A modified version of the fast parallel thinning algorithm proposed by Zhang and Suen is presented in this paper. It preserves the original merits such as the contour noise immunity and good effect in thinning crossin...
详细信息
A modified version of the fast parallel thinning algorithm proposed by Zhang and Suen is presented in this paper. It preserves the original merits such as the contour noise immunity and good effect in thinning crossing lines; and overcomes the original demerits such as the serious shrinking and line connectivity problems.
In this paper, we offer an efficient parallel algorithm for solving the NP-complete Knapsack Problem in its basic, so-called 0-1 variant. To find its exact solution, algorithms belonging to the category branch-and-bou...
详细信息
In this paper, we offer an efficient parallel algorithm for solving the NP-complete Knapsack Problem in its basic, so-called 0-1 variant. To find its exact solution, algorithms belonging to the category branch-and-bound methods have long been used. To speed up the solving with varying degrees of efficiency, various options for parallelizing computations are also used. We propose here an algorithm for solving the problem, based on the paradigm of recursive-parallel computations. We consider it suited well for problems of this kind, when it is difficult to immediately break up the computations into a sufficient number of subtasks that are comparable in complexity, since they appear dynamically at run time. We used the RPM_ParLib library, developed by the author, as the main tool to program the algorithm. This library allows us to develop effective applications for parallel computing on a local network in the .NET Framework. Such applications have the ability to generate parallel branches of computation directly during program execution and dynamically redistribute work between computing modules. Any language with support for the .NET Framework can be used as a programming language in conjunction with this library. For our experiments, we developed some C# applications using this library. The main purpose of these experiments was to study the acceleration achieved by recursive-parallel computing. A detailed description of the algorithm and its testing, as well as the results obtained, are also given in the paper.
In this paper an efficient parallel algorithm to solve a three-dimensional problem of subsidence above exploited gas reservoirs is presented. The parallel program is developed on a cluster of workstations. The paralle...
详细信息
In this paper an efficient parallel algorithm to solve a three-dimensional problem of subsidence above exploited gas reservoirs is presented. The parallel program is developed on a cluster of workstations. The parallel virtual machine (PVM) system is used to handle communications among networked workstations. The method has advantages such as numbering of the finite element mesh in an arbitrary manner, simple programming organization, smaller core requirements and computation times. An implementation of this parallel method on workstations is discussed, the speed-up and efficiency of this method being demonstrated by a numerical example. Copyright (C) 1999 John Wiley & Sons, Ltd.
A fast parallel thinning algorithm is proposed in this paper. It consists of two subiterations: one aimed at deleting the south-east boundary points and the north-west corner points while the other one is aimed at del...
详细信息
Computationally efficient evaluation of penalized estimators of multivariate exponential family distributions is sought. These distributions encompass among others Markov random fields with variates of mixed type (e.g...
详细信息
Computationally efficient evaluation of penalized estimators of multivariate exponential family distributions is sought. These distributions encompass among others Markov random fields with variates of mixed type (e.g., binary and continuous) as special case of interest. The model parameter is estimated by maximization of the pseudo-likelihood augmented with a convex penalty. The estimator is shown to be consistent. With a world of multi-core computers in mind, a computationally efficient parallel Newton-Raphson algorithm is presented for numerical evaluation of the estimator alongside conditions for its convergence. parallelization comprises the division of the parameter vector into subvectors that are estimated simultaneously and subsequently aggregated to form an estimate of the original parameter. This approach may also enable efficient numerical evaluation of other high-dimensional estimators. The performance of the proposed estimator and algorithm are evaluated and compared in a simulation study. Finally, the presented methodology is applied to data of an integrative omics study.
In this paper, we propose an algorithm for solving the maximum common subgraph problem. The sequential and parallel versions of the algorithm and their software implementation are described, and their effectiveness is...
详细信息
In this paper, we propose an algorithm for solving the maximum common subgraph problem. The sequential and parallel versions of the algorithm and their software implementation are described, and their effectiveness is experimentally studied. This problem is one of the most famous NP-complete problems. Its solution may be required when solving many practical problems related to the study of complex structures. We solve it in a formulation in which we need to find all possible isomorphisms of the found common subgraph. Due to the extremely high complexity of the problem, the desire to speed up its solution by parallelizing the algorithm is quite natural. To organize parallel computing, the RPM_ParLib library is used, which makes it possible to create parallel applications running on a local computer network under the control of the .NET Framework runtime environment. The library supports a recursive-parallel programming style and ensures efficient distribution of work and dynamic load balancing of computing modules during program execution. It can be used for applications written in any programming language supported by the .NET Framework. The purpose of the numerical experiment is to study the acceleration achieved through the recursive-parallel organization of calculations. For the experiment, a special application in C# that is designed to generate various sets of initial data with specified parameters is developed. Here, we describe the characteristics of the generated initial graph pairs and the results obtained during the experiment.
The article is devoted to the construction of a parallel algorithm for calculating plasma dynamics by a particle-in-cell method using a semi-implicit scheme that conserves energy and charge. This is a two-stage predic...
详细信息
The article is devoted to the construction of a parallel algorithm for calculating plasma dynamics by a particle-in-cell method using a semi-implicit scheme that conserves energy and charge. This is a two-stage predictor-corrector scheme. At the prediction stage a semi-implicit Lapenta-type method is used in which an energy-conserving linear current does not satisfy the local Gauss law. At the correction stage the currents, electromagnetic fields, and particle velocities are corrected so that difference laws of energy and charge conservation are satisfied exactly. This approach turns out to be efficient in modeling of multi-scale phenomena with a sufficiently large time step. However, the method is computer time-consuming, since it requires not only solving two systems of linear equations per step, but also reconstructing the entire matrix of the system. The authors have developed a matrix-operator software implementation algorithm for this scheme, which allows efficient paralleling of the calculations and using the various available libraries for work with matrices and solvers for systems of linear equations. To construct the matrix, a row-by-row storage algorithm is used with search for the elements via a hash table, which reduces the memory capacity required, the number of thread synchronizations, and can significantly speed up the calculations. This algorithm has been successfully applied in a computer code, Beren3D.
The fractional reaction-diffusion equations play an important role in dynamical systems. Indeed, it is time consuming to numerically solve differential fractional diffusion equations. In this paper, we present a paral...
详细信息
The fractional reaction-diffusion equations play an important role in dynamical systems. Indeed, it is time consuming to numerically solve differential fractional diffusion equations. In this paper, we present a parallel algorithm for the Riesz space fractional diffusion equation. The parallel algorithm, which is implemented with MPI parallel programming model, consists of three procedures: preprocessing, parallel solver and postprocessing. The parallel solver involves the parallel matrix vector multiplication and vector vector addition. As to the authors' knowledge, this is the first parallel algorithm for the Riesz space fractional reaction-diffusion equation. The experimental results show that the parallel algorithm is as accurate as the serial algorithm. The parallel algorithm on single Intel Xeon X5540 CPU runs 3.3-3.4 times faster than the serial algorithm on single CPU core. The parallel efficiency of 64 processes is up to 79.39% compared with 8 processes on a distributed memory cluster system.
The Cosmic Microwave Background (CMB) is a diffuse radiation which is contaminated by the radiation emitted by point sources. The precise knowledge of CMB fluctuations can lead to a better knowledge of the chemistry a...
详细信息
The Cosmic Microwave Background (CMB) is a diffuse radiation which is contaminated by the radiation emitted by point sources. The precise knowledge of CMB fluctuations can lead to a better knowledge of the chemistry at the early stages of the Universe. In this work, we present an efficient algorithm, with a high degree of parallelism, which can improve, from the computational point of view, the classical approaches for detecting point sources in Cosmic Microwave Background maps. High performance computing libraries and parallel computing techniques have allowed to construct a portable, fast and numerically stable algorithm. To check the performance of the new method, we have carried out several simulations resembling the observational data collected by the Low Frequency Instrument of the Planck satellite. The sources are detected in their real positions.
The simulation of biologically realistic neural networks requires the numerical solution of very large systems of differential equations. Variables within the system can be changing at rates that vary by orders of mag...
详细信息
The simulation of biologically realistic neural networks requires the numerical solution of very large systems of differential equations. Variables within the system can be changing at rates that vary by orders of magnitude, not only at different times of the solution, but at the same time in different parts of the network. Therefore, an efficient implementation must be able to vary the solution step size, and do so independently in different subsystems. A single processor algorithm is presented in which each neuron can be solved with its own step size by using a priority queue to integrate them in the correct order. But this leaves the problem of how communication and synchronisation between neurons should be managed when executing in parallel. The proposed solution uses an algorithm based on waveform relaxation, which allows groups of neurons on different processors to be solved independently and hence in parallel, for substantial parts of the computation. Realistic test problems were run on a distributed memory parallel computer and results show that speedups of 10 using 16 processors are achievable, and indicate that further speedups may be possible. (C) 2000 Elsevier Science B.V. All rights reserved.
暂无评论