检索结果-内蒙古大学图书馆

International Symposium on parallel and Distributed computing

作者： Christopher J. Reynolds Zsolt Lichtenberger Stephen Winter Centre for Parallel Computing School of Electronics and Computer Science University of Westminster London UK

The availability of low cost high performance hardware such as graphical processing units (GPUs) has been the driving force for considerable change in both traditional high performance computing (HPC), and more recently the data centre. Vendor independent methods of accessing such hardware include the recently standardised OpenCL framework. However, using GPUs as accelerators for certain computational algorithms requires careful provisioning of infrastructure in order to balance cost, power consumption, and device utilization. In this paper we describe vOpenCL, an architecture for provisioning OpenCL capable hardware. vOpenCL works by transparently offloading processing from traditional cluster nodes, to a remotely located farm of OpenCL capable processors such as GPUs. vOpenCL differs from existing provisioning solutions since it provides mechanisms to optimize the data transfers between components. This is achieved through the use of a module/plug in which fully exploits the Infiniband interconnect architecture. We provide full analysis of vOpenCL and all of its plugins, in a range of scenarios including from within virtualized environments. For certain algorithms, we demonstrate that the Infiniband plug in can provide significant performance benefits.

关键词： Graphics processing unit Servers Sockets IP networks Kernel Libraries Time measurement

来源：评论

学校读者我要写书评

暂无评论

Interfacing RePast with HLA using a generic architecture for COTS simulation package interoperability

Interfacing RePast with HLA using a generic architecture for...

引用

Spring Simulation Interoperability Workshop 2009

作者： Liang, Yuanxi Cai, Wentong Turner, Stephen J. Theodoropoulos, Georgios K. Minson, Rob Parallel and Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore 639798 Singapore School of Computer Science University of Birmingham Edgebaston Birmingham B152TT United Kingdom

ISBN: (纸本)9781605607986

A Distributed Multi-Agent System (MAS) is often appropriate in solving large-scale experimental problems. RePast is a well-known simulation toolkit for agent-based modeling. In order to extend the scalability of RePast, one way is to partition the model into a distributed simulation. Interfacing RePast with the High Level Architecture (HLA) is a way to build the distributed system. This has previously been achieved in the HLA-RePast system by using a traditional interfacing approach which is time-consuming in the development process. In this paper, a new approach to interfacing RePast with the HLA is introduced. It is a pioneering attempt to adopt a generic architecture for Commercial Off-The-Shelf (COTS) simulation package interoperability to interface an agent-based simulation package with the HLA. A middleware called DSManager originally designed to support COTS simulation package interoperability, is proven to be able to support interoperability of RePast models in a fast and easy manner. The advantages and tradeoffs, and the performance of the new distributed RePast system are discussed and compared to the HLA-RePast system.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Cluster based partitioning for agent-based crowd simulations 09

Cluster based partitioning for agent-based crowd simulations

引用

Simulation Winter Conference

作者： Yongwei Wang Michael Lees Wentong Cai Suiping Zhou Malcolm Yoke Hean Low Parallel and Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781424457717

Simulating crowds is a challenging but important problem. There are various methodologies in the literature ranging from macroscopic numerical flow simulations to detailed, microscopic agent simulations. One key issue for all crowd simulations is scalability. Some methods address this issue through abstraction, describing global properties of homogeneous crowds. However, ideally a modeler should be able to simulate large heterogeneous crowds at fine levels of detail. We are attempting to achieve scalability through the application of distributed simulation techniques to agent-based crowd simulation. Distributed simulation, however, introduces its own challenges, in particular how to efficiently partition the load between a number of machines. In this paper we introduce a method of partitioning agents onto machines using an adapted k-means clustering algorithm. We present, validate and use an analysis tool to compare the proposed clustered partitioning approach with a series of existing methods.

关键词： Computational modeling Clustering algorithms Partitioning algorithms Scalability Computer simulation Distributed computing Concurrent computing Numerical simulation Microscopy Humans

来源：评论

学校读者我要写书评

暂无评论

Trusted Block as a Service: Towards Sensitive Applications on the Cloud

Trusted Block as a Service: Towards Sensitive Applications o...

引用

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Jianan Hao Wentong Cai Parallel and Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

Cloud computing grows rapidly as today's advanced information technology. However, by allowing outsourcing computation on the Cloud, users risk of disclosing privacy and obtaining forged results. These potential threats block sensitive applications to join the Cloud. In this paper, we characterize sensitive applications on the Cloud (SAND) problem and define two critical security requirements: confidentiality and verifiability. The former refers to the protection of sensitive programs/data from disclosing to other users or even the Cloud administrators. The latter concerns with user's capability to verify whether computing results are faithfully calculated. To address SAND, we propose a new Cloud model, Trusted Block as a Service (TBaaS), to provide a confidential and verifiable environment for each sensitive application. TBaaS limits Cloud provider's access of sensitive applications while granting user the ability to verify whether the computation is faithfully carried out. Moreover, it offers high flexibility and low performance overhead.

关键词： Virtual machine monitors Encryption Protocols Hardware Software

来源：评论

学校读者我要写书评

暂无评论

Grid Services and Service Discovery for HLA-Based Distributed Simulation 04

Grid Services and Service Discovery for HLA-Based Distribute...

引用

International Workshop/Symposium on Distributed Simulation and Real-Time Applications (DS-RT)

作者： Wenbo Zong Yong Wang Wentong Cai S.J. Turner Parallel and Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

ISBN: (纸本)9780769522326

Modelling and simulation permeate all areas of business, science and engineering and increasingly complex simulation systems often require huge computing resources and data sets that are geographically distributed. The widely adopted platform for building distributed simulations is the High Level Architecture (HLA). Deficiencies associated with HLA have been well discussed in the literature. The advent of Grid technology enables the use of distributed computing resources and facilitates the access of geographically distributed data. In this paper, we propose a framework for executing large-scale distributed simulations using Grid services. The framework addresses some of the deficiencies of HLA, including dynamic discovery and resource utilization. End-users can construct large-scale distributed simulations using this framework with ease.

关键词： Computational modeling Distributed computing Large-scale systems Web services Resource management Concurrent computing Data engineering Computer simulation Computer architecture Buildings

来源：评论

学校读者我要写书评

暂无评论

Toward a Generic Framework for Modeling Human Behaviors in Crowd Simulation

Toward a Generic Framework for Modeling Human Behaviors in C...

引用

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Linbo Luo Suiping Zhou Wentong Cai Malcolm Yoke Hean Low Michael Lees Parallel and Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

This paper presents our ongoing work on modeling agents with human-like decision making and behavior execution capabilities in crowd simulation. We aim to provide a generic framework that reflects the major cognitive and physical processes as observed from human behaviors in real-life situations. The design of the framework is based on some basic assumptions and related cognitive theories on human behaviors in various real-life situations. In this paper, the cognitive architecture of our framework is presented, which emphasizes the role of experiences in human's decision making. The paper also briefly describes the design of agent's decision making process and presents a case study to show some results in a crowd simulation scenario.

关键词： Humans Decision making Intelligent agent Paper technology Computational modeling Computer simulation Distributed computing Conferences Concurrent computing Psychology

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of a bandwidth requirements reduction technique based on timely state update

Performance evaluation of a bandwidth requirements reduction...

引用

Annual Symposium on Simulation

作者： Wentong Cai S.J. Turner Suiping Zhou Junhu Wei Wenbo Zong Parallel & Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

An important issue in distributed real-time simulation is to reduce the amount of data transmitted amongst distributed simulation nodes so that the state updates of simulation entities can be sent to other simulation nodes in a timely manner. To address this issue, we have previously proposed a consistency model to determine the update interval of entities based on their relative importance, a utility model to compute the relative importance of entities, and a flexible state update mechanism to ensure updating within these intervals and to balance the number of updates in each simulation frame. In this paper, we focus on the performance evaluation of these timely state update mechanisms. Using a battlefield benchmark, the performance is evaluated in terms of the total amount of data exchanged, the number of simulation frames skipped, and the number of go-through-accidents occurring during the simulation. The performance results indicate that the mechanisms can significantly reduce the bandwidth requirements while maintaining or even improving the consistency of the simulation.

关键词： Bandwidth Computational modeling Computer simulation Distributed computing Large-scale systems Frequency Engines Concurrent computing Data engineering Military computing

来源：评论

学校读者我要写书评

暂无评论

Multiagent interactions in distributed virtual worlds

Multiagent interactions in distributed virtual worlds

引用

IEEE Region 10 International Conference TENCON

作者： F. Wang S.J. Turner L. Wang Parallel & Distributed Computing Centre School of Computer Engineering Nanyang Technological University Singapore

Multiagent systems provide a valuable tool for handling increasing software complexity and supporting rapid and accurate problem solving. This paper presents a general architecture in which autonomous agents are embedded in a distributed virtual environment and are enabled to communicate with each other. We focus on the interaction issues, using cooperation and coordination patterns. Different cases of the agents' teamwork to improve their efficiency are investigated and compared. A prototype system has been implemented, with message templates and algorithms identified. Finally, some experimental results are given.

关键词： Problem-solving Computational modeling Distributed computing Multiagent systems Software tools Autonomous agents Virtual environment Prototypes Application software Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

Shared Variable Management in SOAr-DSGrid

Shared Variable Management in SOAr-DSGrid

引用

Asia International Conference on Modeling & Simulation

作者： Xinjun Chen Wentong Cai Stephen J. Turner Yong Wang School of Computer Engineering Parallel and Distributed Computing Centre Nanyang Technological University Singapore

Simulation is a low cost alternative to experimentation on real-world physical systems. In light of the prevalence of web services, issues relating to distributed simulation using web services have come to the fore in recent years. We have proposed a service-oriented architecture for distributed simulations on the Grid (SOAr-DSGrid). SOAr-DSGrid facilitates the development and execution of distributed simulations in different views (i.e., a component-based view for development and a service-oriented view for execution). At run time, one component may require information from another component for execution or decision-making. In SOAr-DSGrid, this shared information from one component to another component is implemented through shared variables. Since two components may execute out of phase, without proper shared variable management, the value provided by one component may be invalid for another component due to the time difference. Since SOAr-DSGrid provides a service-oriented view for component execution, the development of shared variable support also follows the service-oriented methodology. Three different approaches, namely Pull without FutureList, Pull with FutureList, and Push, have been implemented as the internal mechanism to solve the shared variable issue. Experimental results of the performance of these three approaches are also presented in this paper.

关键词： Computational modeling Computer simulation Distributed computing Costs Web services Service oriented architecture Computer networks Runtime Asia Conference management

来源：评论

学校读者我要写书评

暂无评论

Cluster computing and Grid 2005 works in progress

引用

IEEE Distributed Systems Online 2005年第9期6卷

作者： Wang, Frank Helian, Na Wu, Sining Deng, Yuhui Zhou, Ke Guo, Yike Thompson, Steve Johnson, Ian Milward, Dave Maddock, Robert Khoo, Benjamin Bharadwaj, Veeravalli Cambridge-Cranfield High Performance Computing Facility London Metropolitan University Cranfield University Imperial College Xyratex Department of Grid Computing and E-science Centre for Grid Computing Data Mining at the London Metropolitan University Centre for Grid Computing Cranfield University London E-science Centre Parallel Computing Centre Imperial College National University of Singapore Department of Electrical and Computer Engineering National University of Singapore

A grid-oriented storage (GOS) project, which aims to support advanced data bank services and data reservoirs for sharing data on the gird, is discussed. The GOS appliance is a disk array that connects directly to the grid using a Globus XIO interface and fits in the thin server categorization. The security model of the GOS is based on the Grid security Infrastructure (GSI). A dynamic estimation scheme for fault-free scheduling in grid systems is also discussed. Most of the grid falls into one of the two categories, planned and negotiated, and dynamic and voluntary. This discrepancy is the main reason behind the complexity in designing robust and fault tolerant scheduling algorithms for both resource categories.

关键词： Data storage equipment

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：