fit with the parallel capabilities of modern microprocessors. Results A parallel algorithm for comparing large genomic banks and targeting middle-range computers has been developed and implemented in PLAST software. The algorithm exploits two key parallel features of existing and future microprocessors: the SIMD programming model (SSE instruction set and the multithreading concept (multicore. Compared to multithreaded BLAST software, tests performed on an 8-processor server have shown speedup ranging from 3 to 6 with a similar level of accuracy. Conclusion A parallel algorithmic approach driven by the knowledge of the internal microprocessor architecture allows significant speedup to be obtained while preserving standard sensitivity for similarity search problems.
11th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing
Barolli, Leonard; Amato, Flora
2017-01-01
P2P, Grid, Cloud and Internet computing technologies have been very fast established as breakthrough paradigms for solving complex problems by enabling aggregation and sharing of an increasing variety of distributed computational resources at large scale. The aim of this volume is to provide latest research findings, innovative research results, methods and development techniques from both theoretical and practical perspectives related to P2P, Grid, Cloud and Internet computing as well as to reveal synergies among such large scale computing paradigms. This proceedings volume presents the results of the 11th International Conference on P2P, Parallel, Grid, Cloud And Internet Computing (3PGCIC-2016), held November 5-7, 2016, at Soonchunhyang University, Asan, Korea.
A scalable approach to modeling groundwater flow on massively parallel computers
International Nuclear Information System (INIS)
Ashby, S.F.; Falgout, R.D.; Tompson, A.F.B.
1995-12-01
We describe a fully scalable approach to the simulation of groundwater flow on a hierarchy of computing platforms, ranging from workstations to massively parallel computers. Specifically, we advocate the use of scalable conceptual models in which the subsurface model is defined independently of the computational grid on which the simulation takes place. We also describe a scalable multigrid algorithm for computing the groundwater flow velocities. We axe thus able to leverage both the engineer's time spent developing the conceptual model and the computing resources used in the numerical simulation. We have successfully employed this approach at the LLNL site, where we have run simulations ranging in size from just a few thousand spatial zones (on workstations) to more than eight million spatial zones (on the CRAY T3D)-all using the same conceptual model
Computing platforms for software-defined radio
Nurmi, Jari; Isoaho, Jouni; Garzia, Fabio
2017-01-01
This book addresses Software-Defined Radio (SDR) baseband processing from the computer architecture point of view, providing a detailed exploration of different computing platforms by classifying different approaches, highlighting the common features related to SDR requirements and by showing pros and cons of the proposed solutions. Coverage includes architectures exploiting parallelism by extending single-processor environment (such as VLIW, SIMD, TTA approaches), multi-core platforms distributing the computation to either a homogeneous array or a set of specialized heterogeneous processors, and architectures exploiting fine-grained, coarse-grained, or hybrid reconfigurability. Describes a computer engineering approach to SDR baseband processing hardware; Discusses implementation of numerous compute-intensive signal processing algorithms on single and multicore platforms; Enables deep understanding of optimization techniques related to power and energy consumption of multicore platforms using several basic a...
Improvements in fast-response flood modeling: desktop parallel computing and domain tracking
Energy Technology Data Exchange (ETDEWEB)
Judi, David R [Los Alamos National Laboratory; Mcpherson, Timothy N [Los Alamos National Laboratory; Burian, Steven J [UNIV. OF UTAH
2009-01-01
It is becoming increasingly important to have the ability to accurately forecast flooding, as flooding accounts for the most losses due to natural disasters in the world and the United States. Flood inundation modeling has been dominated by one-dimensional approaches. These models are computationally efficient and are considered by many engineers to produce reasonably accurate water surface profiles. However, because the profiles estimated in these models must be superimposed on digital elevation data to create a two-dimensional map, the result may be sensitive to the ability of the elevation data to capture relevant features (e.g. dikes/levees, roads, walls, etc...). Moreover, one-dimensional models do not explicitly represent the complex flow processes present in floodplains and urban environments and because two-dimensional models based on the shallow water equations have significantly greater ability to determine flow velocity and direction, the National Research Council (NRC) has recommended that two-dimensional models be used over one-dimensional models for flood inundation studies. This paper has shown that two-dimensional flood modeling computational time can be greatly reduced through the use of Java multithreading on multi-core computers which effectively provides a means for parallel computing on a desktop computer. In addition, this paper has shown that when desktop parallel computing is coupled with a domain tracking algorithm, significant computation time can be eliminated when computations are completed only on inundated cells. The drastic reduction in computational time shown here enhances the ability of two-dimensional flood inundation models to be used as a near-real time flood forecasting tool, engineering, design tool, or planning tool. Perhaps even of greater significance, the reduction in computation time makes the incorporation of risk and uncertainty/ensemble forecasting more feasible for flood inundation modeling (NRC 2000; Sayers et al
Visual analysis of inter-process communication for large-scale parallel computing.
Muelder, Chris; Gygi, Francois; Ma, Kwan-Liu
2009-01-01
In serial computation, program profiling is often helpful for optimization of key sections of code. When moving to parallel computation, not only does the code execution need to be considered but also communication between the different processes which can induce delays that are detrimental to performance. As the number of processes increases, so does the impact of the communication delays on performance. For large-scale parallel applications, it is critical to understand how the communication impacts performance in order to make the code more efficient. There are several tools available for visualizing program execution and communications on parallel systems. These tools generally provide either views which statistically summarize the entire program execution or process-centric views. However, process-centric visualizations do not scale well as the number of processes gets very large. In particular, the most common representation of parallel processes is a Gantt char t with a row for each process. As the number of processes increases, these charts can become difficult to work with and can even exceed screen resolution. We propose a new visualization approach that affords more scalability and then demonstrate it on systems running with up to 16,384 processes.
Proceedings of the workshop on Compilation of (Symbolic) Languages for Parallel Computers
Energy Technology Data Exchange (ETDEWEB)
Foster, I.; Tick, E. (comp.)
1991-11-01
This report comprises the abstracts and papers for the talks presented at the Workshop on Compilation of (Symbolic) Languages for Parallel Computers, held October 31--November 1, 1991, in San Diego. These unreferred contributions were provided by the participants for the purpose of this workshop; many of them will be published elsewhere in peer-reviewed conferences and publications. Our goal is planning this workshop was to bring together researchers from different disciplines with common problems in compilation. In particular, we wished to encourage interaction between researchers working in compilation of symbolic languages and those working on compilation of conventional, imperative languages. The fundamental problems facing researchers interested in compilation of logic, functional, and procedural programming languages for parallel computers are essentially the same. However, differences in the basic programming paradigms have led to different communities emphasizing different species of the parallel compilation problem. For example, parallel logic and functional languages provide dataflow-like formalisms in which control dependencies are unimportant. Hence, a major focus of research in compilation has been on techniques that try to infer when sequential control flow can safely be imposed. Granularity analysis for scheduling is a related problem. The single- assignment property leads to a need for analysis of memory use in order to detect opportunities for reuse. Much of the work in each of these areas relies on the use of abstract interpretation techniques.
Computing Maximum Cardinality Matchings in Parallel on Bipartite Graphs via Tree-Grafting
International Nuclear Information System (INIS)
Azad, Ariful; Buluc, Aydn; Pothen, Alex
2016-01-01
It is difficult to obtain high performance when computing matchings on parallel processors because matching algorithms explicitly or implicitly search for paths in the graph, and when these paths become long, there is little concurrency. In spite of this limitation, we present a new algorithm and its shared-memory parallelization that achieves good performance and scalability in computing maximum cardinality matchings in bipartite graphs. This algorithm searches for augmenting paths via specialized breadth-first searches (BFS) from multiple source vertices, hence creating more parallelism than single source algorithms. Algorithms that employ multiple-source searches cannot discard a search tree once no augmenting path is discovered from the tree, unlike algorithms that rely on single-source searches. We describe a novel tree-grafting method that eliminates most of the redundant edge traversals resulting from this property of multiple-source searches. We also employ the recent direction-optimizing BFS algorithm as a subroutine to discover augmenting paths faster. Our algorithm compares favorably with the current best algorithms in terms of the number of edges traversed, the average augmenting path length, and the number of iterations. Here, we provide a proof of correctness for our algorithm. Our NUMA-aware implementation is scalable to 80 threads of an Intel multiprocessor and to 240 threads on an Intel Knights Corner coprocessor. On average, our parallel algorithm runs an order of magnitude faster than the fastest algorithms available. The performance improvement is more significant on graphs with small matching number.
The FORCE: A portable parallel programming language supporting computational structural mechanics
Jordan, Harry F.; Benten, Muhammad S.; Brehm, Juergen; Ramanan, Aruna
1989-01-01
This project supports the conversion of codes in Computational Structural Mechanics (CSM) to a parallel form which will efficiently exploit the computational power available from multiprocessors. The work is a part of a comprehensive, FORTRAN-based system to form a basis for a parallel version of the NICE/SPAR combination which will form the CSM Testbed. The software is macro-based and rests on the force methodology developed by the principal investigator in connection with an early scientific multiprocessor. Machine independence is an important characteristic of the system so that retargeting it to the Flex/32, or any other multiprocessor on which NICE/SPAR might be imnplemented, is well supported. The principal investigator has experience in producing parallel software for both full and sparse systems of linear equations using the force macros. Other researchers have used the Force in finite element programs. It has been possible to rapidly develop software which performs at maximum efficiency on a multiprocessor. The inherent machine independence of the system also means that the parallelization will not be limited to a specific multiprocessor.
Parallel discontinuous Galerkin FEM for computing hyperbolic conservation law on unstructured grids
Ma, Xinrong; Duan, Zhijian
2018-04-01
High-order resolution Discontinuous Galerkin finite element methods (DGFEM) has been known as a good method for solving Euler equations and Navier-Stokes equations on unstructured grid, but it costs too much computational resources. An efficient parallel algorithm was presented for solving the compressible Euler equations. Moreover, the multigrid strategy based on three-stage three-order TVD Runge-Kutta scheme was used in order to improve the computational efficiency of DGFEM and accelerate the convergence of the solution of unsteady compressible Euler equations. In order to make each processor maintain load balancing, the domain decomposition method was employed. Numerical experiment performed for the inviscid transonic flow fluid problems around NACA0012 airfoil and M6 wing. The results indicated that our parallel algorithm can improve acceleration and efficiency significantly, which is suitable for calculating the complex flow fluid.
Storing files in a parallel computing system using list-based index to identify replica files
Faibish, Sorin; Bent, John M.; Tzelnic, Percy; Zhang, Zhenhua; Grider, Gary
2015-07-21
Improved techniques are provided for storing files in a parallel computing system using a list-based index to identify file replicas. A file and at least one replica of the file are stored in one or more storage nodes of the parallel computing system. An index for the file comprises at least one list comprising a pointer to a storage location of the file and a storage location of the at least one replica of the file. The file comprises one or more of a complete file and one or more sub-files. The index may also comprise a checksum value for one or more of the file and the replica(s) of the file. The checksum value can be evaluated to validate the file and/or the file replica(s). A query can be processed using the list.
9th International Workshop on Parallel Tools for High Performance Computing
Hilbrich, Tobias; Niethammer, Christoph; Gracia, José; Nagel, Wolfgang; Resch, Michael
2016-01-01
High Performance Computing (HPC) remains a driver that offers huge potentials and benefits for science and society. However, a profound understanding of the computational matters and specialized software is needed to arrive at effective and efficient simulations. Dedicated software tools are important parts of the HPC software landscape, and support application developers. Even though a tool is by definition not a part of an application, but rather a supplemental piece of software, it can make a fundamental difference during the development of an application. Such tools aid application developers in the context of debugging, performance analysis, and code optimization, and therefore make a major contribution to the development of robust and efficient parallel software. This book introduces a selection of the tools presented and discussed at the 9th International Parallel Tools Workshop held in Dresden, Germany, September 2-3, 2015, which offered an established forum for discussing the latest advances in paral...
Process-Oriented Parallel Programming with an Application to Data-Intensive Computing
Givelberg, Edward
2014-01-01
We introduce process-oriented programming as a natural extension of object-oriented programming for parallel computing. It is based on the observation that every class of an object-oriented language can be instantiated as a process, accessible via a remote pointer. The introduction of process pointers requires no syntax extension, identifies processes with programming objects, and enables processes to exchange information simply by executing remote methods. Process-oriented programming is a h...
International Nuclear Information System (INIS)
Orii, Shigeo
1998-06-01
A benchmark specification for performance evaluation of parallel computers for numerical analysis is proposed. Level 1 benchmark, which is a conventional type benchmark using processing time, measures performance of computers running a code. Level 2 benchmark proposed in this report is to give the reason of the performance. As an example, scalar-parallel computer SP2 is evaluated with this benchmark specification in case of a molecular dynamics code. As a result, the main causes to suppress the parallel performance are maximum band width and start-up time of communication between nodes. Especially the start-up time is proportional not only to the number of processors but also to the number of particles. (author)
International Nuclear Information System (INIS)
Scheer, Patrick
1998-01-01
Progress in microelectronics lead to electronic circuits which are increasingly integrated, with an operating frequency and an inputs/outputs count larger than the ones supported by printed circuit board and back-plane technologies. As a result, distributed systems with several boards cannot fully exploit the performance of integrated circuits. In synchronous parallel computers, the situation is worsen since the overall system performances rely on the efficiency of electrical interconnects between the integrated circuits which include the processing elements (PE). The study of a real parallel computer named SYMPHONIE shows for instance that the system operating frequency is far smaller than the capabilities of the microelectronics technology used for the PE implementation. Optical interconnections may cancel these limitations by providing more efficient connections between the PE. Especially, free-space optical interconnections based on vertical-cavity surface-emitting lasers (VCSEL), micro-lens and PIN photodiodes are compatible with the required features of the PE communications. Zero bias modulation of VCSEL with CMOS-compatible digital signals is studied and experimentally demonstrated. A model of the propagation of truncated gaussian beams through micro-lenses is developed. It is then used to optimise the geometry of the detection areas. A dedicated mechanical system is also proposed and implemented for integrating free-space optical interconnects in a standard electronic environment, representative of the one of parallel computer systems. A specially designed demonstrator provides the experimental validation of the above physical concepts. (author) [fr
Förster, Michael
2014-01-01
Numerical programs often use parallel programming techniques such as OpenMP to compute the program's output values as efficient as possible. In addition, derivative values of these output values with respect to certain input values play a crucial role. To achieve code that computes not only the output values simultaneously but also the derivative values, this work introduces several source-to-source transformation rules. These rules are based on a technique called algorithmic differentiation. The main focus of this work lies on the important reverse mode of algorithmic differentiation. The inh
Parallel, distributed and GPU computing technologies in single-particle electron microscopy
International Nuclear Information System (INIS)
Schmeisser, Martin; Heisen, Burkhard C.; Luettich, Mario; Busche, Boris; Hauer, Florian; Koske, Tobias; Knauber, Karl-Heinz; Stark, Holger
2009-01-01
An introduction to the current paradigm shift towards concurrency in software. Most known methods for the determination of the structure of macromolecular complexes are limited or at least restricted at some point by their computational demands. Recent developments in information technology such as multicore, parallel and GPU processing can be used to overcome these limitations. In particular, graphics processing units (GPUs), which were originally developed for rendering real-time effects in computer games, are now ubiquitous and provide unprecedented computational power for scientific applications. Each parallel-processing paradigm alone can improve overall performance; the increased computational performance obtained by combining all paradigms, unleashing the full power of today’s technology, makes certain applications feasible that were previously virtually impossible. In this article, state-of-the-art paradigms are introduced, the tools and infrastructure needed to apply these paradigms are presented and a state-of-the-art infrastructure and solution strategy for moving scientific applications to the next generation of computer hardware is outlined
International Nuclear Information System (INIS)
Yamada, Susumu; Igarashi, Ryo; Machida, Masahiko; Imamura, Toshiyuki; Okumura, Masahiko; Onishi, Hiroaki
2010-01-01
We parallelize the density matrix renormalization group (DMRG) method, which is a ground-state solver for one-dimensional quantum lattice systems. The parallelization allows us to extend the applicable range of the DMRG to n-leg ladders i.e., quasi two-dimension cases. Such an extension is regarded to bring about several breakthroughs in e.g., quantum-physics, chemistry, and nano-engineering. However, the straightforward parallelization requires all-to-all communications between all processes which are unsuitable for multi-core systems, which is a mainstream of current parallel computers. Therefore, we optimize the all-to-all communications by the following two steps. The first one is the elimination of the communications between all processes by only rearranging data distribution with the communication data amount kept. The second one is the avoidance of the communication conflict by rescheduling the calculation and the communication. We evaluate the performance of the DMRG method on multi-core supercomputers and confirm that our two-steps tuning is quite effective. (author)
Accelerating Dust Storm Simulation by Balancing Task Allocation in Parallel Computing Environment
Gui, Z.; Yang, C.; XIA, J.; Huang, Q.; YU, M.
2013-12-01
Dust storm has serious negative impacts on environment, human health, and assets. The continuing global climate change has increased the frequency and intensity of dust storm in the past decades. To better understand and predict the distribution, intensity and structure of dust storm, a series of dust storm models have been developed, such as Dust Regional Atmospheric Model (DREAM), the NMM meteorological module (NMM-dust) and Chinese Unified Atmospheric Chemistry Environment for Dust (CUACE/Dust). The developments and applications of these models have contributed significantly to both scientific research and our daily life. However, dust storm simulation is a data and computing intensive process. Normally, a simulation for a single dust storm event may take several days or hours to run. It seriously impacts the timeliness of prediction and potential applications. To speed up the process, high performance computing is widely adopted. By partitioning a large study area into small subdomains according to their geographic location and executing them on different computing nodes in a parallel fashion, the computing performance can be significantly improved. Since spatiotemporal correlations exist in the geophysical process of dust storm simulation, each subdomain allocated to a node need to communicate with other geographically adjacent subdomains to exchange data. Inappropriate allocations may introduce imbalance task loads and unnecessary communications among computing nodes. Therefore, task allocation method is the key factor, which may impact the feasibility of the paralleling. The allocation algorithm needs to carefully leverage the computing cost and communication cost for each computing node to minimize total execution time and reduce overall communication cost for the entire system. This presentation introduces two algorithms for such allocation and compares them with evenly distributed allocation method. Specifically, 1) In order to get optimized solutions, a
Leidi, Tiziano; Scocchi, Giulio; Grossi, Loris; Pusterla, Simone; D'Angelo, Claudio; Thiran, Jean-Philippe; Ortona, Alberto
2012-11-01
In recent decades, finite element (FE) techniques have been extensively used for predicting effective properties of random heterogeneous materials. In the case of very complex microstructures, the choice of numerical methods for the solution of this problem can offer some advantages over classical analytical approaches, and it allows the use of digital images obtained from real material samples (e.g., using computed tomography). On the other hand, having a large number of elements is often necessary for properly describing complex microstructures, ultimately leading to extremely time-consuming computations and high memory requirements. With the final objective of reducing these limitations, we improved an existing freely available FE code for the computation of effective conductivity (electrical and thermal) of microstructure digital models. To allow execution on hardware combining multi-core CPUs and a GPU, we first translated the original algorithm from Fortran to C, and we subdivided it into software components. Then, we enhanced the C version of the algorithm for parallel processing with heterogeneous processors. With the goal of maximizing the obtained performances and limiting resource consumption, we utilized a software architecture based on stream processing, event-driven scheduling, and dynamic load balancing. The parallel processing version of the algorithm has been validated using a simple microstructure consisting of a single sphere located at the centre of a cubic box, yielding consistent results. Finally, the code was used for the calculation of the effective thermal conductivity of a digital model of a real sample (a ceramic foam obtained using X-ray computed tomography). On a computer equipped with dual hexa-core Intel Xeon X5670 processors and an NVIDIA Tesla C2050, the parallel application version features near to linear speed-up progression when using only the CPU cores. It executes more than 20 times faster when additionally using the GPU.
QDP++: Data Parallel Interface for QCD
Energy Technology Data Exchange (ETDEWEB)
Robert Edwards
2003-03-01
This is a user's guide for the C++ binding for the QDP Data Parallel Applications Programmer Interface developed under the auspices of the US Department of Energy Scientific Discovery through Advanced Computing (SciDAC) program. The QDP Level 2 API has the following features: (1) Provides data parallel operations (logically SIMD) on all sites across the lattice or subsets of these sites. (2) Operates on lattice objects, which have an implementation-dependent data layout that is not visible above this API. (3) Hides details of how the implementation maps onto a given architecture, namely how the logical problem grid (i.el lattice) is mapped onto the machine architecture. (4) Allows asynchronous (non-blocking) shifts of lattice level objects over any permutation map of site sonto sites. However, from the user's view these instructions appear blocking and in fact may be so in some implementation. (5) Provides broadcast operations (filling a lattice quantity from a scalar value(s)), global reduction operations, and lattice-wide operations on various data-type primitives, such as matrices, vectors, and tensor products of matrices (propagators). (6) Operator syntax that support complex expression constructions.
Energy Technology Data Exchange (ETDEWEB)
Pinchedez, K
1999-06-01
Parallel computing meets the ever-increasing requirements for neutronic computer code speed and accuracy. In this work, two different approaches have been considered. We first parallelized the sequential algorithm used by the neutronics code CRONOS developed at the French Atomic Energy Commission. The algorithm computes the dominant eigenvalue associated with PN simplified transport equations by a mixed finite element method. Several parallel algorithms have been developed on distributed memory machines. The performances of the parallel algorithms have been studied experimentally by implementation on a T3D Cray and theoretically by complexity models. A comparison of various parallel algorithms has confirmed the chosen implementations. We next applied a domain sub-division technique to the two-group diffusion Eigen problem. In the modal synthesis-based method, the global spectrum is determined from the partial spectra associated with sub-domains. Then the Eigen problem is expanded on a family composed, on the one hand, from eigenfunctions associated with the sub-domains and, on the other hand, from functions corresponding to the contribution from the interface between the sub-domains. For a 2-D homogeneous core, this modal method has been validated and its accuracy has been measured. (author)
Kumar, Sameer
2010-06-15
Disclosed is a mechanism on receiving processors in a parallel computing system for providing order to data packets received from a broadcast call and to distinguish data packets received at nodes from several incoming asynchronous broadcast messages where header space is limited. In the present invention, processors at lower leafs of a tree do not need to obtain a broadcast message by directly accessing the data in a root processor's buffer. Instead, each subsequent intermediate node's rank id information is squeezed into the software header of packet headers. In turn, the entire broadcast message is not transferred from the root processor to each processor in a communicator but instead is replicated on several intermediate nodes which then replicated the message to nodes in lower leafs. Hence, the intermediate compute nodes become "virtual root compute nodes" for the purpose of replicating the broadcast message to lower levels of a tree.
Reactive wavepacket dynamics for four atom systems on scalable parallel computers
International Nuclear Information System (INIS)
Goldfield, E.M.
1994-01-01
While time-dependent quantum mechanics has been successfully applied to many three atom systems, it was nevertheless a computational challenge to use wavepacket methods to study four atom systems, systems with several heavy atoms, and systems with deep potential wells. S.K. Gray and the author are studying the reaction of OH + CO ↔ (HOCO) ↔ H + CO 2 , a difficult reaction by all the above criteria. Memory considerations alone made it impossible to use a single IBM RS/6000 workstation to study a four degree-of-freedom model of this system. They have developed a scalable parallel wavepacket code for the IBM SP1 and have run it on the SP1 at Argonne and at the Cornell Theory Center. The wavepacket, defined on a four dimensional grid, is spread out among the processors. Two-dimensional FFT's are used to compute the kinetic energy operator acting on the wavepacket. Accomplishing this task, which is the computationally intensive part of the calculation, requires a global transpose of the data. This transpose is the only serious communication between processors. Since the problem is essentially data-parallel, communication is regular and load-balancing is excellent. But as the problem is moderately fine-grained and messages are long, the ratio of communication to computation is somewhat high and they typically get about 55% of ideal speed-up
Near real-time digital holographic microscope based on GPU parallel computing
Zhu, Gang; Zhao, Zhixiong; Wang, Huarui; Yang, Yan
2018-01-01
A transmission near real-time digital holographic microscope with in-line and off-axis light path is presented, in which the parallel computing technology based on compute unified device architecture (CUDA) and digital holographic microscopy are combined. Compared to other holographic microscopes, which have to implement reconstruction in multiple focal planes and are time-consuming the reconstruction speed of the near real-time digital holographic microscope can be greatly improved with the parallel computing technology based on CUDA, so it is especially suitable for measurements of particle field in micrometer and nanometer scale. Simulations and experiments show that the proposed transmission digital holographic microscope can accurately measure and display the velocity of particle field in micrometer scale, and the average velocity error is lower than 10%.With the graphic processing units(GPU), the computing time of the 100 reconstruction planes(512×512 grids) is lower than 120ms, while it is 4.9s using traditional reconstruction method by CPU. The reconstruction speed has been raised by 40 times. In other words, it can handle holograms at 8.3 frames per second and the near real-time measurement and display of particle velocity field are realized. The real-time three-dimensional reconstruction of particle velocity field is expected to achieve by further optimization of software and hardware. Keywords: digital holographic microscope,
Computational cost estimates for parallel shared memory isogeometric multi-frontal solvers
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.
Computational cost estimates for parallel shared memory isogeometric multi-frontal solvers
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.
Energy-Efficient FPGA-Based Parallel Quasi-Stochastic Computing
Directory of Open Access Journals (Sweden)
Ramu Seva
2017-11-01
Full Text Available The high performance of FPGA (Field Programmable Gate Array in image processing applications is justified by its flexible reconfigurability, its inherent parallel nature and the availability of a large amount of internal memories. Lately, the Stochastic Computing (SC paradigm has been found to be significantly advantageous in certain application domains including image processing because of its lower hardware complexity and power consumption. However, its viability is deemed to be limited due to its serial bitstream processing and excessive run-time requirement for convergence. To address these issues, a novel approach is proposed in this work where an energy-efficient implementation of SC is accomplished by introducing fast-converging Quasi-Stochastic Number Generators (QSNGs and parallel stochastic bitstream processing, which are well suited to leverage FPGA’s reconfigurability and abundant internal memory resources. The proposed approach has been tested on the Virtex-4 FPGA, and results have been compared with the serial and parallel implementations of conventional stochastic computation using the well-known SC edge detection and multiplication circuits. Results prove that by using this approach, execution time, as well as the power consumption are decreased by a factor of 3.5 and 4.5 for the edge detection circuit and multiplication circuit, respectively.
International Nuclear Information System (INIS)
Woodruff, S.B.
1994-01-01
The Transient Reactor Analysis Code (TRAC), which features a two-fluid treatment of thermal-hydraulics, is designed to model transients in water reactors and related facilities. One of the major computational costs associated with TRAC and similar codes is calculating constitutive coefficients. Although the formulations for these coefficients are local, the costs are flow-regime- or data-dependent; i.e., the computations needed for a given spatial node often vary widely as a function of time. Consequently, a fixed, uniform assignment of nodes to prallel processors will result in degraded computational efficiency due to the poor load balancing. A standard method for treating data-dependent models on vector architectures has been to use gather operations (or indirect adressing) to sort the nodes into subsets that (temporarily) share a common computational model. However, this method is not effective on distributed memory data parallel architectures, where indirect adressing involves expensive communication overhead. Another serious problem with this method involves software engineering challenges in the areas of maintainability and extensibility. For example, an implementation that was hand-tuned to achieve good computational efficiency would have to be rewritten whenever the decision tree governing the sorting was modified. Using an example based on the calculation of the wall-to-liquid and wall-to-vapor heat-transfer coefficients for three nonboiling flow regimes, we describe how the use of the Fortran 90 WHERE construct and automatic inlining of functions can be used to ameliorate this problem while improving both efficiency and software engineering. Unfortunately, a general automatic solution to the load-balancing problem associated with data-dependent computations is not yet available for massively parallel architectures. We discuss why developers should either wait for such solutions or consider alternative numerical algorithms, such as a neural network
International Nuclear Information System (INIS)
Taraglio, S.; Massaioli, F.
1995-08-01
A parallel implementation of a library to build and train Multi Layer Perceptrons via the Back Propagation algorithm is presented. The target machine is the SIMD massively parallel supercomputer Quadrics. Performance measures are provided on three different machines with different number of processors, for two network examples. A sample source code is given
Energy Technology Data Exchange (ETDEWEB)
Kerr, John Patrick [Iowa State Univ., Ames, IA (United States)
1992-01-01
The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.
Massively parallel computing and the search for jets and black holes at the LHC
Energy Technology Data Exchange (ETDEWEB)
Halyo, V., E-mail: vhalyo@gmail.com; LeGresley, P.; Lujan, P.
2014-04-21
Massively parallel computing at the LHC could be the next leap necessary to reach an era of new discoveries at the LHC after the Higgs discovery. Scientific computing is a critical component of the LHC experiment, including operation, trigger, LHC computing GRID, simulation, and analysis. One way to improve the physics reach of the LHC is to take advantage of the flexibility of the trigger system by integrating coprocessors based on Graphics Processing Units (GPUs) or the Many Integrated Core (MIC) architecture into its server farm. This cutting edge technology provides not only the means to accelerate existing algorithms, but also the opportunity to develop new algorithms that select events in the trigger that previously would have evaded detection. In this paper we describe new algorithms that would allow us to select in the trigger new topological signatures that include non-prompt jet and black hole-like objects in the silicon tracker.
Discrete ordinates cross-section generation in parallel plane geometry -- 2: Computational results
International Nuclear Information System (INIS)
Yavuz, M.
1998-01-01
In Ref. 1, the author presented inverse discrete ordinates (S N ) methods for cross-section generation with an arbitrary scattering anisotropy of order L (L ≤ N - 1) in parallel plane geometry. The solution techniques depend on the S N eigensolutions. The eigensolutions are determined by the inverse simplified S N method (ISS N ), which uses the surface Green's function matrices (T and R). Inverse problems are generally designed so that experimentally measured physical quantities can be used in the formulations. In the formulations, although T and R (TR matrices) are measurable quantities, the author does not have such data to check the adequacy and accuracy of the methods. However, it is possible to compute TR matrices by S N methods. The author presents computational results and computationally observed properties
Proxy-equation paradigm: A strategy for massively parallel asynchronous computations
Mittal, Ankita; Girimaji, Sharath
2017-09-01
Massively parallel simulations of transport equation systems call for a paradigm change in algorithm development to achieve efficient scalability. Traditional approaches require time synchronization of processing elements (PEs), which severely restricts scalability. Relaxing synchronization requirement introduces error and slows down convergence. In this paper, we propose and develop a novel "proxy equation" concept for a general transport equation that (i) tolerates asynchrony with minimal added error, (ii) preserves convergence order and thus, (iii) expected to scale efficiently on massively parallel machines. The central idea is to modify a priori the transport equation at the PE boundaries to offset asynchrony errors. Proof-of-concept computations are performed using a one-dimensional advection (convection) diffusion equation. The results demonstrate the promise and advantages of the present strategy.
International Nuclear Information System (INIS)
Rios, Paulo R; Assis, Weslley L S; Ribeiro, Tatiana C S; Villa, Elena
2012-01-01
In a classical paper, Cahn derived expressions for the kinetics of transformations nucleated on random planes and lines. He used those as a model for nucleation on the boundaries, edges and vertices of a polycrystal consisting of equiaxed grains. In this paper it is demonstrated that Cahn's expression for random planes may be used in situations beyond the scope envisaged in Cahn's original paper. For instance, we derived an expression for the kinetics of transformations nucleated on random parallel planes that is identical to that formerly obtained by Cahn considering random planes. Computer simulation of transformations nucleated on random parallel planes is carried out. It is shown that there is excellent agreement between simulated results and analytical solutions. Such an agreement is to be expected if both the simulation and the analytical solution are correct. (paper)
Computational Performance of a Parallelized Three-Dimensional High-Order Spectral Element Toolbox
Bosshard, Christoph; Bouffanais, Roland; Clémençon, Christian; Deville, Michel O.; Fiétier, Nicolas; Gruber, Ralf; Kehtari, Sohrab; Keller, Vincent; Latt, Jonas
In this paper, a comprehensive performance review of an MPI-based high-order three-dimensional spectral element method C++ toolbox is presented. The focus is put on the performance evaluation of several aspects with a particular emphasis on the parallel efficiency. The performance evaluation is analyzed with help of a time prediction model based on a parameterization of the application and the hardware resources. A tailor-made CFD computation benchmark case is introduced and used to carry out this review, stressing the particular interest for clusters with up to 8192 cores. Some problems in the parallel implementation have been detected and corrected. The theoretical complexities with respect to the number of elements, to the polynomial degree, and to communication needs are correctly reproduced. It is concluded that this type of code has a nearly perfect speed up on machines with thousands of cores, and is ready to make the step to next-generation petaflop machines.
An FPGA-Based Quantum Computing Emulation Framework Based on Serial-Parallel Architecture
Directory of Open Access Journals (Sweden)
Y. H. Lee
2016-01-01
Full Text Available Hardware emulation of quantum systems can mimic more efficiently the parallel behaviour of quantum computations, thus allowing higher processing speed-up than software simulations. In this paper, an efficient hardware emulation method that employs a serial-parallel hardware architecture targeted for field programmable gate array (FPGA is proposed. Quantum Fourier transform and Grover’s search are chosen as case studies in this work since they are the core of many useful quantum algorithms. Experimental work shows that, with the proposed emulation architecture, a linear reduction in resource utilization is attained against the pipeline implementations proposed in prior works. The proposed work contributes to the formulation of a proof-of-concept baseline FPGA emulation framework with optimization on datapath designs that can be extended to emulate practical large-scale quantum circuits.
High performance parallel computing of flows in complex geometries: II. Applications
International Nuclear Information System (INIS)
Gourdain, N; Gicquel, L; Staffelbach, G; Vermorel, O; Duchaine, F; Boussuge, J-F; Poinsot, T
2009-01-01
Present regulations in terms of pollutant emissions, noise and economical constraints, require new approaches and designs in the fields of energy supply and transportation. It is now well established that the next breakthrough will come from a better understanding of unsteady flow effects and by considering the entire system and not only isolated components. However, these aspects are still not well taken into account by the numerical approaches or understood whatever the design stage considered. The main challenge is essentially due to the computational requirements inferred by such complex systems if it is to be simulated by use of supercomputers. This paper shows how new challenges can be addressed by using parallel computing platforms for distinct elements of a more complex systems as encountered in aeronautical applications. Based on numerical simulations performed with modern aerodynamic and reactive flow solvers, this work underlines the interest of high-performance computing for solving flow in complex industrial configurations such as aircrafts, combustion chambers and turbomachines. Performance indicators related to parallel computing efficiency are presented, showing that establishing fair criterions is a difficult task for complex industrial applications. Examples of numerical simulations performed in industrial systems are also described with a particular interest for the computational time and the potential design improvements obtained with high-fidelity and multi-physics computing methods. These simulations use either unsteady Reynolds-averaged Navier-Stokes methods or large eddy simulation and deal with turbulent unsteady flows, such as coupled flow phenomena (thermo-acoustic instabilities, buffet, etc). Some examples of the difficulties with grid generation and data analysis are also presented when dealing with these complex industrial applications.
Computational cost of isogeometric multi-frontal solvers on parallel distributed memory machines
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.
Shared memory parallelism for 3D cartesian discrete ordinates solver
International Nuclear Information System (INIS)
Moustafa, S.; Dutka-Malen, I.; Plagne, L.; Poncot, A.; Ramet, P.
2013-01-01
This paper describes the design and the performance of DOMINO, a 3D Cartesian SN solver that implements two nested levels of parallelism (multi-core + SIMD - Single Instruction on Multiple Data) on shared memory computation nodes. DOMINO is written in C++, a multi-paradigm programming language that enables the use of powerful and generic parallel programming tools such as Intel TBB and Eigen. These two libraries allow us to combine multi-thread parallelism with vector operations in an efficient and yet portable way. As a result, DOMINO can exploit the full power of modern multi-core processors and is able to tackle very large simulations, that usually require large HPC clusters, using a single computing node. For example, DOMINO solves a 3D full core PWR eigenvalue problem involving 26 energy groups, 288 angular directions (S16), 46*10 6 spatial cells and 1*10 12 DoFs within 11 hours on a single 32-core SMP node. This represents a sustained performance of 235 GFlops and 40.74% of the SMP node peak performance for the DOMINO sweep implementation. The very high Flops/Watt ratio of DOMINO makes it a very interesting building block for a future many-nodes nuclear simulation tool. (authors)
Micro-mechanical Simulations of Soils using Massively Parallel Supercomputers
Directory of Open Access Journals (Sweden)
David W. Washington
2004-06-01
Full Text Available In this research a computer program, Trubal version 1.51, based on the Discrete Element Method was converted to run on a Connection Machine (CM-5,a massively parallel supercomputer with 512 nodes, to expedite the computational times of simulating Geotechnical boundary value problems. The dynamic memory algorithm in Trubal program did not perform efficiently in CM-2 machine with the Single Instruction Multiple Data (SIMD architecture. This was due to the communication overhead involving global array reductions, global array broadcast and random data movement. Therefore, a dynamic memory algorithm in Trubal program was converted to a static memory arrangement and Trubal program was successfully converted to run on CM-5 machines. The converted program was called "TRUBAL for Parallel Machines (TPM." Simulating two physical triaxial experiments and comparing simulation results with Trubal simulations validated the TPM program. With a 512 nodes CM-5 machine TPM produced a nine-fold speedup demonstrating the inherent parallelism within algorithms based on the Discrete Element Method.
Homemade Buckeye-Pi: A Learning Many-Node Platform for High-Performance Parallel Computing
Amooie, M. A.; Moortgat, J.
2017-12-01
We report on the "Buckeye-Pi" cluster, the supercomputer developed in The Ohio State University School of Earth Sciences from 128 inexpensive Raspberry Pi (RPi) 3 Model B single-board computers. Each RPi is equipped with fast Quad Core 1.2GHz ARMv8 64bit processor, 1GB of RAM, and 32GB microSD card for local storage. Therefore, the cluster has a total RAM of 128GB that is distributed on the individual nodes and a flash capacity of 4TB with 512 processors, while it benefits from low power consumption, easy portability, and low total cost. The cluster uses the Message Passing Interface protocol to manage the communications between each node. These features render our platform the most powerful RPi supercomputer to date and suitable for educational applications in high-performance-computing (HPC) and handling of large datasets. In particular, we use the Buckeye-Pi to implement optimized parallel codes in our in-house simulator for subsurface media flows with the goal of achieving a massively-parallelized scalable code. We present benchmarking results for the computational performance across various number of RPi nodes. We believe our project could inspire scientists and students to consider the proposed unconventional cluster architecture as a mainstream and a feasible learning platform for challenging engineering and scientific problems.
Paralelno umrežavanje računara / Parallel networking of the computers
Directory of Open Access Journals (Sweden)
Milojko Jevtović
2007-04-01
Full Text Available U radu je izložena originalna koncepcija tehničkog rešenja paralelnog umrežavanja računara, kao i lokalnih računarskih mreža (LAN - Local Area Network, odnosno povezivanje i istovremena komunikacija preko više različitih transportnih telekomunikacionih mreža. Opisano je jedno rešenje paralelnog umrežavanja, kojim je omogućen pouzdani prenos multimedijalnog saobraćaja i prenos podataka u realnom vremenu između računara ili LAN istovremeno preko N (N = 1, 2, 3, 4,.. različitih, međusobno nezavisnih mreža širokog prostranstva (WAN - Wide Area Network. Paralelno umrežavanje zasnovano je na korišćenju univerzalnog modema, čije je rešenje, takođe ukratko predstavljeno. / In this paper, new concept for parallel networking of the computers or LANs over different WAN telecommunications networks, is presented. One solution of the parallel networks, which enables reliable transfer of multimedia traffic and data transmission in real time between a computer of LAN via N (N = 1, 2 3, 4,… different inter-connected Wide Area Network. Connections between computers or LANs and wide area networks are realized using universal modems whose solution has also been presented.
Energy Technology Data Exchange (ETDEWEB)
Moryakov, A. V., E-mail: sailor@orc.ru [National Research Centre Kurchatov Institute (Russian Federation)
2016-12-15
An algorithm for solving the time-dependent transport equation in the P{sub m}S{sub n} group approximation with the use of parallel computations is presented. The algorithm is implemented in the LUCKY-TD code for supercomputers employing the MPI standard for the data exchange between parallel processes.
Wang, Zhaocai; Pu, Jun; Cao, Liling; Tan, Jian
2015-10-23
The unbalanced assignment problem (UAP) is to optimally resolve the problem of assigning n jobs to m individuals (m applied mathematics, having numerous real life applications. In this paper, we present a new parallel DNA algorithm for solving the unbalanced assignment problem using DNA molecular operations. We reasonably design flexible-length DNA strands representing different jobs and individuals, take appropriate steps, and get the solutions of the UAP in the proper length range and O(mn) time. We extend the application of DNA molecular operations and simultaneity to simplify the complexity of the computation.
Techniques and environments for big data analysis parallel, cloud, and grid computing
Dehuri, Satchidananda; Kim, Euiwhan; Wang, Gi-Name
2016-01-01
This volume is aiming at a wide range of readers and researchers in the area of Big Data by presenting the recent advances in the fields of Big Data Analysis, as well as the techniques and tools used to analyze it. The book includes 10 distinct chapters providing a concise introduction to Big Data Analysis and recent Techniques and Environments for Big Data Analysis. It gives insight into how the expensive fitness evaluation of evolutionary learning can play a vital role in big data analysis by adopting Parallel, Grid, and Cloud computing environments.
A result-driven minimum blocking method for PageRank parallel computing
Tao, Wan; Liu, Tao; Yu, Wei; Huang, Gan
2017-01-01
Matrix blocking is a common method for improving computational efficiency of PageRank, but the blocking rules are hard to be determined, and the following calculation is complicated. In tackling these problems, we propose a minimum blocking method driven by result needs to accomplish a parallel implementation of PageRank algorithm. The minimum blocking just stores the element which is necessary for the result matrix. In return, the following calculation becomes simple and the consumption of the I/O transmission is cut down. We do experiments on several matrixes of different data size and different sparsity degree. The results show that the proposed method has better computational efficiency than traditional blocking methods.
MOOSE: A parallel computational framework for coupled systems of nonlinear equations
International Nuclear Information System (INIS)
Gaston, Derek; Newman, Chris; Hansen, Glen; Lebrun-Grandie, Damien
2009-01-01
Systems of coupled, nonlinear partial differential equations (PDEs) often arise in simulation of nuclear processes. MOOSE: Multiphysics Object Oriented Simulation Environment, a parallel computational framework targeted at the solution of such systems, is presented. As opposed to traditional data-flow oriented computational frameworks, MOOSE is instead founded on the mathematical principle of Jacobian-free Newton-Krylov (JFNK). Utilizing the mathematical structure present in JFNK, physics expressions are modularized into 'Kernels,' allowing for rapid production of new simulation tools. In addition, systems are solved implicitly and fully coupled, employing physics-based preconditioning, which provides great flexibility even with large variance in time scales. A summary of the mathematics, an overview of the structure of MOOSE, and several representative solutions from applications built on the framework are presented.
Parallel Backprojection: A Case Study in High-Performance Reconfigurable Computing
Directory of Open Access Journals (Sweden)
Cordes Ben
2009-01-01
Full Text Available High-performance reconfigurable computing (HPRC is a novel approach to provide large-scale computing power to modern scientific applications. Using both general-purpose processors and FPGAs allows application designers to exploit fine-grained and coarse-grained parallelism, achieving high degrees of speedup. One scientific application that benefits from this technique is backprojection, an image formation algorithm that can be used as part of a synthetic aperture radar (SAR processing system. We present an implementation of backprojection for SAR on an HPRC system. Using simulated data taken at a variety of ranges, our implementation runs over 200 times faster than a similar software program, with an overall application speedup better than 50x. The backprojection application is easily parallelizable, achieving near-linear speedup when run on multiple nodes of a clustered HPRC system. The results presented can be applied to other systems and other algorithms with similar characteristics.
Parallel Backprojection: A Case Study in High-Performance Reconfigurable Computing
Directory of Open Access Journals (Sweden)
2009-03-01
Full Text Available High-performance reconfigurable computing (HPRC is a novel approach to provide large-scale computing power to modern scientific applications. Using both general-purpose processors and FPGAs allows application designers to exploit fine-grained and coarse-grained parallelism, achieving high degrees of speedup. One scientific application that benefits from this technique is backprojection, an image formation algorithm that can be used as part of a synthetic aperture radar (SAR processing system. We present an implementation of backprojection for SAR on an HPRC system. Using simulated data taken at a variety of ranges, our implementation runs over 200 times faster than a similar software program, with an overall application speedup better than 50x. The backprojection application is easily parallelizable, achieving near-linear speedup when run on multiple nodes of a clustered HPRC system. The results presented can be applied to other systems and other algorithms with similar characteristics.
CERN. Geneva
2012-01-01
With Moore's Law alive and well, more and more parallelism is introduced into all computing platforms at all levels of integration and programming to achieve higher performance and energy efficiency. Especially in the area of High-Performance Computing (HPC) users can entertain a combination of different hardware and software parallel architectures and programming environments. Those technologies range from vectorization and SIMD computation over shared memory multi-threading (e.g. OpenMP) to distributed memory message passing (e.g. MPI) on cluster systems. We will discuss HPC industry trends and Intel's approach to it from processor/system architectures and research activities to hardware and software tools technologies. This includes the recently announced new Intel(r) Many Integrated Core (MIC) architecture for highly-parallel workloads and general purpose, energy efficient TFLOPS performance, some of its architectural features and its programming environment. At the end we will have a br...
International Nuclear Information System (INIS)
Lee, Jin Pyo; Joo, Han Gyu
2010-01-01
In the thermo-fluid analysis code named CUPID, the linear system of pressure equations must be solved in each iteration step. The time for repeatedly solving the linear system can be quite significant because large sparse matrices of Rank more than 50,000 are involved and the diagonal dominance of the system is hardly hold. Therefore parallelization of the linear system solver is essential to reduce the computing time. Meanwhile, Graphics Processing Units (GPU) have been developed as highly parallel, multi-core processors for the global demand of high quality 3D graphics. If a suitable interface is provided, parallelization using GPU can be available to engineering computing. NVIDIA provides a Software Development Kit(SDK) named CUDA(Compute Unified Device Architecture) to code developers so that they can manage GPUs for parallelization using the C language. In this research, we implement parallel routines for the linear system solver using CUDA, and examine the performance of the parallelization. In the next section, we will describe the method of CUDA parallelization for the CUPID code, and then the performance of the CUDA parallelization will be discussed
Better than $1/Mflops substained: a scalable PC-based parallel computer for lattice QCD
International Nuclear Information System (INIS)
Fodor, Z.; Papp, G.
2002-02-01
We study the feasibility of a PC-based parallel computer for medium to large scale lattice QCD simulations. Our cluster built at the Eoetvoes Univ., Inst. Theor. Phys. consists of 137 Intel P4-1.7 GHz nodes with 512 MB RDRAM. The 32-bit, single precision sustained performance for dynamical QCD without communication is 1510 Mflops/node with Wilson and 970 Mflops/node with staggered fermions. This gives a total performance of 208 Gflops for Wilson and 133 Gflops for staggered QCD, respectively (for 64-bit applications the performance is approximately halved). The novel feature of our system is its communication architecture. In order to have a scalable, cost-effective machine we use Gigabit Ethernet cards for nearest-neighbor communications in a two-dimensional mesh. This type of communication is cost effective (only 30% of the hardware costs is spent on the communication). According to our benchmark measurements this type of communication results in around 40% communication time fraction for lattices upto 48 3 . 96 in full QCD simulations. The price/sustained-perfomance ratio for full QCD is better than $1/Mflops for Wilson (and around $1.5/Mflops for staggered) quarks for practically any lattice size, which can fit in our parallel computer. (orig.)
Application of the parallel processing computer to a nuclear disaster prevention support system
Energy Technology Data Exchange (ETDEWEB)
Shigehiro, Nukatsuka; Osami, Watanabe [Mitsubishi Heavy Industries, LTD (Japan)
2003-07-01
At the time of nuclear emergency, it is important to identify the type and the cause of the accident. Besides with these, it is also important to provide adequate information for the emergency response organization to support decision making by predicting and evaluating the development of the event and the influence of the release of radioactivity for the environment. Recently, a new type of nuclear disaster prevention support system called MEASURES (Multiple Radiological Emergency Assistance System for Urgent Response) was developed which provides not only the current state of the nuclear power plant and the influence of the radioactivity for the environment, but also the future prediction of the accident development. In order to provide the accurate results of these analyses quickly, MEASURES utilizes various techniques, such as multiple nesting method which narrows down the calculation area gradually, and parallel processing computer for three dimensional analyses, such as air current distribution analysis. In this paper, the outline and the feature of MEASURES are presented, especially focused on the usage of parallel processing computer for the three dimensional air current distribution analysis. (authors)
Processing optimization with parallel computing for the J-PET scanner
Directory of Open Access Journals (Sweden)
Krzemień Wojciech
2015-12-01
Full Text Available The Jagiellonian Positron Emission Tomograph (J-PET collaboration is developing a prototype time of flight (TOF-positron emission tomograph (PET detector based on long polymer scintillators. This novel approach exploits the excellent time properties of the plastic scintillators, which permit very precise time measurements. The very fast field programmable gate array (FPGA-based front-end electronics and the data acquisition system, as well as low- and high-level reconstruction algorithms were specially developed to be used with the J-PET scanner. The TOF-PET data processing and reconstruction are time and resource demanding operations, especially in the case of a large acceptance detector that works in triggerless data acquisition mode. In this article, we discuss the parallel computing methods applied to optimize the data processing for the J-PET detector. We begin with general concepts of parallel computing and then we discuss several applications of those techniques in the J-PET data processing.
A study on optimal task decomposition of networked parallel computing using PVM
International Nuclear Information System (INIS)
Seong, Kwan Jae; Kim, Han Gyoo
1998-01-01
A numerical study is performed to investigate the effect of task decomposition on networked parallel processes using Parallel Virtual Machine (PVM). In our study, a PVM program distributed over a network of workstations is used in solving a finite difference version of a one dimensional heat equation, where natural choice of PVM programming structure would be the master-slave paradigm, with the aim of finding an optimal configuration resulting in least computing time including communication overhead among machines. Given a set of PVM tasks comprised of one master and five slave programs, it is found that there exists a pseudo-optimal number of machines, which does not necessarily coincide with the number of tasks, that yields the best performance when the network is under a light usage. Increasing the number of machines beyond this optimal one does not improve computing performance since increase in communication overhead among the excess number of machines offsets the decrease in CPU time obtained by distributing the PVM tasks among these machines. However, when the network traffic is heavy, the results exhibit a more random characteristic that is explained by the random nature of data transfer time
International Nuclear Information System (INIS)
Nakamachi, Eiji
2005-01-01
A crystallographic homogenization procedure is introduced to the conventional static-explicit and dynamic-explicit finite element formulation to develop a multi scale - double scale - analysis code to predict the plastic strain induced texture evolution, yield loci and formability of sheet metal. The double-scale structure consists of a crystal aggregation - micro-structure - and a macroscopic elastic plastic continuum. At first, we measure crystal morphologies by using SEM-EBSD apparatus, and define a unit cell of micro structure, which satisfy the periodicity condition in the real scale of polycrystal. Next, this crystallographic homogenization FE code is applied to 3N pure-iron and 'Benchmark' aluminum A6022 polycrystal sheets. It reveals that the initial crystal orientation distribution - the texture - affects very much to a plastic strain induced texture and anisotropic hardening evolutions and sheet deformation. Since, the multi-scale finite element analysis requires a large computation time, a parallel computing technique by using PC cluster is developed for a quick calculation. In this parallelization scheme, a dynamic workload balancing technique is introduced for quick and efficient calculations
Application of the parallel processing computer to a nuclear disaster prevention support system
International Nuclear Information System (INIS)
Shigehiro, Nukatsuka; Osami, Watanabe
2003-01-01
At the time of nuclear emergency, it is important to identify the type and the cause of the accident. Besides with these, it is also important to provide adequate information for the emergency response organization to support decision making by predicting and evaluating the development of the event and the influence of the release of radioactivity for the environment. Recently, a new type of nuclear disaster prevention support system called MEASURES (Multiple Radiological Emergency Assistance System for Urgent Response) was developed which provides not only the current state of the nuclear power plant and the influence of the radioactivity for the environment, but also the future prediction of the accident development. In order to provide the accurate results of these analyses quickly, MEASURES utilizes various techniques, such as multiple nesting method which narrows down the calculation area gradually, and parallel processing computer for three dimensional analyses, such as air current distribution analysis. In this paper, the outline and the feature of MEASURES are presented, especially focused on the usage of parallel processing computer for the three dimensional air current distribution analysis. (authors)
Directory of Open Access Journals (Sweden)
Xiaoliang Yin
2015-03-01
Full Text Available Complex electromechanical system is usually composed of multiple components from different domains, including mechanical, electronic, hydraulic, control, and so on. Modeling and simulation for electromechanical system on a unified platform is one of the research hotspots in system engineering at present. It is also the development trend of the design for complex electromechanical system. The unified modeling techniques and tools based on Modelica language provide a satisfactory solution. To meet with the requirements of collaborative modeling, simulation, and parallel computing for complex electromechanical systems based on Modelica, a general web-based modeling and simulation prototype environment, namely, WebMWorks, is designed and implemented. Based on the rich Internet application technologies, an interactive graphic user interface for modeling and post-processing on web browser was implemented; with the collaborative design module, the environment supports top-down, concurrent modeling and team cooperation; additionally, service-oriented architecture–based architecture was applied to supply compiling and solving services which run on cloud-like servers, so the environment can manage and dispatch large-scale simulation tasks in parallel on multiple computing servers simultaneously. An engineering application about pure electric vehicle is tested on WebMWorks. The results of simulation and parametric experiment demonstrate that the tested web-based environment can effectively shorten the design cycle of the complex electromechanical system.
Larson, Jay W.
1998-01-01
Atmospheric data assimilation is a method of combining actual observations with model forecasts to produce a more accurate description of the earth system than the observations or forecast alone can provide. The output of data assimilation, sometimes called the analysis, are regular, gridded datasets of observed and unobserved variables. Analysis plays a key role in numerical weather prediction and is becoming increasingly important for climate research. These applications, and the need for timely validation of scientific enhancements to the data assimilation system pose computational demands that are best met by distributed parallel software. The mission of the NASA Data Assimilation Office (DAO) is to provide datasets for climate research and to support NASA satellite and aircraft missions. The system used to create these datasets is the Goddard Earth Observing System Data Assimilation System (GEOS DAS). The core components of the the GEOS DAS are: the GEOS General Circulation Model (GCM), the Physical-space Statistical Analysis System (PSAS), the Observer, the on-line Quality Control (QC) system, the Coupler (which feeds analysis increments back to the GCM), and an I/O package for processing the large amounts of data the system produces (which will be described in another presentation in this session). The discussion will center on the following issues: the computational complexity for the whole GEOS DAS, assessment of the performance of the individual elements of GEOS DAS, and parallelization strategy for some of the components of the system.
Large-Scale, Parallel, Multi-Sensor Atmospheric Data Fusion Using Cloud Computing
Wilson, B. D.; Manipon, G.; Hua, H.; Fetzer, E. J.
2013-12-01
NASA's Earth Observing System (EOS) is an ambitious facility for studying global climate change. The mandate now is to combine measurements from the instruments on the 'A-Train' platforms (AIRS, AMSR-E, MODIS, MISR, MLS, and CloudSat) and other Earth probes to enable large-scale studies of climate change over decades. Moving to multi-sensor, long-duration analyses of important climate variables presents serious challenges for large-scale data mining and fusion. For example, one might want to compare temperature and water vapor retrievals from one instrument (AIRS) to another (MODIS), and to a model (MERRA), stratify the comparisons using a classification of the 'cloud scenes' from CloudSat, and repeat the entire analysis over 10 years of data. To efficiently assemble such datasets, we are utilizing Elastic Computing in the Cloud and parallel map/reduce-based algorithms. However, these problems are Data Intensive computing so the data transfer times and storage costs (for caching) are key issues. SciReduce is a Hadoop-like parallel analysis system, programmed in parallel python, that is designed from the ground up for Earth science. SciReduce executes inside VMWare images and scales to any number of nodes in the Cloud. Unlike Hadoop, SciReduce operates on bundles of named numeric arrays, which can be passed in memory or serialized to disk in netCDF4 or HDF5. Figure 1 shows the architecture of the full computational system, with SciReduce at the core. Multi-year datasets are automatically 'sharded' by time and space across a cluster of nodes so that years of data (millions of files) can be processed in a massively parallel way. Input variables (arrays) are pulled on-demand into the Cloud using OPeNDAP URLs or other subsetting services, thereby minimizing the size of the cached input and intermediate datasets. We are using SciReduce to automate the production of multiple versions of a ten-year A-Train water vapor climatology under a NASA MEASURES grant. We will
Parallel computation of fluid-structural interactions using high resolution upwind schemes
Hu, Zongjun
An efficient and accurate solver is developed to simulate the non-linear fluid-structural interactions in turbomachinery flutter flows. A new low diffusion E-CUSP scheme, Zha CUSP scheme, is developed to improve the efficiency and accuracy of the inviscid flux computation. The 3D unsteady Navier-Stokes equations with the Baldwin-Lomax turbulence model are solved using the finite volume method with the dual-time stepping scheme. The linearized equations are solved with Gauss-Seidel line iterations. The parallel computation is implemented using MPI protocol. The solver is validated with 2D cases for its turbulence modeling, parallel computation and unsteady calculation. The Zha CUSP scheme is validated with 2D cases, including a supersonic flat plate boundary layer, a transonic converging-diverging nozzle and a transonic inlet diffuser. The Zha CUSP2 scheme is tested with 3D cases, including a circular-to-rectangular nozzle, a subsonic compressor cascade and a transonic channel. The Zha CUSP schemes are proved to be accurate, robust and efficient in these tests. The steady and unsteady separation flows in a 3D stationary cascade under high incidence and three inlet Mach numbers are calculated to study the steady state separation flow patterns and their unsteady oscillation characteristics. The leading edge vortex shedding is the mechanism behind the unsteady characteristics of the high incidence separated flows. The separation flow characteristics is affected by the inlet Mach number. The blade aeroelasticity of a linear cascade with forced oscillating blades is studied using parallel computation. A simplified two-passage cascade with periodic boundary condition is first calculated under a medium frequency and a low incidence. The full scale cascade with 9 blades and two end walls is then studied more extensively under three oscillation frequencies and two incidence angles. The end wall influence and the blade stability are studied and compared under different
Study on High Performance of MPI-Based Parallel FDTD from WorkStation to Super Computer Platform
Directory of Open Access Journals (Sweden)
Z. L. He
2012-01-01
Full Text Available Parallel FDTD method is applied to analyze the electromagnetic problems of the electrically large targets on super computer. It is well known that the more the number of processors the less computing time consumed. Nevertheless, with the same number of processors, computing efficiency is affected by the scheme of the MPI virtual topology. Then, the influence of different virtual topology schemes on parallel performance of parallel FDTD is studied in detail. The general rules are presented on how to obtain the highest efficiency of parallel FDTD algorithm by optimizing MPI virtual topology. To show the validity of the presented method, several numerical results are given in the later part. Various comparisons are made and some useful conclusions are summarized.
Li, Chuan; Petukh, Marharyta; Li, Lin; Alexov, Emil
2013-08-15
Due to the enormous importance of electrostatics in molecular biology, calculating the electrostatic potential and corresponding energies has become a standard computational approach for the study of biomolecules and nano-objects immersed in water and salt phase or other media. However, the electrostatics of large macromolecules and macromolecular complexes, including nano-objects, may not be obtainable via explicit methods and even the standard continuum electrostatics methods may not be applicable due to high computational time and memory requirements. Here, we report further development of the parallelization scheme reported in our previous work (Li, et al., J. Comput. Chem. 2012, 33, 1960) to include parallelization of the molecular surface and energy calculations components of the algorithm. The parallelization scheme utilizes different approaches such as space domain parallelization, algorithmic parallelization, multithreading, and task scheduling, depending on the quantity being calculated. This allows for efficient use of the computing resources of the corresponding computer cluster. The parallelization scheme is implemented in the popular software DelPhi and results in speedup of several folds. As a demonstration of the efficiency and capability of this methodology, the electrostatic potential, and electric field distributions are calculated for the bovine mitochondrial supercomplex illustrating their complex topology, which cannot be obtained by modeling the supercomplex components alone. Copyright © 2013 Wiley Periodicals, Inc.
Achieving high performance in numerical computations on RISC workstations and parallel systems
Energy Technology Data Exchange (ETDEWEB)
Goedecker, S. [Max-Planck Inst. for Solid State Research, Stuttgart (Germany); Hoisie, A. [Los Alamos National Lab., NM (United States)
1997-08-20
The nominal peak speeds of both serial and parallel computers is raising rapidly. At the same time however it is becoming increasingly difficult to get out a significant fraction of this high peak speed from modern computer architectures. In this tutorial the authors give the scientists and engineers involved in numerically demanding calculations and simulations the necessary basic knowledge to write reasonably efficient programs. The basic principles are rather simple and the possible rewards large. Writing a program by taking into account optimization techniques related to the computer architecture can significantly speedup your program, often by factors of 10--100. As such, optimizing a program can for instance be a much better solution than buying a faster computer. If a few basic optimization principles are applied during program development, the additional time needed for obtaining an efficient program is practically negligible. In-depth optimization is usually only needed for a few subroutines or kernels and the effort involved is therefore also acceptable.
A COMPUTER CLUSTER SYSTEM FOR PSEUDO-PARALLEL EXECUTION OF GEANT4 SERIAL APPLICATION
Directory of Open Access Journals (Sweden)
Memmo Federici
2013-12-01
Full Text Available Simulation of the interactions between particles and matter in studies for developing X-rays detectors generally requires very long calculation times (up to several days or weeks. These times are often a serious limitation for the success of the simulations and for the accuracy of the simulated models. One of the tools used by the scientific community to perform these simulations is Geant4 (Geometry And Tracking [2, 3]. On the best of experience in the design of the AVES cluster computing system, Federici et al. [1], the IAPS (Istituto di Astrofisica e Planetologia Spaziali INAF laboratories were able to develop a cluster computer system dedicated to Geant 4. The Cluster is easy to use and easily expandable, and thanks to the design criteria adopted it achieves an excellent compromise between performance and cost. The management software developed for the Cluster splits the single instance of simulation on the cores available, allowing the use of software written for serial computation to reach a computing speed similar to that obtainable from a native parallel software. The simulations carried out on the Cluster showed an increase in execution time by a factor of 20 to 60 compared to the times obtained with the use of a single PC of medium quality.
Energy Technology Data Exchange (ETDEWEB)
Scheins, J.J.; Garcia Lucio, L.F.; Herzog, H.; Shah, N.J. [Forschungszentrum Juelich GmbH (Germany). Inst. of Neuroscience and Medicine (INM-4)
2011-07-01
Fully 3D PET image reconstruction still remains a challenging computational task due to the tremendous number of registered Lines-of-Response. Typically, billions of geometrical weights have to be repeatedly calculated and evaluated for iterative algorithms. In this context, the reconstruction software PRESTO (PET REconstruction Software TOolkit) provides accurate geometrical weighting schemes for the forward projection and backward projection, e.g. Volume-of-Intersection, while using all measured LORs separately. PRESTO exploits redundancies to realise a strongly compressed, memory-resident system matrix. Consequently, the needed time to calculate matrix weights no longer influences the reconstruction time. Very high compression factors (>300) are achieved by using unconventional non-cartesian voxel patterns. However, in the original implementation the addressing of matrix weights, projection values and voxel values happens in disfavoured memory access patterns. This causes severe computational inefficiencies due to the limited memory bandwidth using CPUs. In this work, the image data and projection data in memory as well as the order of mathematical operations have been completely re-organised to provide an optimal merit for the Single Instruction Multiple Data (SIMD) approach. This reorganisation is directly driven by the induced symmetries of PRESTO. A global speedup factor of 15 for has been achieved for the CPU-based implementation while obtaining identical results. In addition, a GPU-based implementation using CUDA on Nvidia TESLA C1060/S1070 hardware provides another speed up factor of 4 compared to single core CPU processing. (orig.)
International Nuclear Information System (INIS)
Scheins, J.J.; Garcia Lucio, L.F.; Herzog, H.; Shah, N.J.
2011-01-01
Fully 3D PET image reconstruction still remains a challenging computational task due to the tremendous number of registered Lines-of-Response. Typically, billions of geometrical weights have to be repeatedly calculated and evaluated for iterative algorithms. In this context, the reconstruction software PRESTO (PET REconstruction Software TOolkit) provides accurate geometrical weighting schemes for the forward projection and backward projection, e.g. Volume-of-Intersection, while using all measured LORs separately. PRESTO exploits redundancies to realise a strongly compressed, memory-resident system matrix. Consequently, the needed time to calculate matrix weights no longer influences the reconstruction time. Very high compression factors (>300) are achieved by using unconventional non-cartesian voxel patterns. However, in the original implementation the addressing of matrix weights, projection values and voxel values happens in disfavoured memory access patterns. This causes severe computational inefficiencies due to the limited memory bandwidth using CPUs. In this work, the image data and projection data in memory as well as the order of mathematical operations have been completely re-organised to provide an optimal merit for the Single Instruction Multiple Data (SIMD) approach. This reorganisation is directly driven by the induced symmetries of PRESTO. A global speedup factor of 15 for has been achieved for the CPU-based implementation while obtaining identical results. In addition, a GPU-based implementation using CUDA on Nvidia TESLA C1060/S1070 hardware provides another speed up factor of 4 compared to single core CPU processing. (orig.)
Computational Fluid Dynamic Pressure Drop Estimation of Flow between Parallel Plates
Energy Technology Data Exchange (ETDEWEB)
Son, Hyung Min; Yang, Soo Hyung; Park, Jong Hark [Korea Atomic Energy Research Institute, Daejeon (Korea, Republic of)
2014-10-15
Many pool type reactors have forced downward flows inside the core during normal operation; there is a chance of flow inversion when transients occur. During this phase, the flow undergo transition between turbulent and laminar regions where drastic changes take place in terms of momentum and heat transfer, and the decrease in safety margin is usually observed. Additionally, for high Prandtl number fluids such as water, an effect of the velocity profile inside the channel on the temperature distribution is more pronounced over the low Prandtl number ones. This makes the checking of its pressure drop estimation accuracy less important, assuming the code verification is complete. With an advent of powerful computer hardware, engineering applications of computational fluid dynamics (CFD) methods have become quite common these days. Especially for a fully-turbulent and single phase convective heat transfer, the predictability of the commercial codes has matured enough so that many well-known companies adopt those to accelerate a product development cycle and to realize an increased profitability. In contrast to the above, the transition models for the CFD code are still under development, and the most of the models show limited generality and prediction accuracy. Unlike the system codes, the CFD codes estimate the pressure drop from the velocity profile which is obtained by solving momentum conservation equations, and the resulting friction factor can be a representative parameter for a constant cross section channel flow. In addition, the flow inside a rectangular channel with a high span to gap ratio can be approximated by flow inside parallel plates. The computational fluid dynamics simulation on the flow between parallel plates showed reasonable prediction capability for the laminar and the turbulent regime.
Computational experience with a parallel algorithm for tetrangle inequality bound smoothing.
Rajan, K; Deo, N
1999-09-01
Determining molecular structure from interatomic distances is an important and challenging problem. Given a molecule with n atoms, lower and upper bounds on interatomic distances can usually be obtained only for a small subset of the 2(n(n-1)) atom pairs, using NMR. Given the bounds so obtained on the distances between some of the atom pairs, it is often useful to compute tighter bounds on all the 2(n(n-1)) pairwise distances. This process is referred to as bound smoothing. The initial lower and upper bounds for the pairwise distances not measured are usually assumed to be 0 and infinity. One method for bound smoothing is to use the limits imposed by the triangle inequality. The distance bounds so obtained can often be tightened further by applying the tetrangle inequality--the limits imposed on the six pairwise distances among a set of four atoms (instead of three for the triangle inequalities). The tetrangle inequality is expressed by the Cayley-Menger determinants. For every quadruple of atoms, each pass of the tetrangle inequality bound smoothing procedure finds upper and lower limits on each of the six distances in the quadruple. Applying the tetrangle inequalities to each of the (4n) quadruples requires O(n4) time. Here, we propose a parallel algorithm for bound smoothing employing the tetrangle inequality. Each pass of our algorithm requires O(n3 log n) time on a REW PRAM (Concurrent Read Exclusive Write Parallel Random Access Machine) with O(log(n)n) processors. An implementation of this parallel algorithm on the Intel Paragon XP/S and its performance are also discussed.