检索结果-内蒙古大学图书馆

distributed predicate detection in series-parallel systems

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2002年第4期13卷 373-387页

作者： Dumais, G Li, HF Silanis Technol Inc St Laurent PQ Canada Concordia Univ Dept Comp Sci Montreal PQ H3G 1M8 Canada

This paper addresses the problems of state space decomposition and predicate detection in a distributed computation involving asynchronous messages. We introduce a natural communication dependency which leads to the definition of the communication graph. This abstraction proves to be a useful too[ to decompose the state lattice of a distributed computation into simpler structures, known as concurrent intervals. Efficient algorithms have been proposed in the literature to detect special classes of predicates, such as conjunctive predicates and bounded sum predicates. We show that more general classes of predicates can be detected when proper constraints are imposed on the underlying computations. In particular, we introduce a class of predicates, defined herein as separable predicates, that properly includes the above-mentioned classes. We show that separable predicates can be efficiently detected on distributed computations whose communication graphs satisfy the series-parallel constraint.

关键词： distributed computation predicate detection state lattice concurrent interval communication graph series-parallel structure separable predicate

来源：评论

学校读者我要写书评

暂无评论

On distributing the clustering process

引用

PATTERN RECOGNITION LETTERS 2002年第8期23卷 999-1008页

作者： Boutsinas, B Gnardellis, T Univ Patras Dept Business Adm GR-26500 Patras Greece UPAIRC Patras Greece Dept Comp Engn & Informat IS&AI Lab GR-26500 Patras Greece

Clustering algorithms require a large amount of computations of distances among patterns and centers of clusters, Hence, their complexity is dominated by the number of patterns. On the other hand, there is an explosive growth of business or scientific databases storing huge volumes of data. One of the main challenges of today's knowledge discovery systems is their ability to scale up to very large data sets. In this paper, we present a clustering methodology for scaling up any clustering algorithm. It is an iterative process that it is based on partitioning a sample of data into subsets. We, also, present extensive empirical tests that demonstrate the proposed methodology reduces the time complexity and at the same time may maintain the accuracy that would be achieved by a single clustering algorithm supplied with all the data. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： data mining clustering meta-learning parallel processing distributed computation

来源：评论

学校读者我要写书评

暂无评论

DASH - distributed analysis system hierarchy

DASH - distributed analysis system hierarchy

引用

Conference on Astronomical Data Analysis II

作者： Yagi, M Yoshihiko, M Ogasawara, R Kosugi, G Takata, T Ishihara, Y Yokono, Y Morita, Y Nakamoto, H Watanabe, N Ukawa, K Natl Astron Observ Mitaka Tokyo 1818588 Japan

ISBN: (纸本)0819446262

We have developed and are operating an object-oriented data reduction and data analysis system, DASH ( distributed Analysis Software Hierarchy), for efficient data processing for SUBARU telescope. In DASH, all information for reducing a set of data is packed into an abstracted object, named as "Hierarchy". It contains rules how to search calibration data, reduction procedure to the final result, and also the reduction log. With Hierarchy, DASH works as an automated reduction pipeline platform cooperated with STARS (Subaru Telescope ARchive System). DASH is implemented on CORBA and Java technology. The portability of these technology enables us to make a subset of the system for a small stand-alone system, SASH. SASH is compatible with DASH and one can continuously reduce and analyze. data between DASH and SASH.

关键词： pipeline data reduction data analysis distributed computation Subaru CORBA

来源：评论

学校读者我要写书评

暂无评论

distributed storage and control system of the Subaru Telescope on the high speed wide area connection

Distributed storage and control system of the Subaru Telesco...

引用

Conference on Advanced Global Communications Technologies for Astronomy II

作者： Ogasawara, R Kosugi, G Takata, T Yagi, M Chikada, Y Mizumoto, Y Chiba, K Inoue, G Furuichi, M Iwashita, D NAOJ Subaru Telescope Hilo HI 96720 USA

ISBN: (纸本)0819446246

In order to achieve an effective operation and research based on data taken by the Subaru Telescope, we installed a satellite storage and analysis system at Mitaka headquarters of Naoj, on March 2002. Data taken by instruments by Subaru Telescope located at the summit of Mauna Kea is transferred to the STN-II system at Hilo base, and satellite system at Mitaka through the OC3 dedicated network link between Hilo and Mitaka. In Japan, an academic research backbone, SuperSINET spans among various universities and institutes with 10Gbps bandwidth at most, and it is easy for astronomers from Japan to access Subaru data through high speed backbone network in Japan. Database on each site, Hilo and Mitaka, are maintained independently, however, all records and history of updating are transferred each other frequently enough to make it possible for recovery in case of any discrepancy among database. Since the round trip time of the light signal between Hawaii and Japan could not be reduced 45msec, we need a special tuning not only for the data transfer between those two node, but also for the remote control sequence.

关键词： Subaru Telescope high speed network data management remote database distributed computation

来源：评论

学校读者我要写书评

暂无评论

Performance characterization of a molecular dynamics code on PC clusters: Is there any easy parallelism in CHARMM? 16

Performance characterization of a molecular dynamics code on...

引用

16th International Parallel and distributed Processing Symposium, IPDPS 2002

作者： Taufer, M. Perathoner, E. Cavalli, A. Caflisch, A. Stricker, T. Department of Computer Science ETH Zurich Zentrum ZurichCH-8092 Switzerland Department of Biochemistry University of Zurich ZurichCH-8057 Switzerland Università degli Studi di Padova Dipartimento di Elettronica ed Informatica Via Gradenigo 6/a Padova Italy

ISBN: (纸本)0769515738

The molecular dynamics code CHARMM is a popular research tool for computational biology. An increasing number of researchers are currently looking for affordable and adequate platforms to execute CHARMM or similar codes. To address this need, we analyze the resource requirements of a CHARMM molecular dynamics simulation on PC clusters with a particle mesh Ewald (PME) treatment of long range electrostatics, and investigate the scalability of the short-range interactions and PME separately. We look at the workload characterization and the performance gain of CHARMM with different network technologies and different software infrastructures and show that the performance depends more on the software infrastructures than on the hardware components. In the present study, powerful communication systems like Myrinet deliver performance that comes close to the MPP supercomputers of the past decade, but improved scalability can also be achieved with better communication system software like SCore without the additional hardware cost. The experimental method of workload characterization presented can be easily applied to other codes. The detailed performance figures of the breakdown of the calculation into computation, communication and synchronization allow one to derive good estimates about the benefits of moving applications to novel computing platforms such as widely distributed computers (grid). © 2002 IEEE.

关键词： cluster of PCs distributed computation distributed molecular dynamics message passing middleware performance optimization performance tuning

来源：评论

学校读者我要写书评

暂无评论

XML&CORBA-based distributed system for information integration and dissemination in multimedia neuroimaging applications

XML&CORBA-based distributed system for information integrati...

引用

Medical Imaging 2002 Conference

作者： Cao, XH Wong, STC Hoo, KS Ching, W Hawkins, R Dillon, W Univ Calif San Francisco San Francisco CA 94143 USA

ISBN: (纸本)0819444308

Medical information systems based in different hospital departments face tremendous difficulty in information exchange and dissemination due to the multitudes of hardware and software platforms running these systems. In this paper, we describe a distributed information system for integrating various hospital systems in supporting clinical neuroimaging research and epilepsy surgical planning. Our distributed information system uses a three-tiered architecture consists of a user-interface tier, application logic tier and data store tier. Two system implementations based on this software architecture but using different integration technologies were developed and are discussed in this paper: the XML (extensible Mark Up Language)-based implementation and the CORBA (Common Object Request Broker Architecture)-based implementation. In the XML-based implementation, application logic tier communicates with user-interface tier and data store tier using HTTP and XML for data exchange. For the data exchange in CORBA-based implementation, the middleware uses HOP (Internet inter-ORB protocol) to call CORBA objects in the data store tier then to return the results to the user-interface tier. For the user-interface tier of either implementation, the Web browsers are served as clients to invoke application components or agents in the middleware. The application of the proposed distributed system allows clinical users to access, search and retrieve the multimedia information in any underlying computer systems with commonly used Web browsers. Preliminary results show that the system is effective for information integration and data sharing among the different departmental systems in the hospital for neuroimaging applications.

关键词： distributed computation middleware system integration technology XML CORBA IIOP Web

来源：评论

学校读者我要写书评

暂无评论

distributed adaptive algorithms for large dimensional MIMO systems

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2000年第4期48卷 1076-1085页

作者： Van Veen, BD Leblond, O Mani, VP Sebald, DJ Univ Wisconsin Dept Elect & Comp Engn Madison WI 53706 USA

An algorithm for multi-input multi-output (MIMO) adaptive filtering is introduced that distributes the adaptive computation over a set of linearly connected computational modules, Each module has an input and an output and transmits data to and receives data from its nearest neighbor, A gradient-based algorithm for adapting the parameters in each module to minimize the global mean-squared error is derived using principles of hack propagation, The performance surface is explored to understand the characteristics of the adaptive algorithm, The minimum mean-squared error is a many to one function of the parameters;therefore, upper bounds on each parameter are used to prevent excessive parameter drift and insure stability with fixed step sizes, Guidelines for choosing the LMS algorithm step sizes and initial conditions are developed. Several examples illustrate the performance of the algorithm.

关键词： active noise control distributed computation gradient based adaptation MIMO adaptive systems

来源：评论

学校读者我要写书评

暂无评论

PRI: An Periodically Receiver-Initiated Task Scheduling Algorithm

引用

高技术通讯（英文版） 2000年第1期6卷 8-13页

作者： Shi Wei Fang Binxing Zeng Huming Computer Science and Engineering Department Harbin Institute of TechnologyHarbin 150001 P.R.China

Task scheduling is a key problem for the distributed computation. This thesis analyzes receiver-initiated(RI) task scheduling algorithm, finds its weakness and presents an improved algorithm-PRI algorithm. This algorithm schedules the concurrent tasks onto network of workstation dynamically at runtime, and initiates task scheduling by the node of low load. The threshold on each node can be modified according to the system information which is periodically detected. Meanwhile, the detecting period can be adjusted in terms of the change of the system state. The result of the experiments shows that the PRI algorithm is superior to the RI algorithm.

关键词： Task scheduling distributed computation Receiver-initiated Network of workstations Runtime Low load Threshold

来源：评论

学校读者我要写书评

暂无评论

Data analysis environment (DASH2000) for the Subaru Telescope

Data analysis environment (DASH2000) for the Subaru Telescop...

引用

Conference on Advanced Telescope and Instrumentation Control Software

作者： Mizumoto, Y Yagi, M Chikada, Y Ogasawara, R Kosugi, G Takata, T Yoshida, M Ishihara, Y Yanaka, H Yamamoto, T Morita, Y Nakamoto, H Natl Astron Observ Mitaka Tokyo 181 Japan

ISBN: (纸本)0819436348

New framework of data analysis system (DASH) has been developed for the SUBARU Telescope. It is designed using object-oriented methodology and adopted a restaurant model. DASH shares the load of CPU and I/O among distributed heterogeneous computers. The distributed object environment of the system is implemented with JAVA and CORBA. DASH has been evaluated by several prototypings. DASH2000 is the latest version, which will be released as the beta version of data analysis system for the SUBARU Telescope. A pipeline process can be efficiently made using an editor that visually edits analysis procedure object (PROCube). PROCube manages information of input data, work data, processing engines, and log, together. A set of observed data could be automatically selected for a PROCube to analyze a specified object, using observational dataset generated by data acquisition and control system of the SUBARU telescope. DASH defines general interface for a data processing engine (task). DASH prepares a framework into which a task of traditional systems such as IRAF can be built. Moreover, the pipeline process made in DASH framework can be built into the real-time data acquisition system as a quick-look function. Small version of DASH (SASH) is also offered for a stand-alone computer environment. It can be manipulated by the same GUI as DASH2000. And it is enabled that a user continues data processing by SASH on a local computer after the user processes data by DASH2000 on the NAOJ's computer system.

关键词： pipeline data analysis data reduction distributed computation CORBA Java

来源：评论

学校读者我要写书评

暂无评论

distributed virtual reality system based on hybrid rendering

引用

自然科学进展（英文版） 2000年第3期10卷 218-218页

作者： ZHENG Wenting BAO Hujun ENG Qunsheng Zhejiang Univ State Key Lab CAD&CG Hangzhou 310027 Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Shatin Hong Kong Peoples R China

A distributed virtual reality system is presented based on a hybrid rendering scheme. This system first predicts the camera position of the next key frame in real-time according to the tendency of the current camera movement. The predicted key frame is then generated using a geometry-based algorithm. Finally, a real-time backward image warping algorithm is employed to create a smooth transition between the two adjacent key frames. Since the rendering procedure can be divided into two independent steps, this system can be efficiently implemented in distributed mode.

关键词： virtual reality texture mapping distributed computation parallel computation

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：