检索结果-内蒙古大学图书馆

Fast reconfiguration algorithms for time, space, and wavelength dilated optical Benes networks

INTERNATIONAL JOURNAL OF parallel EMERGENT AND DISTRIBUTED SYSTEMS 2007年第1期22卷 39-58页

作者： Lu, Enyue Zheng, S. Q. Salisbury Univ Dept Math & Comp Sci Salisbury MD 21801 USA Univ Texas Dallas Dept Comp Sci Richardson TX 75083 USA

Benes networks are rearrangeable nonblocking networks and are among the most efficient switching architectures in terms of the number of 2 x 2 switching elements (SEs) used. In optical Benes networks, if two I/O connecting paths with the same (close) wavelength(s) share a common SE, crosstalk occurs. In order to reduce the crosstalk effect, three approaches, time, space and wavelength dilations have been proposed. In this paper, we present polylogarithmic-time reconfiguration algorithms for realizing any (partial) permutation in time, space and wavelength dilated optical Benes networks using a linear number of processors. Our algorithms are based on a logarithmic-time permutation decomposition algorithm and apply graph coloring techniques such as edge coloring, equitable coloring and vertex coloring.

关键词： Optical switching Crosstalk Wavelength assignment parallel algorithm Graph coloring Benes network

来源：评论

学校读者我要写书评

暂无评论

ON A UNIFIED NEIGHBOURHOOD BROADCASTING SCHEME FOR INTERCONNECTION NETWORKS

引用

parallel PROCESSING LETTERS 2007年第4期17卷 425-437页

作者： Qiu, Ke Brock Univ Dept Comp Sci St Catharines ON L2S 3A1 Canada

The neighbourhood broadcasting problem in an interconnection network is defined as sending a fixed sized message from the source node to all its neighbours in a single-port model. Previously, this problem has been studied for several interconnection networks including the hypercube and the star. The objective of such works has been to minimize the total number of steps required for the neighbourhood broadcasting algorithms. Here, we first use a general neighbourhood broadcasting scheme to develop a neighbourhood broadcasting algorithm for the star interconnection network that is asymptotically optimal, conceptually simple, and easy to implement since routing for all nodes involved is uniform. It uses the cycle structures of the star graph as well as the standard technique of recursive doubling. We then show that the scheme for the star network is general enough to be applied to a broader family of interconnection networks such as the pancake interconnection network for which no previous neighbourhood broadcasting algorithm is known, resulting in asymptotically optimal algorithms. Finally, we use this scheme to develop neighbourhood broadcasting algorithms for multiple messages for several interconnection networks.

关键词： parallel algorithm interconnection network neighbourhood broadcasting

来源：评论

学校读者我要写书评

暂无评论

A fast preprocessing algorithm for massive MODIS 1B data

A fast preprocessing algorithm for massive MODIS 1B data

引用

15th International Conference on Geoinformatics

作者： Shu, Yuanming Liu, Yongxue Duan, Zhengyu Zhang, Yu Chen, Zhenjie Nanjing Univ Sch Geog & Oceanog Sci Nanjing 210093 Peoples R China

ISBN: (纸本)9780819469120

MODIS 1B data preprocessing consists of "bowtie" effect elimination and geometric correction. The paper proposes a fast preprocessing algorithm. First, partition the input image into small sub-images without "bowtie" effect. Secondly, do geometric correction to each sub-image. Finally, mosaic each sub-image in the output coordinate system and eliminate the "bowtie" effect in the process. The proposed algorithm shows both a better geometric performance and faster preprocessing speed. For the massive MODIS 1B data preprocessing, a parallel preprocessing method based on this algorithm above is further proposed. Analysis shows that real-time preprocessing for massive MODIS 1B data can be realized by the parallel algorithm.

关键词： massive MODIS 1B data preprocessing parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Reliability-directed distributed computer-aided design system

Reliability-directed distributed computer-aided design syste...

引用

IEEE International Conference on Industrial Engineering and Engineering Management

作者： Abramov, O. V. Katueva, Y. V. Nazarov, D. A. Far Eastern Branch Russian Acad Sci Inst Automat & Control Proc Vladivostok Russia

ISBN: (纸本)9781424415281

A theoretical approach and applied techniques for designing analogous electronic devices and systems with due account of random variations in system parameters and reliability specifications are considered. The paper discusses the problem of choosing parameter nominals of electronic devices and systems for which the system survival probability or the performance assurance probability for the predetermined time period is maximized. Several algorithms for region of acceptability location, modeling and discrete optimization using parallel and distributed processing are discussed. For seeking a numerical solution of the parametric design problem a distributed computer-aided reliability-oriented design system is proposed.

关键词： parameter optimization reliability parallel algorithm distributed computer-aided design system

来源：评论

学校读者我要写书评

暂无评论

Research on GNSS receiver for spinning projectile in trajectory correction fuze

Research on GNSS receiver for spinning projectile in traject...

引用

2nd International Conference on Space Information Technology

作者： Xiao Hongbing Shen Qiang Zhao Qing Li Huquan Wang Qin Beijing Inst Technol Sch Aerosp Sci & Technol Beijing 100081 Peoples R China China Petr Pipeline Bur Langfang 065000 Hebei Peoples R China

ISBN: (纸本)9780819469601

In trajectory correction fuze of spinning projectiles, the rotating rate experienced by fuze GNSS(Global Navigation Satellite System) receiver causes it positioning inaccurately for the amplitude or phase of signal from them are modulated by rotation. With multi-antenna array, this GNSS Receiver could improve signal-to-noise and anti-interference ability of the system. In addition, the special rotation demodulation loop with three channels helped the GNSS receiver demodulate rotation-modulated signals and thus provided correct position and attitude information. Besides, the quick searching and parallel algorithm realization based on SDR and FPGA were given here. At last, the effect of magnitude and phase modulation and roll rates were simulated, and primary data were obtained. The results show that it can capture and track the rotating projectiles effectively.

关键词： GNSS receiver multi-antenna rotation demodulation spinning projectile trajectory correction fuze SDR parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

The Simulation of Dual Layer Fuel Tank During the Impact With the Ground Based on parallel Computing

引用

JOURNAL OF COMPUTATIONAL AND NONLINEAR DYNAMICS 2007年第4期2卷 366-373页

作者： Li Zheng Jin Xiang-long Chen Xiang-dong Shanghai Jiao Tong Univ Ctr High Performance Comp Shanghai 200240 Peoples R China

The crashworthiness of a dual layer fuel tank, with the outer layer made of metal and the inner layer made of woven fabric composite material, is fundamental for the survivability of air impact with the ground in emergency. In this research, the simulation of a three-dimensional dual layer fuel tank in the impact with the ground is achieved through the multimaterial arbitrary Lagrangian-Eulerian (ALE) finite element method because of its ability to control mesh geometry independently of geometry. At the same time, the naked flexible tank in the impact with the ground is simulated for the evaluation of the outer metal tank. The ALE description is adopted for the fluid domain, while for the structural domain the Lagrangian formulation is considered. The computation of the fluid-structure interaction and the impact contact between the tank and the ground are realized by the penalty-based coupling method. Then, the dynamic behaviors of the dual layer fuel tank and the naked flexible tank in the impact are analyzed. In the meantime, the parallelism of the dual layer fuel tank is discussed because the computation of the fluid-structure interaction and the impact contact is quite nine consuming. Based on domain decomposition, the recursive coordinate bisection (RCB) is improved according to the time-consuming characteristics of fluid-filled tank in the impact. The result indicates, comparing with the RCB algorithm, that the improved recursive coordinate bisection algorithm has improved the speedup and parallel efficiency

关键词： dual layer fuel tank parallel algorithm ALE finite element domain decomposition

来源：评论

学校读者我要写书评

暂无评论

FPGA Implementation of a Unidirectional Systolic Array Generator for Matrix-Vector Multiplication

FPGA Implementation of a Unidirectional Systolic Array Gener...

引用

IEEE International Conference on Signal Processing and Communications

作者： Karra, M. Ch. Bekakos, M. P. Milovanovic, I. Z. Milovanovic, E. I. Democritus Univ Thrace Lab Digital Syst Dept Elect & Comp Engn Sch Engn GR-67100 Xanthi Greece Fac Elect Engn Belgrade 18000 Serbia

ISBN: (纸本)9781424412358

Systolic arrays may prove ideal structures for the representation and the mapping of many applications concerning various numerical and non-numerical scientific applications. Especially, some formulation of Dynamic Programming (DP) - a commonly used technique for solving a wide variety of discrete optimization problems, such as scheduling, string-editing, packaging, and inventory management-can be solved in parallel on systolic arrays as matrix-vector products. Systolic arrays usually have a very high rate of I/O and are well suited for intensive parallel operations Herein is a description of the FPGA hardware implementation of a matrix-vector multiplication algorithm designed to produce a unidirectional systolic array representation.

关键词： Systolic arrays parallel algorithm Field Programmable Gate Array technology

来源：评论

学校读者我要写书评

暂无评论

Novel algorithms for quantum simulation of 3D atom-diatom reactive scattering

Novel algorithms for quantum simulation of 3<i>D</i> atom-di...

引用

International Conference on Computational Science and Its Applications (ICCSA 2007)

作者： Gevorkyan, Ashot S. Balint-Kurti, Gabriel G. Bogdanov, Alexander Nyman, Gunnar NAS Armenia Inst Informat & Automat Problems P Sevak St 1 Yerevan 375014 Armenia Univ Bristol Sch Chem Bristol BS8 1TS Avon England Inst High Performance Comp & Informat Syst St Petersburg 195251 Russia Univ Gothenburg Dept Chem SE-41296 Gothenburg Sweden

ISBN: (纸本)9783540744825

A new approach is described to the evaluation of the S-matrix in three-dimensional atom-diatom reactive quantum scattering theory. A theory based on natural collision coordinates is developed, where the reaction coordinate can be viewed as fulfilling the same role as time in a time-dependent formulation. By writing the full wavefunction in coupled-channel form it is proved that the 3D multi-channel quantum reactive scattering problem can be treated in the same way as an inelastic single-arrangement problem. In particularly in the work two type coupled-channel representations;which lead to to two different systems of coupled-channel differential equations. The first system of coupled-channel equations is solved with the help of the R-matrix propagation method yielding simultaneously the full wavefunction and all S-matrix elements without further calculation. The second one is treated similarly. In this way we avoid a great volume of grid computations for 1D Schrodinger problem. The both algorithms use the intrinsic symmetry of scattering body-system;which allows to carry out maximally effective parallel computations of 3D scattering problem.

关键词： quantum scattering S-matrix elements coupled-channel differential equations R-matrix method parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Work-efficient BSR-based parallel algorithms for some fundamental problems in graph theory

引用

JOURNAL OF SUPERCOMPUTING 2006年第1期38卷 83-107页

作者： Myoupo, Jean-Frederic Seme, David Univ Picardie LaRIA Fac Math & Informat F-80039 Amiens 1 France

This paper presents BSR-parallel algorithms for some problems in fundamental graph theory : transitive closure, connected components, spanning tree, bridges and articulation points of a graph and bipartite graph recognition. There already exist constant time algorithms to solve these problems on a mesh with reconfigurable bus system using O(N-4) processors. Here we show that these problems can be solved in constant time using only O(N-2) processors on the BSR model (N is the number of vertices of the graph G). Therefore, our algorithms are more work-efficient. These new results suggest that many other problems in graph theory can be solved in constant time using the BSR model.

关键词： broadcast CRCW PRAM parallel algorithm reduction selection graph theory transitive closure connected components spanning tree bridge articulation point bipartite graph

来源：评论

学校读者我要写书评

暂无评论

PCR algorithm for the parallel computation of the solution of a class of singular linear systems

引用

APPLIED MATHEMATICS AND COMPUTATION 2006年第1期176卷 237-244页

作者： Gu, Chao Wang, Guorong Xu, Zhaoliang Shanghai LiXIn Univ Commerce Dept Math & Stat Shanghai 201600 Peoples R China Shanghai Normal Univ Dept Math Shanghai 200234 Peoples R China Shanghai Maritime Univ Dept Basic Sci Shanghai 200135 Peoples R China

The paper presents a new highly parallel algorithm for computing the solution of a class of singular linear systems WAWx = b, b epsilon R((WA)(k2)), x epsilon R((AW)(k1)) By the algorithm the solution x = A(d), (W)b is obtained in T = m{7 + [log(2)(n)] + (1 + [log(2)(m)])(2) + [log(2)(m - r + 1)]} + [log(2)(mn)] steps with P = mn processors when n >= 2(m - 1) and with P = 2m(m - 1) processors otherwise. (c) 2005 Elsevier Inc. All rights reserved.

关键词： parallel algorithm singular linear systems W-weighted Drazin inverse index time complexity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：