Semantic annotation plays a central role in building Semantic Web, which in general could be completed by committing a web resource to a domain ontology. However, there exist many circumstances in which semantic annot...
详细信息
ISBN:
(纸本)0780378407
Semantic annotation plays a central role in building Semantic Web, which in general could be completed by committing a web resource to a domain ontology. However, there exist many circumstances in which semantic annotation needs more than one ontologies In this paper, we propose an approach based distributed Description Logics(DDL) with intention to deal withthese circumstances, in which ontologies form a distributed system, and no extra conditions and. changes are imposed to those component ontologies.
Due to the increased complexity of applications, the distributed hierarchy architecture of clusters and the deficiency of efficient compiling strategies, developing efficient applications for large-scale scientific an...
详细信息
ISBN:
(纸本)0780378407
Due to the increased complexity of applications, the distributed hierarchy architecture of clusters and the deficiency of efficient compiling strategies, developing efficient applications for large-scale scientific and engineering computing on clusters is difficult. Our strategy to address this problem is to extend a generic data-parallel programming environment with an extensible component library. A component is a reusable routine that can be called by an alias in applications to perform some specific computation. All algorithmic and programming complexity as well as the specialized knowledge required to implement and optimize the computation are encapsulated in the routine. the alias is provided to the programming model as an extended operator for end users to develop new applications. Programmers use data-parallel construct and high-level operators to specify applications and its parallelism, and rely on sophisticated implementations of these programming systems to ensure that applications achieve high performance.
We present an automatic parallelization scheme involving extracting inter-block parallelism within sequential programs, scheduling block graphs, and generating appropriate target codes for message passing multiprocess...
详细信息
ISBN:
(纸本)0780378407
We present an automatic parallelization scheme involving extracting inter-block parallelism within sequential programs, scheduling block graphs, and generating appropriate target codes for message passing multiprocessors. Compared with existing parallelization compilers, it is capable of exploiting more parallelism because potential parallelism existing within blocks is take into consideration.
Online Analytical Processing (OLAP) is a critical component of data warehouse. Most of today9;s OLAP applications work on data warehouses with a centralized structure in which a single database contains huge amount...
详细信息
ISBN:
(纸本)0780378407
Online Analytical Processing (OLAP) is a critical component of data warehouse. Most of today's OLAP applications work on data warehouses with a centralized structure in which a single database contains huge amounts of data. A range query is a very popular and important operation on OLAP data cube in finding trends or relations between attributes. Methods of computing range query in a centralized data warehouse environment have been well studied. But to the best of our knowledge, there is no literature to date to discuss how to deal withthe range query in a PC cluster-based parallel data warehouse. In this paper, we present a parallel data cube storage structure, called parallel hierarchical data cube(PHDC). the analytical results show that PHDC may achieve better load-balance and optimum speed-up for range sum queries.
this paper proposes an approach to the design of distributedparallelcomputing systems based on the concept of reflective middleware, skeleton parallel programming and object-oriented software engineering. In the app...
详细信息
ISBN:
(纸本)0780378407
this paper proposes an approach to the design of distributedparallelcomputing systems based on the concept of reflective middleware, skeleton parallel programming and object-oriented software engineering. In the approach, the programmer does not need to be bothered by the architectural details. Furthermore, the approach provides support for the mostly used parallel paradigms, which will ease the onerous work for the programmer to construct the parallelism. It offers a method for the user to map the programming design seamlessly to the real environment.
We compare the performance of the Treadmarks DSM system with two popular message passing systems (PVM and MPI). the comparison is done on 1, 2, 4, 8, 16, 24, and 32 nodes. applications are chosen to represent three cl...
详细信息
ISBN:
(纸本)0780378407
We compare the performance of the Treadmarks DSM system with two popular message passing systems (PVM and MPI). the comparison is done on 1, 2, 4, 8, 16, 24, and 32 nodes. applications are chosen to represent three classes of problems: loosely synchronous, embarrassingly parallel, and synchronous. the results show DSM has similar performance to message passing for the embarrassingly parallel class. However, the performance of DSM is lower than PVM and MPI for the synchronous and loosely synchronous classes of problems. An analysis of the reasons is presented.
this paper presents a distributedparallel system for face recognition. the face database in this system is so huge (more than 1,000 thousand faces) that matching and recognition processes can not be carried out on on...
详细信息
ISBN:
(纸本)0780378407
this paper presents a distributedparallel system for face recognition. the face database in this system is so huge (more than 1,000 thousand faces) that matching and recognition processes can not be carried out on only one computer. So cluster system must be used to improve the matching speed. But many current clusters existing have some problems and can not fit our system. A special distributedparallel system was developed to complete face query and recognition. the concept of parallel virtual machine and a kind of linked table structure adopted in this system not only decreased lots of moving overhead of adding or deleting nodes in the array structure but also truly realized the infinite extensibility. Furthermore, key techniques such as distributed database, buffer and synchronization techniques in communication and multithreading in control flow were adopted to guarantee the normal running. Practical results proved that this parallel system can improve the matching speed for more than 4 times. Moreover, the greatest advantage of this system is not only increasing matching speed but breaking the upper limit of face data capacity. Consequently, the face data capability of this system can be extended to arbitrary figure as bigger as possible.
In the past five years, hosts on Internet have multiplied more than five times, and along withthe network9;s rapid expansion, more and more attention is paid to the challenging task of studying the topology charac...
详细信息
ISBN:
(纸本)0780378407
In the past five years, hosts on Internet have multiplied more than five times, and along withthe network's rapid expansion, more and more attention is paid to the challenging task of studying the topology characteristics of Internet infrastructure. Based on the features of Internet topology discovery and practical experience, we present a three-level distributed architecture for Internet router-level routing topology discovering system. We employ an integrated framework for the deployment of the system. We are examining, from a macroscopic point of view, what architecture is appropriate for this-like system, with an emphasis placed on the flexibility in practical work. the architecture enjoys the advantages of a clear train of thought and high modularization. Experiments show that this architecture has an instructive meaning for the development, deployment, and maintenance of Internet topology discovering system.
Control systems for process plants are complex applications running in several interacting computers with varying degrees of integration. the construction, deployment and maintenance of the software system is a diffic...
详细信息
ISBN:
(纸本)0780379373
Control systems for process plants are complex applications running in several interacting computers with varying degrees of integration. the construction, deployment and maintenance of the software system is a difficult problem and distributed object oriented technology offers a good way to deal with it. the open standard CORBA provides flexible middleware capable of integrating complex applications in heterogeneous environments, but was originally designed with large business applications in mind and is not perfectly suited for the construction of control systems. Even with recent advances in the real-time specification for CORBA, it is only suitable for soft real-time applications and does not deal withthe tight requirements of closed control loops. this paper describes the HRTC project, an experiment of CORBA-based control systems. this project addresses the analysis of the technology and the implementation of two testbeds, one in process control and another one in robot control. the benefits of such technology are discussed.
In this paper we discuss a new parallel algorithm of 2-D Discrete Wavelet Transform (DWT) using MPI_Scatterv and MPI_Gatherv (MPI: Message Passing Interface). In this algorithm, the 2-D sequential Daubechies Discrete ...
详细信息
ISBN:
(纸本)0780378407
In this paper we discuss a new parallel algorithm of 2-D Discrete Wavelet Transform (DWT) using MPI_Scatterv and MPI_Gatherv (MPI: Message Passing Interface). In this algorithm, the 2-D sequential Daubechies Discrete Wavelet Transform program is first decomposed into several 1-D transforms, and then the parallel conversion is made on them. this parallel program has already been successfully implemented on the Dawning parallel Computer System, and experimental results show that high performance and pretty flexibility can be achieved.
暂无评论