检索结果-内蒙古大学图书馆

International Conference on algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI)

作者： Tian, Min Qiao, Shan Wang, Junjie Du, Wei Qilu Univ Technol Shandong Acad Sci Natl Supercomp Ctr Jinan Shandong Comp Sci Ctr Jinan Peoples R China Qilu Univ Technol Shandong Acad Sci Sch Math & Stat Jinan Peoples R China

ISBN: (数字)9781510651890

ISBN: (纸本)9781510651890;9781510651883

Solving large-scale sparse linear systems is a critical problem in scientific and engineering computing. Partial differential equations can solve problems in many fields. They can be transformed into large-scale linear systems with a series of methods, and the parallel solution of tridiagonal linear systems is one of them. The solution of linear systems is very time-consuming in most of the problems, accounting for more than half of the total time. Load balancing can reduce process time for waiting and improves computational efficiency, and it is the focus of many algorithms. The article is based on Stone's proposed recursive doubling algorithm, an improved algorithm for solving tridiagonal linear systems using the full-recursive-doubling communication model and the Mobiu transform. The improved algorithm can calculate the million-dimensional linear systems. Numerical experiments show that compared with ordinary parallel algorithms, the improved algorithm shows up to 2x improvement than the original version, and some results even show up to 3x. In addition, the load-balancing performance has been greatly improved, and the time difference of the processes is 1/7 of the original version. The improved algorithm has a good load balancing, and the running time of each process is not much different, avoiding process waiting and resource wastage.

关键词： tridiagonal linear systems parallel algorithm load balancing recursive doubling Mobius transformation

来源：评论

学校读者我要写书评

暂无评论

A novel fault-tolerant parallel algorithm

引用

7th International Symposium on Advanced parallel Processing Technologies

作者： Wang, Panfeng Du, Yunfei Fu, Hongyi Zhou, Haifang Yang, Xuejun Yang, Wenjing Natl Univ Def Technol Natl Lab Paralleling & Distributed Proc Coll Comp Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9783540768364

The mean-time-between-failure of current high-performance computer systems is much shorter than the running times of many computational applications, whereas those applications are the main workload for those systems. Currently, checkpoint/restart is the most commonly used scheme for such applications to tolerate hardware failures. But this scheme has its performance limitation when the number of processors becomes much larger. In this paper, we propose a novel fault-tolerant parallel algorithm FPAPR. First, we introduce the basic idea of FPAPR. Second, we specify the details of how to implement a FPAPR program by using two NPB kernels as examples. Third, we theoretically analyze the overhead of FPAPR, and find out that the overhead of FPAPR decreases with the increase of the number of processors. At last, the experimental results on a 512-CPU cluster show the overhead introduced by the algorithm is very small.

关键词： high-performance computing fault tolerance parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

P-MinMax: A novel parallel algorithm for mining maximal frequent itemsets

P-MinMax: A novel parallel algorithm for mining maximal freq...

引用

4th International Conference on Cybernetics and Information Technologies, Systems and Applications/5th Int Conf on Computing, Communications and Control Technologies

作者： Wang, Hui Qu, Qiang Wuhan Telecommun Acad Wuhan 430010 Peoples R China Huawei Technol Co Res Dev Ctr Shenzhen 518129 Peoples R China

ISBN: (纸本)9781934272084

Mining frequent itemsets is a crucial issue in data mining applications. The complexity of the problem has been shown as NP-hard. parallel techniques are widely used to improve the efficiency of mining algorithms. A novel and powerful parallel algorithm for mining maximal frequent itemsets, called P-MinMax, is proposed in this paper, which is based on its serial version MinMax. The new algorithm decomposes the search space by prefix-based equivalence classes, distributes work among the processors by complete inclusive relation between equivalence class gene itemsets and selectively duplicates databases in such a way that each processor can compute the frequent itemsets independently. These techniques eliminate the need for synchronization, drastically cutting down the I/O overhead. The analysis and experimental results demonstrate the superb efficiency of the approach in comparison with the previous work.

关键词： frequent itemsets parallel algorithm data mining

来源：评论

学校读者我要写书评

暂无评论

AN ITERATIVE parallel algorithm OF FINITE ELEMENT METHOD

引用

Applied Mathematics and Mechanics(English Edition) 1992年第4期13卷 305-313页

作者：胡宁张汝清 Department of Engineering Mechanics Chongqing University Chongqing

In this paper, a parallel algorithm with iterative form for solving finite element equation is presented. Based on the iterative solution of linear algebra equations, the parallel computational steps are introduced in this method. Also by using the weighted residual method and choosing the appropriate weighting functions, the finite element basic form of parallel algorithm is deduced. The program of this algorithm has been realized on the ELXSI-6400 parallel computer of Xi'an Jiaotong University. The computational results show the operational speed will be raised and the CPU time will be cut down effectively. So this method is one kind of effective parallel algorithm for solving the finite element equations of large-scale structures.

关键词： parallel algorithm finite element method iterative solution weighted residual method

来源：评论

学校读者我要写书评

暂无评论

A Fast parallel algorithm for Finding a Most Reliable Source on a General Ring-Tree Graph with Unreliable Edges

A Fast Parallel Algorithm for Finding a Most Reliable Source...

引用

5th Annual International Conference on Combinatorial Optimization and Applications (COCOA 2011)

作者： Ding, Wei Xue, Guoliang Zhejiang Water Conservancy & Hydropower Coll Hangzhou 310000 Zhejiang Peoples R China Arizona State Univ Dept Comp Sci & Engn Tempe AZ 85287 USA

ISBN: (纸本)9783642226151

Given an unreliable communication network, we aim to find a most reliable source (MRS) on the network, which maximizes the expected number of nodes that are reachable from it. Although the problem of finding an MRS on general graphs is #P-hard, it is tractable in several types of sparse graphs. The ring-tree graph is such a kind of sparse graph that not only has the capability of failure tolerance but also holds an underlying tree topology which facilitates network administration. In this paper, we are concerned with unreliable general ring-tree graphs in which each edge has an independent operational probability while all nodes are immune to failures. We first design a complementary dynamic programming algorithm and then develop a parallel algorithm based on the underlying tree for finding an MRS on the network.

关键词： Most reliable source general ring-tree graph complementary dynamic programming parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm to Compute the Transport of Suspended Particles Based on 3D Models 15th

A Parallel Algorithm to Compute the Transport of Suspended P...

引用

15th International Scientific Conference on parallel Computational Technologies (PCT)

作者： Atayan, Asya M. Kuznetsova, Inna Yu Don State Tech Univ Rostov Na Donu Russia Sirius Sci & Technol Univ Soci Russia Southern Fed Univ Rostov Na Donu Russia

ISBN: (纸本)9783030816919;9783030816902

We consider 2D and 3D models dealing with the transport of suspended particles. The approximation of 2D and 3D models that describe the transport of suspended particles is considered on the example of the two-dimensional diffusion-convection equation. We use discrete analogs of convective and diffusion transfer operators on the assumption of partial filling of cells. The geometry of the computational domain is described based on the filling function. We solve the problem of transport of suspended particles using a difference scheme that is a linear combination of the Upwind and the Standard Leapfrog difference schemes with weight coefficients obtained from the condition of minimization of the approximation error. The scheme is designed to solve the problem of transfer of impurities for large grid Peclet numbers. We have developed some parallel algorithms for the solution of this problem on multiprocessor systems with distributed memory. The results of numerical experiments give us grounds to draw conclusions about the advantages of 3D models of transport of suspended particles over 2D ones.

关键词： Model of transport of suspended particles Upwind Leapfrog scheme Partial filling of cells Three-dimensional model Convection-diffusion equation parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

A Preconditioned Two Stage Iterative parallel algorithm for Block-Tridiagonal Linear Equations

A Preconditioned Two Stage Iterative Parallel Algorithm for ...

引用

2nd International Conference on Modelling and Simulation

作者： Duan, Liu Gang Lv, Quan Yi Nie, Yu Feng NW Polytech Univ Dept Appl Math Xian Peoples R China

ISBN: (纸本)9781846260612

In the paper, the preconditioner of linear systems is directly extented to the solutions of block-tridiagonal equations. And by corresponding parallel processing, a parallel algorithm of two stage iterative method for solving block-tridiagonal linear equations is presented. According to theoretical analysis, a sufficient condition of the new algorithm convergence is given. Finally, the results of numerical experiments on HP rx2600 cluster indicate that the algorithm is feasible and effective.

关键词： Block-tridiagonal linear equations parallel algorithm HP rx2600 cluster Preconditioned Optimal parameter

来源：评论

学校读者我要写书评

暂无评论

Research on Association Rules parallel algorithm Based on FP-Growth

Research on Association Rules Parallel Algorithm Based on FP...

引用

2nd International Conference on Information Computing and Applications

作者： Chen, Ke Zhang, Lijun Li, Sansi Ke, Wende Guangdong Univ Petrochem Technol Dept Comp Sci & Technol Guangzhou Guangdong Peoples R China Beijing Inst Graphic Commun Sch Informat & Mech Engn Beijing Peoples R China

ISBN: (纸本)9783642274510

In view of the FP-Growth algorithm needs to establish huge FP-Tree to take the massive memories, when is confronted with very huge database, its algorithm obviously insufficient in efficiency. This article unified FP-Growth and parallel algorithm, proposed one kind association rule parallel algorithm based on the FP-Growth, this algorithm in the FP-Growth algorithm foundation, with the aid of parallel algorithm's thought that carried on the database resolution as well as the FP-tree tree the division reasonable combination, In the task allocation, the load stabilization, has done the research, the duty rational distribution, the combination, has achieved the good load stabilization, raised the algorithm speed, this algorithm is suitable in the large-scale database carries on the data mining, compared with former algorithm had the remarkable enhancement in the efficiency.

关键词： FP-Growth Association Rules parallel algorithm Load Balancing

来源：评论

学校读者我要写书评

暂无评论

Chaotic Relaxation Asynchronous Iterative parallel algorithm and Its Implementation

Chaotic Relaxation Asynchronous Iterative Parallel Algorithm...

引用

2011年第十届分布式计算及其应用国际学术研讨会

作者： LI Wenjing YANG Wen LI Shuju College of Computer Science and Information Engineering Guangxi Teachers Education University

In order to solve the system load imbalanced problem of the synchronized parallel algorithm on unconstrained optimization problems,improve the speed of solving *** relaxation asynchronous

ISBN: (纸本)9780769544151

In order to solve the system load imbalanced problem of the synchronized parallel algorithm on unconstrained optimization problems,improve the speed of solving *** relaxation asynchronous

关键词： Asynchronous Iterative Chaotic Relaxation parallel algorithm PC Cluster Unconstrained Optimization Problems

来源：评论

学校读者我要写书评

暂无评论

A simple optimal parallel algorithm for constructing a spanning tree of a trapezoid graph

引用

JOURNAL OF DISCRETE MATHEMATICAL SCIENCES & CRYPTOGRAPHY 2007年第5期10卷 655-660页

作者： Chen, Hon-Chan Natl Chin Yi Univ Technol Dept Informat Management 35 Lane 215Sect 1Chung Shan Rd Taiping City 411 Taichung County Taiwan

Let G be a connected graph with n vertices. A spanning tree of G is an acyclic subgraph of G that has n vertices and n - 1 edges. In this paper, we propose a simple optimal parallel algorithm for constructing a spanni... 详细信息

关键词： Spanning tree trapezoid graph parallel algorithm

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：