检索结果-内蒙古大学图书馆

17th IEEE international Conference on High Performance computing and Communications, IEEE 7th international symposium on Cyberspace Safety and Security and IEEE 12th international Conference on Embedded Software and Systems, HPCC-ICESS-CSS 2015

作者： Wang, Kebing Bian, Zhaojuan Chen, Qian Software and Service Group Intel Corporation Shanghai China

ISBN: (纸本)9781479989362

Hadoop YARN is evolving to become the de-facto standard that allows multiple data processing engines such as interactive SQL, real-time streaming, data science and batch processing to handle data stored in a single platform. And, there are lots of researches about efficiently managing cluster resources and scheduling parallel jobs over YARN clusters. However, the scheduling of sub-tasks derived from one application doesn't receive enough attention, which still managed by independent data processing engines on YARN. In this paper, we analyze the limitation of sub-task scheduling algorithms of popular data processing engines running on YARN, including MapReduce 2.0, Spark then, we propose Millipedes: a distributed & set-based sub-task scheduling framework. In Millipedes, YARN's application master dispatches a set of sub tasks to data nodes, and then the local task scheduler of each data node schedules the execution of these sub tasks according to real-time dynamic resource usage. © 2015 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Behavior-based Autonomous Cooperative Control of Intelligent Mobile Robot Systems with Embedded Petri Nets 7

Behavior-based Autonomous Cooperative Control of Intelligent...

引用

Joint 7th international Conference on Soft computing and Intelligent Systems (SCIS) and 15th international symposium on Advanced Intelligent Systems (ISIS)

作者： Yasuda, Gen'ichi Nagasaki Inst Appl Sci 536 Aba Machi Nagasaki 8510193 Japan

ISBN: (纸本)9781479959556

this paper presents a methodology of distributed control system design for autonomous cooperative control of intelligent mobile robots. Following the natural concept of control architecture evolution, a bottom-up approach for control system design is presented. First, microcomputer based intelligent device modules, such as multiple infrared range finding sensor modules, and odometry and locomotor control modules, are constructed as a device manager layer on a distributed multi-microcontroller network based hardware structure to detect walls and obstacles and to move around the surroundings of a two-wheeled mobile robot. then functional control modules, such as landmark and obstacle recognition and localization, robot motion control are implemented based on the device layer. Environment features such as lines and corners are estimated using a set of range sensors and a vision sensor. Next, some intelligent behavior modules, such as wall following, obstacle rounding, and target seeking, and environment mapping are implemented as cooperative activities based on the functional control modules. Upon these hierarchical activity modules, a non-centralized control approach is applied to implement the autonomous coordination of concurrent activities among behavior modules for the high-level tasks such as sensory navigation in unknown environments. the system integration and implementation issues are discussed for the proposed approach.

关键词： Autonomous cooperative robot systems distributed control behavior-based modular synthesis Petri nets implementation

来源：评论

学校读者我要写书评

暂无评论

An Experiment on the Load Shifting from Service Registry to Service Providers in SOA 7

An Experiment on the Load Shifting from Service Registry to ...

引用

IEEE 7th international symposium on Cloud and Service computing (IEEE SC2)

作者： Hsu, Kuo-Hsun Lai, Kuan-Chou Huang, Li-Yung Yang, Hsuan-Fu Tsai, Wei-Shan Natl Taichung Univ Educ Dept Comp Sci Taichung 403 Taiwan

ISBN: (纸本)9781538658628

In SOA (Service-Oriented Architecture), the service match making process is conducted in the registry. When the amount of requests increases, the communication load between registry and requesters could also increase, which may overload the registry and result in a longer response time. this could be worse when the service match making is based on semantic rather than syntax. To address this issues, we proposed, in this paper, an extension of the SOA to reduce the response time and registry loading by reallocating the major service match making tasks to service providers. An experiment is also conducted to compare the performance of the proposed architecture with original SOA to illustrate the feasibility of the proposed approach.

关键词： SOA distributed architecture XMPP

来源：评论

学校读者我要写书评

暂无评论

A distributed query execution engine in a grid environment 07

A distributed query execution engine in a grid environment

引用

7th IEEE international symposium on Cluster computing and the Grid, CCGrid 2007

作者： Trevisol, Gustavo G. Biancardi, Cristiano Barbosa, Alvaro C. P. Filho, José G. Pereira Costa, Ramon G. Cardoso, Evellin S. Federal University of Espirito Santo Computer Science Department Av. Fernando Ferrari 514 29060-970 Vitoria ES Brazil

ISBN: (纸本)0769528333

Grid is a computational environment in which applications can use multiple distributed computational resources in a safe, coordinated, efficient and transparent way. Data Integration Middleware Systems (DIMS) are originally distributed systems that can make use of Grid environments to obtain a better performance and a rational use of available resources. this work describes a distributed Query Execution Engine (DQEE) inserted in a Grid environment for executing sub-queries and operators in a distributed and parallel way. We present an approach to obtain an efficient distributed query execution with a reduced response time by the use of the DQEE. © 2007 IEEE.

关键词： Grid computing

来源：评论

学校读者我要写书评

暂无评论

Overdrive controllers for distributed scientific computation 07

Overdrive controllers for distributed scientific computation

引用

7th IEEE international symposium on Cluster computing and the Grid

作者： Wozniak, Justin M. Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA

ISBN: (纸本)9780769528335

Large distributed computer systems have been successfully employed to solve modern scientific problems that were previously impracticable. Tools exist to bind together notably underutilized high speed computers and sizable storage resources, creating architectures that provide performance and capacity that scales with the quantity of resources invested. In various forms such as Internet computing, desktop grids, and even "big iron" grids, users and administrators find it difficult, however, to obtain aggregate systems that are more reliable than their underlying components and simple to utilize in concert. In this work, we will propose a model for controlling complex distributed systems and its application to the construction of scientific repositories.

关键词： distributed control distributed computing Grid computing Fabrics Control systems Computer architecture Internet Process design Software systems Mathematical model

来源：评论

学校读者我要写书评

暂无评论

parallel and distributed Frugal Tracking of a Quantile 7

Parallel and Distributed Frugal Tracking of a Quantile

引用

7th international Workshop on Systems and Network Telemetry and Analytics (SNTA)

作者： Cafaro, Massimo Epicoco, Italo Pulimeno, Marco Univ Salento Lecce Italy

ISBN: (纸本)9798400706486

In this paper we deal with the problem of monitoring network latency. Indeed, latency is a key network metric related to both network performance and Quality of Service, since it directly impacts on the overall user's experience. High latency leads to unacceptably slow response times of network services, and may increase network congestion and reduce the throughput, in turn disrupting communications and the user's experience. A common approach to monitoring network latency takes into account the frequently skewed distribution of latency values, and therefore specific quantiles are monitored, such as the 95th, 98th, and 99th percentiles. We present a parallel, message-passing based version of the FRUGAL algorithm that can be used for monitoring network latency quickly and accurately. A distributed version is also discussed.

关键词： Latency Quantile Stream parallel computing distributed computing

来源：评论

学校读者我要写书评

暂无评论

Proceedings - 7th international Conference on parallel and distributed Systems: Workshops

Proceedings - 7th International Conference on Parallel and D...

引用

7th international Conference on parallel and distributed Systems, ICPADS 2000

ISBN: (纸本)0769505716

the proceedings contain 82 papers. the topics discussed include: a new list scheduling method based on structural properties of task graphs;network based genetic algorithm;a memory management architecture for a mobile computing environment;domination in bounded interval tolerance graphs;a constant queue partial permutation routing algorithm for cube-connected-cycles multicomputer systems;packet loss detection scheme for retransmission-based real-time data transfer;a totally ordered and secure multicast protocol for distributed virtual environment;access control model in object-oriented systems;concurrent exception handling in a distributed object-oriented computing environment;and a generalized approach for transferring data-types with arbitrary communication libraries.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel Multi-Layer Ghost Cell Generation for distributed Unstructured Grids 7

Parallel Multi-Layer Ghost Cell Generation for Distributed U...

引用

IEEE 7th symposium on Large Data Analysis and Visualization (LDAV)

作者： Patchett, John M. Nouanesengesy, Boonthanome Pouderoux, Joachim Ahrens, James Hagen, Hans TU Kaiserslautern Los Alamos Natl Lab Kaiserslautern Germany Los Alamos Natl Lab Los Angeles CA USA Kitware SAS Villeurbanne France TU Kaiserslautern Kaiserslautern Germany

ISBN: (纸本)9781538606179

Ghost cells are important for distributed memory parallel operations that require neighborhood information, and are required for correctness on the boundaries of local data partitions. Ghost cells are one or more layers of grid cells surrounding the external boundary of the local partition, which are owned by other data partitions. they are used by the local partition when neighbor information is required. Finding ghost cells in structured data is trivial and can normally be done by calculating on cell indices. Obtaining ghost cells for unstructured grid data, however, is a nontrivial task. It requires an analysis of the connectivity of the grid in order to find neighbor cells. When the grid is distributed, the operation is further complicated by the need to determine which processes own the neighbor cells, and coordinating communication with them. this is a problem when operating on unstructured grid data sets that do not already have ghost cells. parallel visualization algorithms will usually assume that a cell does not exist if it is not in the local data partition. Without ghost cells, this leads to operations that need neighborhood information, such as point data interpolated from cell data, being calculated incorrectly at partition boundaries. Production visualization tools generally support the existence of ghost cells, but not their generation, especially for unstructured grids. In the literature, there is no documented algorithm for generating in parallel one or more layers of ghost cells for unstructured grid data which has already been partitioned. We present a new algorithm to compute ghost cells in parallel on distributed unstructured data sets with no global cell or point IDs. Given a partitioned data set without ghost cells, this algorithm is capable of producing any number of layers of ghost cells necessary to support parallel operations. Performance results and timing comparisons to ParaView's D3 filter are presented. A number of optimizations to th

关键词： I.3.2 [COMPUTER GRAPHICS]: Graphics Systems-distributed/network graphics G.1.0 [Mathematics of computing]: Numerical Analysis-parallel Algorirthms

来源：评论

学校读者我要写书评

暂无评论

Special Issue: Performance evaluation of ubiquitous computing and networked systems

引用

international JOURNAL OF parallel EMERGENT AND distributed SYSTEMS 2010年第4期25卷 237-239页

作者： Al-Dubai, Ahmed Y. Ould-Khaoua, Mohamed Min, Geyong Napier Univ Sch Comp 10 Colinton Rd Edinburgh EH10 5DT Midlothian Scotland Sultan Qaboos Univ Dept Elect & Comp Engn Muscat Oman Univ Bradford Dept Comp Bradford BD7 1DP W Yorkshire England

In April 2008, we organised the 7th international workshop on Performance Modelling, Evaluation and Optimization of Ubiquitous computing and Networked Systems (PMEO-UCNS'2008) held in conjunction with the IEEE-IPDPS, 14-18 April 2008, Miami, Florida, USA. We selected seven high quality papers (out of 17 papers, which were presented at the workshop) and invited the authors of the selected papers to extend them and submit them for a complete new peer-review for consideration in this special issue.

关键词： Ubiquitous computing paper PERFORMANCE MODELING Workshops CONJUNCTION workshops Performance Evaluation

来源：评论

学校读者我要写书评

暂无评论

Approximating biconnectivity in parallel

引用

ALGORIthMICA 1998年第4期21卷 395-410页

作者： Chong, KW Lam, TW Max Planck Inst Informat D-66123 Saarbrucken Germany Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

Consider the following NP-hard problems: Given a graph G, find minimum 2-edge connected and 2-vertex connected subgraphs spanning all vertices of G. Over the past few years, exciting sequential algorithms for approximating such minimum subgraphs have been produced [6], [10]. the approximation factors are improved from 2 to 3/2 for both of the problems. Yet the techniques involved are all based on augmenting depth-first-search trees and no similar progress has been carried to the parallel context. this paper presents NC algorithms to achieve approximation factors of 3/2 + epsilon for these two problems without computing depth-first-search trees.

关键词： approximation algorithms graph algorithms NC PRAM biconnectivity perfect matching maximum matching

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：