首页 > 最新文献

Proceedings 11th IEEE International Symposium on High Performance Distributed Computing最新文献

英文 中文
Partitionable services: A framework for seamlessly adapting distributed applications to heterogeneous environments 可分区服务:用于无缝地使分布式应用程序适应异构环境的框架
A. Ivan, J. Harman, M. Allen, V. Karamcheti
Several recently proposed infrastructures permit client applications to interact with distributed network-accessible services by simply "plugging in" into a substrate that provides essential functionality, such as naming, discovery, and multi-protocol binding. However much work remains before the interaction can be considered truly seamless in the sense of adapting to the characteristics of the heterogeneous environments in which clients and services operate. This paper describes a novel approach for addressing this shortcoming: the partitionable services framework, which enables services to be flexibly assembled from multiple components, and facilitates transparent migration and replication of these components at locations closer to the client while still appearing as a single monolithic service. The framework consists of three pieces: (1) declarative specification of services in terms of constituent components; (2) run-time support for dynamic component deployment; and (3) planning policies, which steer the deployment to accomodate underlying environment characteristics. We demonstrate the salient features of the framework and highlight its usability and performance benefits with a case study involving a security-sensitive mail service.
最近提出的几个基础设施允许客户机应用程序通过简单地“插入”提供基本功能(如命名、发现和多协议绑定)的基础来与分布式网络可访问的服务进行交互。然而,在适应客户端和服务运行的异构环境的特征之前,在认为交互是真正无缝的意义上,还有很多工作要做。本文描述了一种解决这一缺点的新方法:可分区服务框架,它允许从多个组件灵活地组装服务,并促进这些组件在更靠近客户端的位置的透明迁移和复制,同时仍然显示为单个整体服务。该框架由三部分组成:(1)根据组成组件对服务进行声明性规范;(2)运行时支持动态组件部署;(3)规划策略,指导部署以适应潜在的环境特征。我们将通过一个涉及对安全敏感的邮件服务的案例研究,演示该框架的主要特性,并强调其可用性和性能优势。
{"title":"Partitionable services: A framework for seamlessly adapting distributed applications to heterogeneous environments","authors":"A. Ivan, J. Harman, M. Allen, V. Karamcheti","doi":"10.1109/HPDC.2002.1029908","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029908","url":null,"abstract":"Several recently proposed infrastructures permit client applications to interact with distributed network-accessible services by simply \"plugging in\" into a substrate that provides essential functionality, such as naming, discovery, and multi-protocol binding. However much work remains before the interaction can be considered truly seamless in the sense of adapting to the characteristics of the heterogeneous environments in which clients and services operate. This paper describes a novel approach for addressing this shortcoming: the partitionable services framework, which enables services to be flexibly assembled from multiple components, and facilitates transparent migration and replication of these components at locations closer to the client while still appearing as a single monolithic service. The framework consists of three pieces: (1) declarative specification of services in terms of constituent components; (2) run-time support for dynamic component deployment; and (3) planning policies, which steer the deployment to accomodate underlying environment characteristics. We demonstrate the salient features of the framework and highlight its usability and performance benefits with a case study involving a security-sensitive mail service.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130028036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 48
Adaptive online data compression 自适应在线数据压缩
E. Jeannot, Björn Knutsson, M. Björkman
Quickly transmitting large datasets in the context of distributed computing on wide area networks can be achieved by compressing data before transmission, However such an approach is not efficient when dealing with higher speed networks. Indeed, the time to compress a large file and to send it is greater than the time to send the uncompressed file. In this paper we explore and enhance an algorithm that allows us to overlap communications with compression and to automatically adapt the compression effort to currently available network and processor resources.
在广域网分布式计算环境下,可以通过传输前压缩数据来实现大型数据集的快速传输,但这种方法在处理高速网络时效率不高。实际上,压缩大文件并发送它的时间比发送未压缩文件的时间要长。在本文中,我们探索并增强了一种算法,该算法允许我们将通信与压缩重叠,并自动调整压缩工作以适应当前可用的网络和处理器资源。
{"title":"Adaptive online data compression","authors":"E. Jeannot, Björn Knutsson, M. Björkman","doi":"10.1109/HPDC.2002.1029938","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029938","url":null,"abstract":"Quickly transmitting large datasets in the context of distributed computing on wide area networks can be achieved by compressing data before transmission, However such an approach is not efficient when dealing with higher speed networks. Indeed, the time to compress a large file and to send it is greater than the time to send the uncompressed file. In this paper we explore and enhance an algorithm that allows us to overlap communications with compression and to automatically adapt the compression effort to currently available network and processor resources.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115972849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 70
UNICORE-Globus interoperability: getting the best of both worlds UNICORE-Globus互操作性:两全其美
M. Rambadt, P. Wieder
Summary form only given. This work describes a software prototype developed at Research Center Julich to demonstrate the interoperability between UNICORE (Uniform Interface to Computer Resources) and Globus without changes to any of the systems. By combining UNICORE's workflow oriented approach to job submission with Globus, grid users can gain seamless access to a wide number of Globus enabled systems. We define the following scenario of a job submission from UNICORE to Globus: the user prepares the job via UNICORE's graphical user interface, chooses a Globus site where the job is to be computed and submits it to UNICORE's target system interface (TSI). This is the entity normally interfacing with the local batch system. It is enhanced to communicate with Globus. The TSI translates the job description from the UNICORE specific abstract job object (AJO) into the GRAM Resource Specification Language (RSL) and submits it to the GRAM Gatekeeper. Standard Globus mechanisms are used to monitor the status of the job and transfer the output back to the TSI.
只提供摘要形式。这项工作描述了Julich研究中心开发的一个软件原型,用于演示UNICORE(计算机资源统一接口)和Globus之间的互操作性,而无需更改任何系统。通过将UNICORE面向工作流的作业提交方法与Globus相结合,网格用户可以无缝访问大量启用Globus的系统。我们定义了以下从UNICORE向Globus提交作业的场景:用户通过UNICORE的图形用户界面准备作业,选择要计算作业的Globus站点,并将其提交给UNICORE的目标系统接口(TSI)。这是通常与本地批处理系统接口的实体。增强了与Globus的通信。TSI将工作描述从UNICORE特定的抽象工作对象(AJO)翻译成GRAM资源规范语言(RSL),并将其提交给GRAM Gatekeeper。标准的Globus机制用于监视作业的状态,并将输出传输回TSI。
{"title":"UNICORE-Globus interoperability: getting the best of both worlds","authors":"M. Rambadt, P. Wieder","doi":"10.1109/HPDC.2002.1029952","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029952","url":null,"abstract":"Summary form only given. This work describes a software prototype developed at Research Center Julich to demonstrate the interoperability between UNICORE (Uniform Interface to Computer Resources) and Globus without changes to any of the systems. By combining UNICORE's workflow oriented approach to job submission with Globus, grid users can gain seamless access to a wide number of Globus enabled systems. We define the following scenario of a job submission from UNICORE to Globus: the user prepares the job via UNICORE's graphical user interface, chooses a Globus site where the job is to be computed and submits it to UNICORE's target system interface (TSI). This is the entity normally interfacing with the local batch system. It is enhanced to communicate with Globus. The TSI translates the job description from the UNICORE specific abstract job object (AJO) into the GRAM Resource Specification Language (RSL) and submits it to the GRAM Gatekeeper. Standard Globus mechanisms are used to monitor the status of the job and transfer the output back to the TSI.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126794212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 10
QoS-based resource discovery in intermittently available environments 在间歇性可用的环境中基于qos的资源发现
Yun Huang, N. Venkatasubramanian
In this paper, we address the problem of resource discovery in a grid based multimedia environment, where the resources providers, i.e. servers, are intermittently available. Given a graph theoretic approach, we define and formulate various policies for QoS-based resource discovery with intermittently available servers that can meet a variety of user needs. We evaluate the performance of these policies under various time-map scenarios and placement strategies. Our performance results illustrate the added benefits obtained by adding flexibility to the scheduling process.
在本文中,我们解决了基于网格的多媒体环境中的资源发现问题,其中资源提供者(即服务器)是间歇性可用的。给定图论方法,我们定义并制定了基于qos的资源发现的各种策略,这些策略具有间歇性可用的服务器,可以满足各种用户需求。我们评估了这些政策在不同时间图情景和安置策略下的表现。我们的性能结果说明了通过在调度过程中增加灵活性所获得的额外好处。
{"title":"QoS-based resource discovery in intermittently available environments","authors":"Yun Huang, N. Venkatasubramanian","doi":"10.1109/HPDC.2002.1029903","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029903","url":null,"abstract":"In this paper, we address the problem of resource discovery in a grid based multimedia environment, where the resources providers, i.e. servers, are intermittently available. Given a graph theoretic approach, we define and formulate various policies for QoS-based resource discovery with intermittently available servers that can meet a variety of user needs. We evaluate the performance of these policies under various time-map scenarios and placement strategies. Our performance results illustrate the added benefits obtained by adding flexibility to the scheduling process.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133535361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 26
GridMapper: a tool for visualizing the behavior of large-scale distributed systems GridMapper:大规模分布式系统行为可视化工具
W. Allcock, J. Bester, J. Bresnahan, Ian T Foster, Jarek Gawor, J. Insley, Joseph M. Link, M. Papka
Grid applications can combine the use of computation, storage, network, and other resources. These resources are often geographically distributed, adding to application complexity and thus the difficulty of understanding application performance. We present GridMapper, a tool for monitoring and visualizing the behavior of such distributed systems. GridMapper builds on basic mechanisms for registering, discovering, and accessing performance information sources, as well as for mapping from domain names to physical locations. The visualization system itself then supports the automatic layout of distributed sets of such sources and animation of their activities. We use a set of examples to illustrate how the system can provide valuable insights into the behavior and performance of a range of different applications.
网格应用程序可以结合使用计算、存储、网络和其他资源。这些资源通常是地理上分布的,这增加了应用程序的复杂性,从而增加了理解应用程序性能的难度。我们提出GridMapper,一个用于监控和可视化这种分布式系统行为的工具。GridMapper建立在注册、发现和访问性能信息源以及从域名到物理位置的映射的基本机制之上。可视化系统本身支持这些源的分布式集的自动布局和它们的活动的动画。我们使用一组示例来说明系统如何提供对一系列不同应用程序的行为和性能的有价值的见解。
{"title":"GridMapper: a tool for visualizing the behavior of large-scale distributed systems","authors":"W. Allcock, J. Bester, J. Bresnahan, Ian T Foster, Jarek Gawor, J. Insley, Joseph M. Link, M. Papka","doi":"10.1109/HPDC.2002.1029917","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029917","url":null,"abstract":"Grid applications can combine the use of computation, storage, network, and other resources. These resources are often geographically distributed, adding to application complexity and thus the difficulty of understanding application performance. We present GridMapper, a tool for monitoring and visualizing the behavior of such distributed systems. GridMapper builds on basic mechanisms for registering, discovering, and accessing performance information sources, as well as for mapping from domain names to physical locations. The visualization system itself then supports the automatic layout of distributed sets of such sources and animation of their activities. We use a set of examples to illustrate how the system can provide valuable insights into the behavior and performance of a range of different applications.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131118420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 25
An enterprise-based grid resource management system 基于企业的网格资源管理系统
Q. Snell, K. Tew, J. Ekstrom, M. Clement
As the Internet began its exponential growth into a global information environment, software was often unreliable, slow and had difficulty in interoperating with other systems. Supercomputing node counts also continue to follow high growth trends. Supercomputer and grid resource management software must mature into a reliable computational platform in much the same way that web services matured for the Internet. DOGMA The Next Generation (DOGMA-NG) improves on current resource management approaches by using tested off-the-shelf enterprise technologies to build a robust, scalable, and extensible resource management platform. Distributed web service technologies constitute the core of DOGMA-NG's design and provide fault tolerance and scalability. DOGMA-NG's use of open standard web technologies and efficient management algorithms promises to reduce management time and accommodate the growing size of future supercomputers. The use of web technologies also provides the opportunity for anew parallel programming paradigm, enterprise web services parallel programming, that also gains benefit from the scalable, robust component architecture.
随着互联网开始呈指数级增长,进入全球信息环境,软件往往不可靠,速度慢,难以与其他系统进行互操作。超级计算节点数量也继续保持高增长趋势。超级计算机和网格资源管理软件必须成熟为可靠的计算平台,就像互联网的web服务成熟一样。下一代(DOGMA- ng)通过使用经过测试的现成企业技术来构建健壮的、可伸缩的和可扩展的资源管理平台,从而改进了当前的资源管理方法。分布式web服务技术构成了DOGMA-NG设计的核心,并提供了容错性和可伸缩性。DOGMA-NG使用开放标准的网络技术和高效的管理算法,有望减少管理时间,并适应未来超级计算机不断增长的规模。web技术的使用也为新的并行编程范例——企业web服务并行编程——提供了机会,它也从可伸缩的、健壮的组件体系结构中获益。
{"title":"An enterprise-based grid resource management system","authors":"Q. Snell, K. Tew, J. Ekstrom, M. Clement","doi":"10.1109/HPDC.2002.1029906","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029906","url":null,"abstract":"As the Internet began its exponential growth into a global information environment, software was often unreliable, slow and had difficulty in interoperating with other systems. Supercomputing node counts also continue to follow high growth trends. Supercomputer and grid resource management software must mature into a reliable computational platform in much the same way that web services matured for the Internet. DOGMA The Next Generation (DOGMA-NG) improves on current resource management approaches by using tested off-the-shelf enterprise technologies to build a robust, scalable, and extensible resource management platform. Distributed web service technologies constitute the core of DOGMA-NG's design and provide fault tolerance and scalability. DOGMA-NG's use of open standard web technologies and efficient management algorithms promises to reduce management time and accommodate the growing size of future supercomputers. The use of web technologies also provides the opportunity for anew parallel programming paradigm, enterprise web services parallel programming, that also gains benefit from the scalable, robust component architecture.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116663077","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 13
Location-transparent naming in grid computing using Legion-G 使用Legion-G的网格计算中的位置透明命名
M. Humphrey, S. Arnold, G. Wasson
Globus is a powerful toolkit but lacks location transparency in its naming system, due to a reliance on URLs. In practical terms, this means that a Grid user (or software running on behalf of the user) must know precisely where Grid entities are. The problem is that hardware reconfiguration, file system reorganization, and changes in organizational structure can often result in dangling links. At the University of Virginia, we are designing and implementing a comprehensive project that combines the best aspects of Globus and Legion into Legion-G - roughly an "applications-level" interface from Legion to Globus, whereby Legion "runs on" key Grid functionality of Globus such as GSI. Among the capabilities already supported in Legion, and thus will be delivered to the Globus user, are: end-user tools for transparent remote execution and parameter-space studies; support for dynamic, transparent remote instantiation of transient Grid services, with integrated scheduling support; fine-grained access control for Grid services; and the Legion programming model which supports arbitrary, asynchronous, data-flow-style, secure Grid computations. This poster describes the Legion-G support for location-transparent naming in Grid Computing and illustrates its value in the context of Globus MPI computations that accesses LegionFS which is a location-transparent, Grid-enabled distributed file system.
Globus是一个功能强大的工具包,但由于依赖url,它的命名系统缺乏位置透明性。实际上,这意味着Grid用户(或代表用户运行的软件)必须精确地知道Grid实体的位置。问题是硬件重新配置、文件系统重组和组织结构的更改通常会导致悬空链接。在弗吉尼亚大学,我们正在设计和实现一个综合项目,将Globus和Legion的最佳方面结合到Legion- g中——大致是一个从Legion到Globus的“应用程序级”接口,因此Legion“运行”在Globus的关键网格功能(如GSI)上。Legion已经支持并将交付给Globus用户的功能包括:用于透明远程执行和参数空间研究的最终用户工具;支持瞬态网格服务的动态、透明的远程实例化,并具有集成的调度支持;网格服务的细粒度访问控制;军团编程模型支持任意的、异步的、数据流风格的、安全的网格计算。这张海报描述了Legion-G在网格计算中对位置透明命名的支持,并说明了它在访问LegionFS的Globus MPI计算上下文中的价值,LegionFS是一个位置透明的、支持网格的分布式文件系统。
{"title":"Location-transparent naming in grid computing using Legion-G","authors":"M. Humphrey, S. Arnold, G. Wasson","doi":"10.1109/HPDC.2002.1029948","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029948","url":null,"abstract":"Globus is a powerful toolkit but lacks location transparency in its naming system, due to a reliance on URLs. In practical terms, this means that a Grid user (or software running on behalf of the user) must know precisely where Grid entities are. The problem is that hardware reconfiguration, file system reorganization, and changes in organizational structure can often result in dangling links. At the University of Virginia, we are designing and implementing a comprehensive project that combines the best aspects of Globus and Legion into Legion-G - roughly an \"applications-level\" interface from Legion to Globus, whereby Legion \"runs on\" key Grid functionality of Globus such as GSI. Among the capabilities already supported in Legion, and thus will be delivered to the Globus user, are: end-user tools for transparent remote execution and parameter-space studies; support for dynamic, transparent remote instantiation of transient Grid services, with integrated scheduling support; fine-grained access control for Grid services; and the Legion programming model which supports arbitrary, asynchronous, data-flow-style, secure Grid computations. This poster describes the Legion-G support for location-transparent naming in Grid Computing and illustrates its value in the context of Globus MPI computations that accesses LegionFS which is a location-transparent, Grid-enabled distributed file system.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116709229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
The GridLab grid application toolkit GridLab网格应用程序工具包
Gabrielle Allen, Kelly Davis, Thomas Dramlitsch, T. Goodale, I. Kelley, Gerd Lanfermann, Jason Novotny, T. Radke, Kashif Rasul, Michael Russell, E. Seidel, Oliver Wehrens
We present a synopsis of the Grid Application Toolkit, under development in the EU GridLab project, along with some of the new application scenarios which it will enable.
我们简要介绍了网格应用程序工具包(Grid Application Toolkit),它正在EU GridLab项目中开发,以及它将支持的一些新应用场景。
{"title":"The GridLab grid application toolkit","authors":"Gabrielle Allen, Kelly Davis, Thomas Dramlitsch, T. Goodale, I. Kelley, Gerd Lanfermann, Jason Novotny, T. Radke, Kashif Rasul, Michael Russell, E. Seidel, Oliver Wehrens","doi":"10.1109/HPDC.2002.1029941","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029941","url":null,"abstract":"We present a synopsis of the Grid Application Toolkit, under development in the EU GridLab project, along with some of the new application scenarios which it will enable.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116732785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 16
Multigrain parallelism for eigenvalue computations on networks of clusters 簇网络特征值计算的多粒并行性
James R. McCombs, A. Stathopoulos
Clusters of workstations have become a cost-effective means of performing scientific computations. However, large network latencies, resource sharing, and heterogeneity found in networks of clusters and Grids can impede the performance of applications not specifically tailored for use in such environments. A typical example is the traditional fine grain implementations of Krylov-like iterative methods, a central component in many scientific applications. To exploit the potential of these environments, advances in networking technology must be complemented by advances in parallel algorithmic design. In this paper, we present an algorithmic technique that increases the granularity of parallel block iterative methods by inducing additional work during the preconditioning (inexact solution) phase of the iteration. During this phase, each vector in the block is preconditioned by a different subgroup of processors, yielding a much coarser granularity. The rest of the method comprises a small portion of the total time and is still implemented in fine grain. We call this combination of fine and coarse grain parallelism multigrain. We apply this idea to the block Jacobi-Davidson eigensolver, and present experimental data that shows the significant reduction of latency effects on networks of clusters of roughly equal capacity and size. We conclude with a discussion on how multigrain can be applied dynamically based on runtime network performance monitoring.
工作站集群已经成为执行科学计算的一种经济有效的手段。然而,在集群和网格网络中发现的大型网络延迟、资源共享和异构性可能会阻碍应用程序的性能,这些应用程序不是专门为在这种环境中使用而定制的。一个典型的例子是Krylov-like迭代方法的传统细粒度实现,这是许多科学应用的核心组件。为了开发这些环境的潜力,网络技术的进步必须与并行算法设计的进步相辅相成。在本文中,我们提出了一种算法技术,通过在迭代的预处理(不精确解)阶段引入额外的工作来增加并行块迭代方法的粒度。在此阶段,块中的每个向量都由不同的处理器子组进行预处理,从而产生更粗的粒度。该方法的其余部分只占总时间的一小部分,并且仍然以细粒度实现。我们把这种细粒和粗粒并行性的结合称为杂粮。我们将这一想法应用于块Jacobi-Davidson特征解算器,并提供实验数据,显示在容量和大小大致相等的集群网络上显著减少了延迟效应。最后,我们讨论了如何基于运行时网络性能监控动态应用多粒。
{"title":"Multigrain parallelism for eigenvalue computations on networks of clusters","authors":"James R. McCombs, A. Stathopoulos","doi":"10.1109/HPDC.2002.1029912","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029912","url":null,"abstract":"Clusters of workstations have become a cost-effective means of performing scientific computations. However, large network latencies, resource sharing, and heterogeneity found in networks of clusters and Grids can impede the performance of applications not specifically tailored for use in such environments. A typical example is the traditional fine grain implementations of Krylov-like iterative methods, a central component in many scientific applications. To exploit the potential of these environments, advances in networking technology must be complemented by advances in parallel algorithmic design. In this paper, we present an algorithmic technique that increases the granularity of parallel block iterative methods by inducing additional work during the preconditioning (inexact solution) phase of the iteration. During this phase, each vector in the block is preconditioned by a different subgroup of processors, yielding a much coarser granularity. The rest of the method comprises a small portion of the total time and is still implemented in fine grain. We call this combination of fine and coarse grain parallelism multigrain. We apply this idea to the block Jacobi-Davidson eigensolver, and present experimental data that shows the significant reduction of latency effects on networks of clusters of roughly equal capacity and size. We conclude with a discussion on how multigrain can be applied dynamically based on runtime network performance monitoring.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129468639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 5
Adaptive timeout discovery using the Network Weather Service 使用网络天气服务进行自适应超时发现
Matthew S. Allen, R. Wolski, J. Plank
In this paper we present a novel methodology for improving the performance and dependability of application-level messaging in Grid systems. Based on the Network Weather Service, our system uses nonparametric statistical forecasts of request-response times to automatically determine message timeouts. By choosing a timeout based on predicted network performance, the methodology improves application and Grid service performance as extraneous and overly-long timeouts are avoided. We describe the technique, the additional execution and programming overhead it introduces, and demonstrate the effectiveness using a wide-area test application.
在本文中,我们提出了一种新的方法来提高网格系统中应用级消息传递的性能和可靠性。基于网络天气服务,我们的系统使用请求-响应时间的非参数统计预测来自动确定消息超时。通过根据预测的网络性能选择超时,该方法可以提高应用程序和网格服务的性能,因为避免了不必要的和过长的超时。我们描述了该技术,它引入的额外执行和编程开销,并使用广域测试应用程序演示了其有效性。
{"title":"Adaptive timeout discovery using the Network Weather Service","authors":"Matthew S. Allen, R. Wolski, J. Plank","doi":"10.1109/HPDC.2002.1029901","DOIUrl":"https://doi.org/10.1109/HPDC.2002.1029901","url":null,"abstract":"In this paper we present a novel methodology for improving the performance and dependability of application-level messaging in Grid systems. Based on the Network Weather Service, our system uses nonparametric statistical forecasts of request-response times to automatically determine message timeouts. By choosing a timeout based on predicted network performance, the methodology improves application and Grid service performance as extraneous and overly-long timeouts are avoided. We describe the technique, the additional execution and programming overhead it introduces, and demonstrate the effectiveness using a wide-area test application.","PeriodicalId":279053,"journal":{"name":"Proceedings 11th IEEE International Symposium on High Performance Distributed Computing","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116413078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 9
期刊
Proceedings 11th IEEE International Symposium on High Performance Distributed Computing
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1