检索结果-内蒙古大学图书馆

Efficient data distribution scheme for multi-dimensional sparse arrays

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2007年第1期23卷 315-327页

作者： Lin, Chun-Yuan Chung, Yeh-Ching Natl Tsing Hua Univ Inst Mol & Cellular Biol Hsinchu 300 Taiwan Natl Tsing Hua Univ Dept Comp Sci Hsinchu 300 Taiwan

Array operations are useful in a large number of important scientific codes, such as molecular dynamics, finite-element methods, climate modeling, etc. It is a challenging problem to provide an efficient data distribution for irregular problems. Multi-dimensional (AM) sparse array operations can be used in atmosphere and ocean sciences, image processing, etc., and have been an extensively investigated problem. In our previous work, a data distribution scheme, Encoding-Decoding (ED), was proposed for two-dimensional (2D) sparse arrays. In this paper, ED is extended to be useful for MD sparse arrays first. then, the performance of ED is compared with that of Send Followed Compress (SFC) and Compress Followed Send (CFS). Both theoretical analysis and experimental tests were conducted and then shown that ED is superior to SFC and CFS for all of evaluated criteria.

关键词： data compression method data distribution scheme data layout distributed memory multicomputers sparse ratio sparse array

来源：评论

学校读者我要写书评

暂无评论

A fast topology inference: A building block for network-aware parallel processing 07

A fast topology inference: A building block for network-awar...

引用

16th international symposium on High Performance distributed computing 2007, HPDC'07 and Co-Located Workshops

作者： Shirai, Tatsuya Saito, Hideo Taura, Kenjiro University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo Japan

ISBN: (纸本)1595936734

Adapting to the network is the key to achieving high performance for communication-intensive applications, including scientific computing,data intensive computing, and multicast, especially in Grid environments. this paper investigates an approach of representing network as a tree of participating hosts and switches matching or approximating their physical topology, and describes a fast, non-intrusive, and portable algorithm for inferring such a topology. this representation and the proposed inference algorithm serves as a key to building network-aware applications in a portable manner. the algorithm is based solely on RTTs of small packets between end hosts;it does not rely on popular but not universally available protocols such as trace route and SNMP. Another benefit is that it can handle all layers of network uniformly without any a priori knowledge of cluster configurations. the required number of measurements is O(Nd) in certain idealizing assumptions made for the purpose of analysis, where N is the number of participating processes and d the diameter of the network, which is usually small in real networks. In our experimental environment, the inference algorithm built a topology of 64 hosts in a single cluster in 4 seconds and and that of 256 hosts across 4 clusters in 15 seconds. It is able to not only identify clusters within a Grid, but also to partially identify the Layer 2 topology within a cluster. this is important for optimizing bandwidth-limited operations such as broadcast. We built several network-aware applications upon the inference system, including efficient bandwidth measurements and long message broadcasts. the topology is used to schedule as many measurements as possible in parallel without competing on shared links. We were able to build a bandwidth map of 256 hosts across 4 clusters in 27 seconds. Copyright 2007 ACM.

关键词： Computer networks

来源：评论

学校读者我要写书评

暂无评论

P2P file sharing in wireless mesh networks

引用

7th international symposium on Advanced parallel Processing Technologies

作者： Luo Huiqiong Ding Xuyang Lao Hansheng Wang Wenmin Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610054 Peoples R China Coll Zhongshan Torch Profess Zhongshan 528437 Peoples R China

ISBN: (纸本)9783540768364

In wireless mesh networks, the connective time would be relatively short in multi-hop nodes because of the mobility of peer nodes and the wireless collision. therefore, it is important that how peers choose reasonable schemes to gain more benefits and improve the networks performance when they implement the peer-to-peer file sharing in limited environment. On the basis of the researches of peer-to-peer file sharing and the inherent characteristic of wireless mesh networks, a novel venture investment based file sharing model is proposed. the model provides a mechanism to maximize investment benefit and minimize investment venture, and makes optimization investment schemes through a benefit evaluation method. the simulation results show that the venture investment model can assist networks nodes to invest file sharing effectively and improve the performance of networks.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

A flexible job scheduling system for heterogeneous grids

引用

7th international symposium on Advanced parallel Processing Technologies

作者： Cheng, Lan Jin, Hai Qi, Li Tao, Yongcai Huazhong Univ Sci & Technol Sch Comp Sci & Technol Cluster & Grid Comp Lab Serv Comp Technol & Syst Lab Wuhan 430074 Peoples R China

ISBN: (纸本)9783540768364

Job management is the most complicated and kernel component of grid system. However, due to the dynamic, heterogeneous and dispersed nature of grid environment, grid job submission and scheduling are always intractable issues that needs to be addressed, especially across heterogeneous grids. In this paper, a Flexible Job Scheduling System (FISS) is designed, which exploits and extends JSDL to support the job submission with different QoS requirements across heterogeneous grid platforms. Based on the extended JSDL, multiple types of jobs are supported, including WS, WSRF, GRS. Moreover, it conduces to the interoperation among heterogeneous grid systems. Experiments are carried out and proven that FISS proposed in the paper can improve the efficiency and utilization of grid system while satisfying users' QoS requirements and achieving the interoperability among heterogeneous grids.

关键词： Grid computing

来源：评论

学校读者我要写书评

暂无评论

A computational framework for cardiac modeling based on distributed computing and web applications

A computational framework for cardiac modeling based on dist...

引用

7th international Conference on High Performance computing for Computational Science

作者： Martins, D. M. S. Campos, F. O. Ciuffo, L. N. Oliveira, R. S. Amorim, R. M. Vieira, V. F. Ebecken, N. F. F. Barbosa, C. B. dos Santos, R. Weber Univ Fed Juiz Fora Dept Comp Sci Juiz De Fora MG Brazil Univ Fed Rio de Janeiro Dept Comp Sci Rio De Janeiro Rio De Janeiro Brazil

ISBN: (纸本)9783540713500

Cardiac modeling is here to stay. Computer models are being used in a variety of ways and support the tests of drugs, the development of new medical devices and non-invasive diagnostic techniques. Computer models have become valuable tools for the study and comprehension of the complex phenomena of cardiac electrophysiology. However, the complexity and the multidisciplinary nature of cardiac models still restrict its use to a few specialized research centers in the world. We propose a computational framework that provides support for cardiac electrophysiology modeling. this framework integrates different computer tools and allows one to bypass many complex steps during the development and use of cardiac models. the implementation of cardiac cell models is automatically provided by a tool that translates models described in CellML language to executable code that allows one to manipulate and solve the models numerically. the automatically generated cell models are integrated in an efficient 2-dimensional parallel cardiac simulator. the set up and use of the simulator is supported by a user-friendly graphical interface that offers the tasks of simulation configuration, parallel execution in a pool of connected computer clusters, storage of results and basic visualization. All these tools are being integrated in a Web portal that is connected to a pool of clusters. the Web portal allows one to develop and simulate cardiac models efficiently via this user-friendly integrated environment. As a result, the complex techniques and the know-how behind cardiac modeling are all taken care of by the web distributed applications.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Exploiting lustre file joining for effective collective IO 07

Exploiting lustre file joining for effective collective IO

引用

7th IEEE international symposium on Cluster computing and the Grid

作者： Yu, Weikuan Vetter, Jeffrey Canon, R. Shane Jiang, Song Oak Ridge Natl Lab Oak Ridge TN 37831 USA Wayne State Univ Detroit MI 48202 USA

ISBN: (纸本)9780769528335

Lustre is, a parallel file system that presents high aggregated 10 bandwidth by striping file extents across many storage devices. However, our experiments indicate excessively wide striping can cause performance degradation. Lustre supports an innovative file joining feature that joins files in place. To mitigate striping overhead and benefit collective 10, we propose two techniques: split writing and hierarchical striping. hi split writing, a file is created as separate subfiles, each of which is striped to only a few storage devices. they are joined as a single file at the file close time. Hierarchical striping builds on top of split writing and orchestrates the span of subfiles in a hierarchical manner to avoid overlapping and achieve the appropriate coverage of storage devices. Together, these techniques can avoid the overhead associated with large stripe width, while still being able to combine bandwidth available from many storage devices. We have prototyped these techniques in the ROMIO implementation of MPI-IO. Experimental results indicate that split writing and hierarchical striping can significantly improve the performance of Lustre collective 10 in terms of both data transfer and management operations. On a Lustre file system configured with 46 object storage targets, our implementation improves collective write performance of a 16-process job by as much as 220%.

关键词： File systems Writing Bandwidth Application software Degradation Prototypes Software libraries Scalability Biology computing Laboratories

来源：评论

学校读者我要写书评

暂无评论

Understanding the impact of multi-core architecture in cluster computing: A case study with intel dual-core system 07

Understanding the impact of multi-core architecture in clust...

引用

7th IEEE international symposium on Cluster computing and the Grid

作者： Chai, Lei Gao, Qi Panda, Dhabaleswar K. Ohio State Univ Dept Comp Sci & Engn Columbus OH 43210 USA

ISBN: (纸本)9780769528335

Multi-core processors are growing as a new industry trend as single core processors rapidly reach the physical limits of possible complexity and speed. In the new Top500 supercomputer list, more than 20% processors belong to the multi-core processor family However without an in-depth study on application behaviors and trends on multi-core clusters, we might not be able to understand the characteristics of multi-core cluster in a comprehensive manner and hence not be able to get optimal performance. In this paper, we take on these challenges and design a set of experiments to study the impact of multi-core architecture on cluster computing. We choose to use one of the most advanced multi-core servers, Intel Bensley system with Wood-crest processors, as our evaluation Platform, and use benchmarks including HPL, NAMD, and NAS as the applications to study From our message distribution experiments, we find that on an average about 50% messages are transferred through intra-Node communication, which is much higher than intuition. this trend indicates that optimizing intra-node communication is as important as optimizing internode communication in a multi-core cluster We also observe that cache and memory, contention may be a potential bottleneck in multi-core clusters, and communication middleware and applications should be multi-core aware to alleviate this problem. We demonstrate that multi-core aware algorithm, e.g. data tiling, improves benchmark execution time by up to 70%. We also compare the scalability of a multi-core cluster with that of a single-core cluster and find that the scalability of the multi-core cluster is promising.

关键词： Computer architecture Multicore processing Scalability Middleware Supercomputers Sun Moore's Law Costs parallel processing Grid computing

来源：评论

学校读者我要写书评

暂无评论

Metaserver locality and scalability in a distributed NFS

Metaserver locality and scalability in a distributed NFS

引用

7th international Meeting on High-Performance computing for Computational Science, VECPAR 2006

作者： Hermann, Everton Ávila, Rafael Navaux, Philippe Denneulin, Yves Instituto de Informática/UFRGS Caixa Postal 15064 91501-970 Porto Alegre Brazil Laboratoire ID/IMAG 51 avenue Jean Kuntzmann 38330 Montbonnot-Saint Martin France

ISBN: (纸本)9783540713500

the leveraging of existing storage space in a cluster is a desirable characteristic of a parallel file system. While undoubtedly an advantage from the point of view of resource management, this possibility may face the administrator with a wide variety of alternatives for configuring the file server, whose optimal layout is not always easy to devise. Given the diversity of parameters such as the number of processors on each node and the capacity and topology of the network, decisions regarding the locality of server components like metadata servers and I/O servers have a direct impact on performance and scalability. In this paper, we explore the capabilities of the dNFSp file system on a large cluster installation, observing how scalable the system behaves in different scenarios and comparing it to a dedicated parallel file system. Our obtained results show that the design of dNFSp allows for a scalable and resource-saving configuration for clusters with a large number of nodes. © Springer-Verlag Berlin Heidelberg 2007.

关键词： distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic regions of interest for interactive flow exploration

Dynamic regions of interest for interactive flow exploration

引用

7th Eurographics symposium on parallel Graphics and Visualization, EGPGV 2007

作者： Wolter, M. Bischof, C. Kuhlen, T. Virtual Reality Group RWTH Aachen University Germany Institute for Scientific Computing RWTH Aachen University Germany

ISBN: (纸本)9783905673500

Virtual Reality (VR) provides a useful tool for understanding complex, unsteady flow phenomena. the user can directly interact with the data and therefore benefits from a spatial coherence of action and result. However, visualization in virtual environments imposes very high demands on interactivity in order to maintain this coherence. Exploration of large, unsteady datasets in VR requires efficient visualization or data reduction algorithms to produce results within acceptable waiting times. We propose a technique for reducing required data especially suited for direct interaction in virtual environments. We use a distributed system to parallely extract a dynamic region of interest (DROI) from the simulation data. this DROI is adapted according to the user’s interaction behavior and allows for the analysis of local flow features. With this reduction we provide interactive extraction of local features from large, time-varying datasets. © the Eurographics Association 2007.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multilingual interfaces for parallel coupling in multiphysics and multiscale systems

Multilingual interfaces for parallel coupling in multiphysic...

引用

7th international Conference on Computational Science (ICCS 2007)

作者： Ong, Everest T. Larson, J. Walter Norris, Boyana Jacob, Robert L. Tobis, Michael Steder, Michael Univ Wisconsin Dept Atmospher & Ocean Sci Madison WI 53706 USA Argonne Natl Lab Math & Comp Sci Div Argonne IL 60439 USA Australian Natl Univ ANU Supercomp Facil Canberra ACT 0200 Australia Univ Chicago Dept Geophys Sci Chicago IL 60637 USA

ISBN: (纸本)9783540725831

Multiphysics and multiscale simulation systems are emerging as a new grand challenge in computational science, largely because of increased computing power provided by the distributed-memory parallel programming model on commodity clusters. these systems often present a parallel coupling problem in their intercomponent data exchanges. Another potential problem in these coupled systems is language interoperability between their various constituent codes. In anticipation of combined parallel coupling/language interoperability challenges, we have created a set of interlanguage bindings for a successful parallel coupling library, the Model Coupling Toolkit. We describe the method used for automatically generating the bindings using the Babel language interoperability tool, and illustrate with short examples how MCT can be used from the C++ and Python languages. We report preliminary performance reports for the MCT interpolation benchmark. We conclude with a discussion of the significance of this work to the rapid prototyping of large parallel coupled systems.

关键词： Interfaces (computer)

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：