2009 International Conference on Parallel Processing最新文献

Direct N-body Kernels for Multicore Platforms 多核平台的直接n体内核

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.71

Nitin Arora, A. Shringarpure, R. Vuduc

引用次数: 41

Computing Equilibria in Bimatrix Games by Parallel Vertex Enumeration 用并行顶点枚举法计算双矩阵对策的平衡点

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.11

J. Widger, Daniel Grosu

引用次数: 5

Exploring the Cost-Availability Tradeoff in P2P Storage Systems 探讨P2P存储系统的成本-可用性权衡

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.46

Zhi Yang, Yafei Dai, Zhen Xiao

引用次数: 7

Stochastic-Based Robust Dynamic Resource Allocation in a Heterogeneous Computing System 异构计算系统中基于随机的鲁棒动态资源分配

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.45

Jay Smith, E. Chong, A. A. Maciejewski, H. Siegel

引用次数: 25

Performance Characterization of a Hierarchical MPI Implementation on Large-scale Distributed-memory Platforms 大规模分布式存储平台上分层MPI实现的性能表征

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.51

S. Alam, R. Barrett, J. Kuehn, Steve Poole

{"title":"Performance Characterization of a Hierarchical MPI Implementation on Large-scale Distributed-memory Platforms","authors":"S. Alam, R. Barrett, J. Kuehn, Steve Poole","doi":"10.1109/ICPP.2009.51","DOIUrl":"https://doi.org/10.1109/ICPP.2009.51","url":null,"abstract":"The building blocks of emerging Petascale massively parallel processing (MPP) systems are multi-core processors with four or more cores as a single processing element and a customized network interface. The resulting memory and communication hierarchy of these platforms are now exposed to application developers and end users by creating a hierarchical or multi-core aware message-passing (MPI) programming interface and by providing a handful of runtime, tunable parameters that allows mapping and control of MPI tasks and message handling. We characterize performance of MPI communication patterns and present strategies for optimizing applications performance on Cray XT series systems that are composed of contemporary AMD processors and a proprietary network infrastructure. We highlight dependencies in its memory and network subsystems, which could influence production-level applications performance. We demonstrate that MPI micro-benchmarks could mislead an application developer or end user since these benchmarks often do not expose the interplay between memory allocation and usage in the user space, which depends on the number of tasks or cores and workload characteristics. Our studies show performance improvements compared to the default options for our target scientific benchmarks and production-level applications.","PeriodicalId":169408,"journal":{"name":"2009 International Conference on Parallel Processing","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125667825","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

Mediacoop: Hierarchical Lookup for P2P-VoD Services Mediacoop: P2P-VoD服务的分层查找

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.58

Tieying Zhang, Jianming Lv, Xueqi Cheng

引用次数: 4

GePSeA: A General-Purpose Software Acceleration Framework for Lightweight Task Offloading GePSeA:用于轻量级任务卸载的通用软件加速框架

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.39

Ajeet Singh, P. Balaji, W. Feng

引用次数: 14

Fast Isosurface Extraction for Medical Volume Dataset on Cell BE 基于Cell BE的医学体数据集快速等值面提取

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.47

Hai Jin, Bo Li, Ran Zheng, Qin Zhang

{"title":"Fast Isosurface Extraction for Medical Volume Dataset on Cell BE","authors":"Hai Jin, Bo Li, Ran Zheng, Qin Zhang","doi":"10.1109/ICPP.2009.47","DOIUrl":"https://doi.org/10.1109/ICPP.2009.47","url":null,"abstract":"The size of volumetric data generated by medical imaging and scientific simulations is increased significantly due to the dramatic advances in medical imaging modalities and computing technologies. The volumetric data generally need to be visualized and Marching Cubes algorithm (MC for short) is one of the standard methods of the isosurface extraction for the medical applications. However, MC algorithm requires a large amount of data computing power. The Cell Broadband Engine (Cell for short) processor, which is a typical COTS (commodity off-the-shelf) heterogeneous designed to handle extremely demanding computations, can be used to hasten isosurface extraction in medial application. In this paper, we present a streaming model-based scheme to efficiently map MC algorithm to Cell. Specifically, a block-based filter running on PPE is imposed as a preprocessing stage to avoid unnecessary data transfer and computation, and the MC kernel runs on SPEs as the subsequent stage. Through tuning the size of the block, the workload of PPE and SPE is orchestrated harmoniously. The experimental results demonstrate that overall isosurface extraction speedup of more than 10 times is achieved compared with conventional heavy iron CPUs.","PeriodicalId":169408,"journal":{"name":"2009 International Conference on Parallel Processing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131655819","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

A Parallel Algorithm for Computing Betweenness Centrality 一种计算中间性中心性的并行算法

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.53

Guangming Tan, Dengbiao Tu, Ninghui Sun

引用次数: 43

Performance Analysis of DHT Algorithms for Range-Query and Multi-Attribute Resource Discovery in Grids 网格中距离查询和多属性资源发现的DHT算法性能分析

2009 International Conference on Parallel Processing Pub Date : 2009-09-22 DOI: 10.1109/ICPP.2009.37

Haiying Shen, Chengzhong Xu

{"title":"Performance Analysis of DHT Algorithms for Range-Query and Multi-Attribute Resource Discovery in Grids","authors":"Haiying Shen, Chengzhong Xu","doi":"10.1109/ICPP.2009.37","DOIUrl":"https://doi.org/10.1109/ICPP.2009.37","url":null,"abstract":"Resource discovery is critical to the usability and accessibility of grid computing systems. Distributed Hash Table (DHT) has been applied to grid systems as a distributed mechanism for providing scalable range-query and multiattribute resource discovery. Multi-DHT-based approaches depend on multiple DHT networks with each network responsible for a single attribute. Single-DHT-based approaches keep the resource information of all attributes in a single node. Both classes of approaches lead to high overhead. Recently, we proposed a heuristic Low-Overhead Range-query Multiattribute DHT-based resource discovery approach (LORM). It relies on a single hierarchical DHT network and distributes resource information among nodes in balance by taking advantage of the hierarchical structure. We demonstrated its effectiveness and efficiency via simulation. In this paper, we analyze the performance of the LORM approach rigorously by comparing it with other multi-DHT-based and single-DHTbased approaches with respect to their overhead and efficiency. The analytical results are consistent with simulation results. The results prove the superiority of the LORM approach in theory","PeriodicalId":169408,"journal":{"name":"2009 International Conference on Parallel Processing","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133041890","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