Search results

Historically, library catalogs have been rather insular, often based on specialized hardware and/or operating systems lacking industry‐standard networking capabilities. Network access was not a major consideration in the design or selection of these specialized systems. But when library automation systems are attached to the network as an afterthought, they often display unsatisfactory functional characteristics; libraries now face the realities of the wired campus environment and the collision between library automation tradition and the new world of networks.

The purpose of this paper is to explain one of the most important collective communication patterns used in scientific applications which is the complete exchange, also called All‐to‐All. Although efficient algorithms have been studied for specific networks, general solutions like those available in well‐known MPI distributions (e.g. the MPI_Alltoall operation) are strongly influenced by the congestion of network resources.

In this paper we present an integrated approach to model the performance of the All‐to‐All collective operation, which consists in identifying a contention signature that characterizes a given network environment, using it to augment a contention‐free communication model.

This approach, assessed by experimental results, allows an accurate prediction of the performance of the All‐to‐All operation over different network architectures with a small overhead.

The paper discusses the problem of network contention in a grid environment, studying some strategies to minimize the impact of contention on the performance of an All‐to‐All operation.

The approach used, assessed by experimental results, allows an accurate prediction of the performance of the All‐to‐All operation over different network architectures with a small overhead. Also discussed is the problem of network contention in a grid environment and some strategies to minimize the impact of contention on the performance of an All‐to‐All operation.

Investigates some complex issues concerning local area networking (LAN). Examines the two basic forms of network – peer‐to‐peer and server‐based and their advantages and disadvantages for workgroups of various sizes. Compares Token Ring with Ethernet networks. Finally, offers some advice on choosing operating systems.

The Polytechnic of Central London has developed and installed a wide area network connecting libraries on six sites. The network is linked to SWALCAP for circulation control, and cataloguing services will be added in 1984. Two local area network (LAN) projects are planned. An analysis of the telecommunications options considered is presented, with costs for the system adopted for the wide area network.

The ARPANET, initiated in 1969 by the Advanced Research Projects Agency (DARPA) of the Department of Defense (DoD), was the first wide area packet switching network. In 1984, the ARPANET, which had grown to over 100 nodes, was separated into two parts: an operational component, the MILNET, to serve the operational needs of the DoD, and a research component that retained the ARPANET name. After the network split, the MILNET expanded, and it should reach over 250 nodes within a year. The DARPA Internet was formed in the 1970s in response to a requirement to interconnect different types of packet‐switching networks that were being implemented. It has grown to be very large; it now consists of over 330 networks, hundreds of gateways, and tens of thousands of hosts. Where the ARPANET used to connect hosts that were single computers into a network, many of these hosts now serve as gateways to local campus networks, regional networks, and other national networks, such as the NSFNET. The impact of this growing system of inter‐connected networks on research, communications, and library access will be profound.

The basic technical components of ‘information networking’ have been in place since the mid‐1970s, when the first generation online bibliographic services such as the INSPEC databases and MEDLINE, implemented on dial‐up hosts like Dialog and ESA changed the ways in which librarians approached bibliographic searching — at least in the better funded organizations. The peak of diversification and growth of the online bibliographic database probably came around 1988 when Williams reviewed the near‐exponential growth of new services and the extraordinary diversity of the sources which appeared to be viable. At about the same time, however, it was being pointed out that despite the excitement this was generating in libraries, it amounted to less than 15% of the European market in electronic information services, with data‐oriented financial services dominating the remainder. The share of the host‐based financial data services has probably subsequently grown — at the time of writing in August 1993, Reuters (a market leader in financial data services) was reported as having difficulty in disposing of its trading profits.

This paper responds to continuing arguments about the necessity for structural separation of the telecommunications local loop. It attempts to strike a balance by stressing that in fact a wide range of questions are yet to be answered. And the onus is fairly placed on the proponents of structural separation to provide persuasive answers proving that the drastic action they call for is necessary. In addition, many of the benefits of structural separation are unquantifiable and, indeed, conjectural, while the costs of this severe measure are more certain and substantial. Moreover, while seemingly simple in concept, there is a formidable range of difficulties relating to the implementation of structural separation.

This paper reports on the use of Information Technologies (IT) in the South African building industry. It offers an insight into the architecture profession, a profession that plays a major role in the construction sector. The analysis is based on the results of a survey conducted in the Western Cape Province during the year 2000. In an attempt to uncover the similarities and differences between the local context and the international one, this paper outlines a few elements of IT for comparison. After a brief introduction to the IT map of South Africa, the analysis concentrates on the following four issues: Response and Respondents, General IT usage, Use of Computer‐Aided‐Design (CAD) and Use of Networks. Each of these issues is framed in both the local and the international contexts. Despite the shortcomings of using different questions with different emphasis when referring to other surveys, it is still believed that reporting on local practices is not extremely meaningful in isolation. It is hoped that this type of analysis will serve to unravel the particulars of the construction industry in South Africa providing its counterparts with a new perspective.

An intelligent building incorporates two key components: automated building control systems and information management control systems. Automated building control systems include energy management systems, automated security and fire systems, and network life‐support systems. Information management control systems include telecommunications, data networking, local area networks, and other short and long haul networks. When these systems are linked together with common wiring and central controls, the building becomes intelligent. The integration of these components in Infomart, a high‐tech facility located in Dallas, Texas, is described. The usage of these components by tenants, and their possible application to library buildings are discussed.