2005 IEEE International Conference on Cluster Computing最新文献_第7页

Providing Local ORB-Like Services to Collocated CORBA Components 为配置的CORBA组件提供类似orb的本地服务

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347018

H. Momeni, T. Rahmani, M. Sharifi, V. Rafe

{"title":"Providing Local ORB-Like Services to Collocated CORBA Components","authors":"H. Momeni, T. Rahmani, M. Sharifi, V. Rafe","doi":"10.1109/CLUSTR.2005.347018","DOIUrl":"https://doi.org/10.1109/CLUSTR.2005.347018","url":null,"abstract":"The CORBA Component Model (CCM) middleware provides a standard way to configure, manage and deploy distributed components. However, some current implementation of CCM is flawed with unreasonable communication overhead when components are in the same address space. Previous attempts to alleviate this drawback have tried to provide mechanisms for direct local communication of such components, but have sacrificed ORB services all together. Since such components do not communicate through ORB. They are deprived from ORB services such as events and naming. In case of need, programmers should implement such services themselves. This paper presents an alternative approach that likewise eliminates the unnecessary communication overhead between local components, but in addition provides them with local ORB-like services. A unit inside each container is made responsible for directing the communications between components within or outside the container. In case of local communications, requests are passed to the local components without ORB involvement. ORB-like services, namely events and naming, are provided by this unit locally for local components. Implementation results of the proposed approach with local event and naming services support show a favorable reduction of local communication overheads","PeriodicalId":255312,"journal":{"name":"2005 IEEE International Conference on Cluster Computing","volume":"419 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122923957","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: 0

VioCluster: Virtualization for Dynamic Computational Domains VioCluster:动态计算域的虚拟化

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347064

P. Ruth, Phil McGachey, Dongyan Xu

引用次数: 136

A Feasibility Analysis of Power Awareness in Commodity-Based High-Performance Clusters 基于商品的高性能集群中权力意识的可行性分析

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347063

C. Hsu, Wu-chun Feng

引用次数: 66

An Infrastructure of Network Services for Seamless Integration in Advanced Collaborative Computing Environments 高级协同计算环境下无缝集成的网络服务基础结构

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347072

Han Gao, I. Judson, T. Uram, S. Lefvert, T. Disz, M. Papka, R. Stevens

{"title":"An Infrastructure of Network Services for Seamless Integration in Advanced Collaborative Computing Environments","authors":"Han Gao, I. Judson, T. Uram, S. Lefvert, T. Disz, M. Papka, R. Stevens","doi":"10.1109/CLUSTR.2005.347072","DOIUrl":"https://doi.org/10.1109/CLUSTR.2005.347072","url":null,"abstract":"Advanced collaborative computing environments are one of the most important tools for integrating high-performance computers and computations and for interacting with colleagues around the world. However, heterogeneous characteristics such as network transfer rates, computational abilities, and hierarchical systems make the seamless integration of distributed resources a challenge. In this paper, we argue that advanced collaborative computing environments need an infrastructure of network services to support distributed and quality guaranteed multimedia applications. Accordingly, we propose the design of network services for high-performance collaborative computing. We present a collaborative environment network service infrastructure (CENSI) to embed network services into various systems intelligently and elastically. We also discuss three management modules: a three-party matching module (resources, requests, and network services), a module for performance monitoring and evaluation of group communications, and a module for distribution topology analysis","PeriodicalId":255312,"journal":{"name":"2005 IEEE International Conference on Cluster Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126682335","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: 0

Fire Phoenix Cluster Operating System Kernel and its Evaluation Fire Phoenix集群操作系统内核及其评价

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347066

Jianfeng Zhan, Ninghui Sun

引用次数: 20

IBRIX File System: Architecture and Design IBRIX文件系统:架构与设计

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347088

Sudhir Srinivasan, Amina Saify, R. Radhakrishnan

{"title":"IBRIX File System: Architecture and Design","authors":"Sudhir Srinivasan, Amina Saify, R. Radhakrishnan","doi":"10.1109/CLUSTR.2005.347088","DOIUrl":"https://doi.org/10.1109/CLUSTR.2005.347088","url":null,"abstract":"Summary form only given. Recently, there have been significant advances in file system technology in the form of cluster, distributed and/or parallel file systems in an attempt to break the I/O bottleneck plaguing the effective utilization of clusters of commodity computers. Successes have been achieved in scaling performance when defined as bandwidth, as typified by sequential access of large files using large I/O sizes. Applications with such access patterns does not represent all application classes to which cluster computing is being applied as a potential solution, the balance being those that access small and medium sized files in a random or sequential manner using small I/O sizes. Specifically, these access patterns perform as many and often more \"metadata\" operations on the file system as data reads or writes. Since metadata operations are at the heart of a file system and impact its integrity, scaling throughput or metadata performance through concurrency across many servers poses the most difficult technical challenge in file system design. This poster will present details about the fundamentally new architecture for constructing parallel file systems called segmented file system that scales linearly for both data and metadata oriented applications. Performance results will be presented with the IBRIX Fusion product (http:Wwww.ibrix.com) based on this architecture using micro benchmarks as well as real applications demonstrating the general-purpose scalability of this architecture. The poster will also show typical I/O cluster offerings from Dell that use IBRIX, using large cluster installations at universities and research labs as an example","PeriodicalId":255312,"journal":{"name":"2005 IEEE International Conference on Cluster Computing","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132486146","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: 1

Robust Processor Allocation for Independent Tasks When Dollar Cost for Processors is a Constraint 处理器成本约束下独立任务的鲁棒处理器分配

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347023

Prasanna Sugavanam, H. Siegel, A. A. Maciejewski, Junxing Zhang, V. Shestak, Michael Raskey, Alan J. Pippin, Ron Pichel, Mohana Oltikar, Ashish M. Mehta, Panho Lee, Yogish G. Krishnamurthy, Aaron Horiuchi, Kumara Guru, Mahir Aydin, M. Al-Otaibi, Shoukat Ali

{"title":"Robust Processor Allocation for Independent Tasks When Dollar Cost for Processors is a Constraint","authors":"Prasanna Sugavanam, H. Siegel, A. A. Maciejewski, Junxing Zhang, V. Shestak, Michael Raskey, Alan J. Pippin, Ron Pichel, Mohana Oltikar, Ashish M. Mehta, Panho Lee, Yogish G. Krishnamurthy, Aaron Horiuchi, Kumara Guru, Mahir Aydin, M. Al-Otaibi, Shoukat Ali","doi":"10.1109/CLUSTR.2005.347023","DOIUrl":"https://doi.org/10.1109/CLUSTR.2005.347023","url":null,"abstract":"In a distributed heterogeneous computing system, the resources have different capabilities and tasks have different requirements. Different classes of machines used in such systems typically vary in dollar cost based on their computing efficiencies. Makespan (defined as the completion time for an entire set of tasks) is often the performance feature that is optimized. Resource allocation is often done based on estimates of the computation time of each task on each class of machines. Hence, it is important that makespan be robust against errors in computation time estimates. The dollar cost to purchase the machines for use can be a constraint such that only a subset of the machines available can be purchased. The goal of this study is to: (1) select a subset of all the machines available so that the cost constraint for the machines is satisfied, and (2) find a static mapping of tasks so that the robustness of the desired system feature, makespan, is maximized against the errors in task execution time estimates. Six heuristic techniques to this problem are presented and evaluated","PeriodicalId":255312,"journal":{"name":"2005 IEEE International Conference on Cluster Computing","volume":"32 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130901043","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: 7

Co-Scheduling Parallel Electronic Structure Calculations in SMP Cluster Environments SMP集群环境下协同调度并行电子结构计算

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347014

Nurzhan Ustemirov, M. Sosonkina

引用次数: 2

Illuminator: a Free Graphics Toolkit for Parallel Visualization of Continuum Field Data 光源:一个免费的图形工具包，用于连续场数据的并行可视化

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347093

A. Powell, O. Ocholi, J. Vieyra, B. Zhou

{"title":"Illuminator: a Free Graphics Toolkit for Parallel Visualization of Continuum Field Data","authors":"A. Powell, O. Ocholi, J. Vieyra, B. Zhou","doi":"10.1109/CLUSTR.2005.347093","DOIUrl":"https://doi.org/10.1109/CLUSTR.2005.347093","url":null,"abstract":"Summary form only given. Illuminator is a visualization toolkit closely coupled with parallel computation and storage. Its close links to PETSc (the portable extensible toolkit for scientific computation) make it ideal for display of finite difference calculation results. During a simulation, Illuminator functions provide parallel storage of PETSc distributed array objects across cluster hard drives with optional lossless or lossy compression. This lets cluster machines operate as a large RAID0 (or optionally RAID1) array, with fast storage and retrieval directly to/from the compute nodes with zero network load. Visualization is similarly parallel: compute nodes load simulation results from their hard drives and calculate triangle locations and colors for contour surfaces of scalar fields. Triangles are then rendered using one of three methods: send all triangle data to the head node and display using Geomview; locally render triangles using Imlib2 and layer images in a binary tree; locally render semitransparent triangles using a multilayer zbuffer, redistribute and assemble these zbuffers for display. Results are discussed in terms of image quality and frame rate","PeriodicalId":255312,"journal":{"name":"2005 IEEE International Conference on Cluster Computing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133506306","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: 0

A Poly-Algorithm for Efficient Parallel Matrix Multiplication on Metacomputing Platforms 元计算平台上高效并行矩阵乘法的一种多算法

2005 IEEE International Conference on Cluster Computing Pub Date : 2005-09-01 DOI: 10.1109/CLUSTR.2005.347020

S. Jeddi, W. Nasri

引用次数: 1