检索结果-内蒙古大学图书馆

作者： Feng, Shuangtong Virginia Tech | University

The problem of efficient parallelization of 2D Ising spin systems requires realistic algorithmic design and implementation based on an understanding of issues from computer science and statistical physics. In this work, we not only consider fundamental parallel computing issues but also ensure that the major constraints and criteria of 2D Ising spin systems are incorporated into our study. This realism in both parallel computation and statistical physics has rarely been reflected in previous research for this problem.

In this thesis,we designed and implemented a variety of parallel algorithms for both sweep spin selection and random spin selection. We analyzed our parallel algorithms on a portable and general parallel machine model, namely the LogP model. We were able to obtain rigorous theoretical run-times on LogP for all the parallel algorithms. Moreover, a guiding equation was derived for choosing data layouts (blocked vs. stripped) for sweep spin selection. In regards to random spin selection, we were able to develop parallel algorithms with efficient communication schemes. We analyzed randomness of our schemes using statistical methods and provided comparisons between the different schemes. Furthermore, algorithms were implemented and performance data gathered and analyzed in order to determine further design issues and validate theoretical analysis.

关键词： spin selection schemes data layout optimization computational science Ising model LogP parallel model performance prediction parallel and distributed processing Thesis

来源：评论

学校读者我要写书评

暂无评论

parallel image convolution processing with replicas in a network of workstations

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2005年第6期E88D卷 1199-1209页

作者： Aritsugi, M Fukatsu, H Kanamori, Y Gunma Univ Fac Engn Dept Comp Sci Kiryu Gumma 3768515 Japan

Data accessed by many sites are replicated in distributed environments for performance and availability. In this paper, replication schemes are examined in parallel image convolution processing. This paper presents a system architecture that we have developed with CORBA (Common Object Request Broker Architecture) for the processing. Employing CORBA enables us to make use of a cluster of workstations, each of which has a different level of computing power. The paper also describes a parallel and distributed image convolution processing model using replicas stored in a network of workstations, and reports some experimental results showing that our analytical model can agree with practical situations.

关键词： digital image convolution CORBA performance evaluation network of work-stations parallel and distributed processing

来源：评论

学校读者我要写书评

暂无评论

An algorithm for node-disjoint paths in pancake graphs

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2003年第3期E86D卷 610-615页

作者： Suzuki, Y Kaneko, K Tokyo Univ Agr & Technol Fac Technol Koganei Tokyo 1848588 Japan

For any pair of distinct nodes in an n-pancake graph, we give an algorithm for construction of n - 1 internally disjoint paths connecting the nodes in the time complexity of polynomial order of n. The length of each path obtained and the time complexity of the algorithm are estimated theoretically and verified by computer simulation.

关键词： pancake graphs node-to-node disjoint paths problem interconnection networks parallel and distributed processing

来源：评论

学校读者我要写书评

暂无评论

Performance comparison between Hadoop and Spark frameworks using HiBench benchmarks

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2018年第12期30卷

作者： Samadi, Yassir Zbakh, Mostapha Tadonki, Claude Mohammed V Univ Natl Sch Comp Sci & Syst Anal Rabat Morocco MINES ParisTech CRI Paris France

Big Data has become one of the major areas of research for cloud service providers due to a large amount of data produced every day and the inefficiency of traditional algorithms and technologies to handle these large amounts of data. Big Data with its characteristics such as volume, variety, and veracity (3V) requires efficient technologies to process in real time. To solve this problem and to process and analyze this vast amount of data, there are many powerful tools like Hadoop and Spark, which are mainly used in the context of Big Data. They work following the principles of parallel computing. The challenge is to specify which Big Data's tool is better depending on the processing context. In this paper, we present and discuss a performance comparison between two popular Big Data frameworks deployed on virtual machines. Hadoop MapReduce and Apache Spark are used to efficiently process a vast amount of data in parallel and distributed mode on large clusters, and both of them suit for Big Data processing. We also present the execution results of Apache Hadoop in Amazon EC2, a major cloud computing environment. To compare the performance of these two frameworks, we use HiBench benchmark suite, which is an experimental approach for measuring the effectiveness of any computer system. The comparison is made based on three criteria: execution time, throughput, and speedup. We test Wordcount workload with different data sizes for more accurate results. Our experimental results show that the performance of these frameworks varies significantly based on the use case implementation. Furthermore, from our results we draw the conclusion that Spark is more efficient than Hadoop to deal with a large amount of data in major cases. However, Spark requires higher memory allocation, since it loads the data to be processed into memory and keeps them in caches for a while, just like standard databases. So the choice depends on performance level and memory constraints.

关键词： Amazon EC2 Big Data cloud computing Hadoop HiBench parallel and distributed processing Spark

来源：评论

学校读者我要写书评

暂无评论

Assessment of NSF application benchmarks on SGI Altix machines and Cray Opteron cluster

引用

INTERNATIONAL JOURNAL OF parallel EMERGENT AND distributed SYSTEMS 2010年第4期25卷 315-329页

作者： Fatoohi, Rod San Jose State Univ Dept Comp Engn San Jose CA 95192 USA

The National Science Foundation released a set of application benchmarks that would be a key factor in selecting the next-generation high-performance computing environment. These benchmarks consist of six codes that require large amount of memory and work with large data sets. Here we study the complexity, performance and scalability of these codes on three SGI machines: a 512-processor Altix 3700, a 512-processor Altix 3700/BX2 and 512-processor dual-core based Altix 4700;and a 128-processor Cray Opteron cluster interconnected by the Myrinet network. We evaluated these codes for two different problem sizes using different numbers of processors. Our results show that some of these codes scale up very well as we increase the number of processors while others scaled up poorly. Also, one code achieved about 2/3 of the peak rate of an SGI Altix processor. Moreover, the dual-core system achieved comparable performance results to the single-core system.

关键词： engineering applications parallel and distributed processing high-performance computing benchmarking

来源：评论

学校读者我要写书评

暂无评论

Extracting-Transforming-Loading Modeling Approach for Big Data Analytics

引用

INTERNATIONAL JOURNAL OF DECISION SUPPORT SYSTEM TECHNOLOGY 2016年第4期8卷 50-69页

作者： Bala, Mahfoud Boussaid, Omar Alimazighi, Zaia Saad Dahleb Univ Dept Informat Blida 1 Algeria Univ Lyon 1 Lab ERIC Lyon France Univ Sci & Technol Houari Boumediene Dept Comp Sci Bab Ezzouar Algeria

Due to their widespread use, Internet, Web 2.0 and digital sensors create data in non-traditional volumes (at terabytes and petabytes scale). The big data characterized by the four V's has brought with it new challenges given the limited capabilities of traditional computing systems. This paper aims to provide solutions which can cope with very large data in Decision-Support Systems (DSSs). In the data integration phase, specifically, the authors propose a conceptual modeling approach for parallel and distributed Extracting-Transforming-Loading (ETL) processes. Among the complexity dimensions of big data, this study focuses on the volume of data to ensure a good performance for ETL processes. The authors' approach allows anticipating on the parallelization/distribution issues at the early stage of Data Warehouse (DW) projects. They have implemented an ETL platform called parallel-ETL (P-ETL for short) and conducted some experiments. Their performance analysis reveals that the proposed approach enables to speed up ETL processes by up to 33% with the improvement rate being linear.

关键词： Big Data Data Warehousing Extracting-Transforming-Loading Hadoop MapReduce parallel and distributed processing

来源：评论

学校读者我要写书评

暂无评论

Designing Energy Surface for Truck Back-Upper Problem

Designing Energy Surface for Truck Back-Upper Problem

引用

IJCNN International Joint Conference on Neural Networks

作者： Cheng Yuan Liou Jiann Ming Wu Dept.of Computer Science and Information Engineer National Taiwan University

In this work,the idea of energy surfaces which are designed by analogy to the flow 5eld in fluid dynamics is employed to build controller for truck-and-trailer back-upper problem with presence of dynamic obstacles in arbitrary *** first demonstrate that the truck back upper problem in free space,which is an unstable nonlinear control problem,can be naturally solved by the controller based on the flow field of the two dimensional doublet in fluid ***,parallel and distributed algorithms on two dimensional lattices are further developed to compute the emergent flow field,abbreviated as EFF,for general obstacle avoidance navigation with kinematic *** new controller generally guides the navigation along the tangent direction of the streamlines in the developed emergent flow *** the kinematic constraints of the controller,a greedy search for the minimum of the orientation moments surrounding the motor will guide the motor to the desired *** efficiency and direct use of raw images are main advantages of our approach in many real time applications.

关键词： autonomous navigation neural network cellular automata parallel and distributed processing obstacle avoidance Al planning lattice architecture

来源：评论

学校读者我要写书评

暂无评论

Dependability Evaluation of parallel Differential Evolutionary Particle Swarm Optimization for Online Optimal Operational Planning of Energy Plants

Dependability Evaluation of Parallel Differential Evolutiona...

引用

IEEE Region 10 Conference

作者： Norihiro Nishimura Yoshikazu Fukuyama Tetsuro Matsui School of Interdisciplinary Math. Sciences Meiji Univ. Tokyo Japan Corporate R&D Headquarters Fuji Electric Co. Ltd. Tokyo Japan

ISBN: (纸本)9781509025985

This paper evaluates speed-up and dependability of parallel differential evolutionary particle swarm optimization (DEEPSO) for on-line optimal operational planning of energy plants. The planning can be formulated as a mixed integer nonlinear optimization problem (MINLP). When optimal operational planning of numbers of energy plants are calculated simultaneously in a data center, it is required to generate optimal operational planning as rapidly as possible considering control intervals and numbers of treated plants. One of the solutions for this challenge is speeding up by parallel and distributed processing (PDP). However, PDP utilizes numbers of processes and countermeasures for various faults of the processes should be considered. On-line optimal operational planning requires successive calculation at every control interval for keeping customer services. Therefore, sustainable (dependable) calculation keeping quality of solutions are required even if some of the calculation results cannot be returned from distributed processes. Using the proposed parallel DEEPSO based method, it is observed that calculation time becomes about 3 times faster than a sequential calculation, and high quality of solutions can be kept even with high fault probabilities.

关键词： Differential Evolutionary Particle Swarm Optimization Dependability Energy Management System Optimal Operational Planning of Energy Plant parallel and distributed processing

来源：评论

学校读者我要写书评

暂无评论

Connectivity Results of Complete Cubic Networks as Associated with Linearly Many Faults

引用

JOURNAL OF INTERCONNECTION NETWORKS 2015年第1-2期15卷 1550007-1550007页

作者： Cheng, Eddie Qiu, Ke Shen, Zhizhang Oakland Univ Dept Math & Stat Rochester MI 48309 USA Brock Univ Dept Comp Sci St Catharines ON L2S 3A1 Canada Plymouth State Univ Dept Comp Sci & Technol Plymouth NH 03264 USA

We propose the complete cubic network structure to extend the existing class of hierarchical cubic networks, and establish a general connectivity result which states that the surviving graph of a complete cubic network, when a linear number of vertices are removed, consists of a large (connected) component and a number of smaller components which altogether contain a limited number of vertices. As applications, we characterize several fault-tolerance properties for the complete cubic network, including its restricted connectivity, i.e., the size of a minimum vertex cut such that the degree of every vertex in the surviving graph has a guaranteed lower bound;its cyclic vertex-connectivity, i.e., the size of a minimum vertex cut such that at least two components in the surviving graph contain a cycle;its component connectivity, i.e., the size of a minimum vertex cut whose removal leads to a certain number of components in its surviving graph;and its conditional diagnosability, i.e., the maximum number of faulty vertices that can be detected via a self-diagnostic process, in terms of the common Comparison Diagnosis model.

关键词： Complete cubic network hierarchical cubic network fault-tolerance property graph connectivity parallel and distributed processing

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：