检索结果-内蒙古大学图书馆

A parallel algorithm of Kirchhoff Pre-stack Depth Migration Based on GPU 1

14th International Conference on algorithms and Architectures for parallel Processing (ICA3PP)

作者： Wang, Yida Li, Chao Tian, Yang Yan, Haihua Zhao, Changhai Zhang, Jianlei Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China

ISBN: (数字)9783319111940

ISBN: (纸本)9783319111940;9783319111933

Kirchhoff pre-stack depth migration (KPSDM) algorithm, as one of the most widely used migration algorithms, plays an important part in getting the real image of the earth. However, this program takes considerable time due to its high computational cost;hence the working efficiency of the oil industry is affected. The general purpose Graphic Processing Unit (GPU) and the Compute Unified Device Architecture (CUDA) developed by NVIDIA have provided a new solution to this problem. In this study, we have proposed a parallel algorithm of the Kirchhoff pre-stack depth migration and an optimization strategy based on the CUDA technology. Our experiments indicate that for large data computations, the accelerated algorithm achieves a speedup of 8 similar to 15 times compared with NVIDIA GPU.

关键词： Kirchhoff pre-stack depth migration GPU CUDA parallel algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

NearlyWork-Efficient parallel algorithm for Digraph Reachability 2018

NearlyWork-Efficient Parallel Algorithm for Digraph Reachabi...

引用

50th Annual ACM SIGACT Symposium on the Theory of Computing (STOC)

作者： Fineman, Jeremy T. Georgetown Univ Washington DC 20057 USA

ISBN: (纸本)9781450355599

One of the simplest problems on directed graphs is that of identifying the set of vertices reachable from a designated source vertex. This problem can be solved easily sequentially by performing a graph search, but efficient parallel algorithms have eluded researchers for decades. For sparse high-diameter graphs in particular, there is no known work-efficient parallel algorithm with nontrivial parallelism. This amounts to one of the most fundamental open questions in parallel graph algorithms: Is there a parallel algorithm for digraph reachability with nearly linear work? This paper shows that the answer is yes. This paper presents a randomized parallel algorithm for digraph reachability and related problems with expected work (O) over tilde (m) and span (Omega) over tilde (n(2/3)), and hence parallelism (Omega) over tilde (m/n(2/3)) = (Omega) over tilde (n(1/3)), on any graph with n vertices and m arcs. This is the first parallel algorithm having both nearly linear work and strongly sublinear span, i.e., span (Omega) over tilde (n(1-epsilon)) for any constant epsilon > 0. The algorithm can be extended to produce a directed spanning tree, determine whether the graph is acyclic, topologically sort the strongly connected components of the graph, or produce a directed ear decomposition, all with work (O) over tilde (m) and span (O) over tilde (n(2/3)). The main technical contribution is an efficient Monte Carlo algorithm that, through the addition of (O) over tilde (n) shortcuts, reduces the diameter of the graph to (Omega) over tilde (n(2/3)) with high probability. While both sequential and parallel algorithms are known with those combinatorial properties, even the sequential algorithms are not efficient, having sequential runtime (Omega) over tilde (m (1)). This paper presents a surprisingly simple sequential algorithm that achieves the stated diameter reduction and runs in O(m) time. parallelizing that algorithm yields the main result, but doing so involves overcomi

关键词： parallel algorithm randomized algorithm graph search reachability shortcuts

来源：评论

学校读者我要写书评

暂无评论

Design and Improvement of the parallel algorithm in the Computer Games System 28

Design and Improvement of the Parallel Algorithm in the Comp...

引用

28th Chinese Control and Decision Conference

作者： Wu, Gui Tao, Jun Jianghan Univ Educ Adm Off Wuhan 430056 Peoples R China Jianghan Univ Sch Math & Comp Sci Wuhan 430056 Peoples R China Rowan Univ Dept Elect & Comp Engn Glassboro NJ 08028 USA

ISBN: (纸本)9781467397148

The core technology of the computer games is the search. The paper is studied to research both the mononuclear search algorithm and the parallel search algorithm. For the mononuclear search algorithm, the selective search thought is supplied to the computer games system. For the parallel search algorithm, the paper studies the several existing multi-core parallel search methods and analyzes their advantages and disadvantages. According to the characteristics, the improvement scheme is put forward to the parallel search algorithm. The practical results of the computer games system show the comparison effect between the original methods and the improved methods. The paper finally discusses some special programming skills of the Alpha-Beta implementation in the parallel search system. The advanced and modified algorithm is proved to be practical and applicative by experimentations and tests of parallel computer games system provided in this paper.

关键词： parallel algorithm Search algorithm Computer Games Alpha-Beta Search

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm for finding all the roots of a polynomial

A Parallel algorithm for finding all the roots of a polynomi...

引用

6th International Conference for Young Computer Scientists

作者： Jin, YM Zhang, SY Hangzhou Inst Commerce Hangzhou 310035 Peoples R China

ISBN: (纸本)7506251817

Finding all roots of a polynomial is basic and important work for numerical and algebraic calculation. We develop a method that only simple root is needed computing, either the roots are real or complex, Firstly, a parallel algorithm for computing the greatest common factor of two polynomials is put forward;Secondly, a standard decomposing for a polynomial is given. Lastly, a method for converting the complex roots of a polynomial to the real roots of another polynomials is obtained.

关键词： greatest common factor parallel algorithm conjugate complex root

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm to Calculate an Approximation to the Order-K Voronoi Diagram using Java Streams and Thrust 9

A Parallel Algorithm to Calculate an Approximation to the Or...

引用

9th IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Trefftz, Christian Gautam, Debaditya Szakas, Joseph Grand Valley State Univ Sch Comp Allendale MI 49401 USA Univ Maine Dept Comp Informat Syst Augusta ME USA

A parallel algorithm to find an approximate solution to the Order-K Voronoi Diagram problem is presented. Results of parallel implementations using Java Streams and Thrust are reported.

ISBN: (纸本)9781728105543

A parallel algorithm to find an approximate solution to the Order-K Voronoi Diagram problem is presented. Results of parallel implementations using Java Streams and Thrust are reported.

关键词： Order-k Voronoi Diagram Java Streams Thrust parallel algorithm

来源：评论

学校读者我要写书评

暂无评论

Extreme Learning Machine Optimization Based High Speed parallel algorithm for Reed-Solomon Decoding

Extreme Learning Machine Optimization Based High Speed Paral...

引用

International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE)

作者： Kumar, Sanjeev Verma, Priyanka Kulhari, Sandeep Sine Int Inst Technol ECE Dept Jaipur Rajasthan India NIET ECE Dept Greater Noida India Sine Int Inst Technol Jaipur Rajasthan India

ISBN: (纸本)9781509034116

A lot of research has been done on efficient implementation of RS code encoders and decoders as VLSI chips. However, none of them tries to seek a unified approach for solution to obtain VLSI hardware for RS encoders and decoders which can be easily configured for use across a large set of application areas with varying specifications. In this paper, a novel parallel RS decoding algorithm suitable for multi- Gb/s communication systems has been designed. Extreme Learning Machine is used in order to overcome the drawbacks of existing designs. Through the proposed design the performance benefit of the algorithm is truly witnessed. It is suitable for high speed real-time systems with hard timing constraints. The design is implemented and simulated in Xilinx Virtex 6 FPGA through MATLAB and VHDL.

关键词： RS Decoder VLSI MATLAB High speed parallel algorithm ELM VHDL FPGA Design

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm for Mining Association Rules Based on FP-tree

A Parallel Algorithm for Mining Association Rules Based on F...

引用

International Conference on Advances in Computer Science, Environment, Ecoinformatics, and Education

作者： Tu, Fei He, Bo ChongQing Univ Technol Sch Engn & Comp Sci Chongqing 400054 Peoples R China

ISBN: (纸本)9783642233388

The paper proposed a parallel algorithm for mining association rules based on FP-tree, namely, PAMARF algorithm. It distributed data according horizontal projection method. PAMARF algorithm made nodes compute local frequent itemsets with FP-tree, then the centre node exchanged data with other nodes and combined, finally, global frequent itemsets were gained. PAMARF algorithm required far less communication traffic by the strategy of top-down. Theoretical analysis and experimental results suggest that PAMARF algorithm is effective.

关键词： parallel algorithm Association Rules FP-tree

来源：评论

学校读者我要写书评

暂无评论

A new efficient parallel algorithm for minimum spanning tree 30

A new efficient parallel algorithm for minimum spanning tree

引用

30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

作者： de Alencar Vasconcellos, Jucele Franca Caceres, Edson Norberto Mongelli, Henrique Song, Siang Wun Univ Fed Mato Grosso do Sul Coll Comp Campo Grande MS Brazil Univ Sao Paulo Inst Math & Stat Sao Paulo SP Brazil

ISBN: (纸本)9781538677698

In this paper, using the BSP/CGM model, we propose a parallel algorithm and implement it on a GPGPU to obtain a minimum spanning tree of a graph. Previous works for this problem are based on the solution of the list ranking problem which, though efficient in theory, did not produce good speedups in practice. In a later work, based on the idea of computing a structure called strut, we proposed a parallel algorithm under the BSP/CGP model to obtain a minimum spanning tree without using list ranking. It is based on the construction of an auxiliary bipartite graph and uses integer sorting. In this paper, we improve that work in some aspects. The proposed algorithm does not require the computation of the bipartite graph, and the strut construction does not require the sorting algorithm. The efficiency and scalability of the proposed algorithm are verified through experimental results obtained by an implementation on GPGPU.

关键词： minimum spanning tree parallel algorithm BSP/CGM Model GPU

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm of Optimal Power Flow on Hadoop Platform

A Parallel Algorithm of Optimal Power Flow on Hadoop Platfor...

引用

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)

作者： Liang, Bing Jin, Song Tang, Wei Sheng, Wanxing Liu, Keyan North China Elect Power Univ Dept Elect & Commun Engn Beijing Peoples R China China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China China Elect Power Res Inst Beijing 100192 Peoples R China

ISBN: (纸本)9781509054183

Application of smart grid leads to significant increase in scale and data of the power systems, bringing new challenges to the calculation of optimal power flow. However, the existing parallel algorithms, such as MPI-based solutions, suffer from high computational complexity. In this paper, we propose a parallel algorithm of optimal power flow based on Map-Reduce framework. More concretely, the node reordering in our algorithm can greatly accelerate solution speed of the linear equations meanwhile fit well with Map-Reduce programming specifications. Moreover, we determine the appropriate formats for input, intermediate and output data sets and partition the algorithm into separate map/reduce tasks. This facilitates our algorithm to be executed in parallel on a large number of computing nodes. The proposed algorithm is verified on a Hadoop cluster. The experimental results demonstrate that the effectiveness of the propose algorithm.

关键词： Optimal power flow parallel algorithm Node reordering Map-Reduce Hadoop cluster

来源：评论

学校读者我要写书评

暂无评论

parallel algorithm for solving least-squares problems and its convergence analysis

引用

Jianghan Shiyou Xueyuan Xuebao/Journal of Jianghan Petroleum Institute 2002年第1期24卷 92-93+VIII页

作者： Chen, Zhong Jianghan Petroleum Institute Jingzhou 434023 China

Based on the thought of Gauss-Seidel iteration, a parallel algorithm is proposed for solving the least-square problems, the method is proved to be convergent. The calculated amount is greatly reduced, thus calculating time is saved extensively when the method is used, because only triangle decomposition is needed for one of the submatrices of Matrix Jacobi and the decomposition is not needed for the whole Jacobi.

关键词： Convergence Least-squares parallel algorithm SOR iteration

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：