Simin H. Pakzad

A taxonomy and current issues in multidatabase systems

A taxonomy of global information-sharing systems is presented, and the way in which multidatabase systems fit into the spectrum of solutions is discussed. The taxonomy is used as a basis for defining multidatabase systems. Issues associated with multidatabase systems are reviewed. Two major design approaches for multidatabases, global schema systems and multidatabase language systems, are described. Existing multidatabase projects and areas for further research are also discussed.<<ETX>>

Automated resolution of semantic heterogeneity in multidatabases

A multidatabase system provides integrated access to heterogeneous, autonomous local databases in a distributed system. An important problem in current multidatabase systems is identification of semantically similar data in different local databases. The Summary Schemas Model (SSM) is proposed as an extension to multidatabase systems to aid in semantic identification. The SSM uses a global data structure to abstract the information available in a multidatabase system. This abstracted form allows users to use their own terms (imprecise queries) when accessing data rather than being forced to use system-specified terms. The system uses the global data structure to match the users terms to the semantically closest available system terms. A simulation of the SSM is presented to compare imprecise-query processing with corresponding query-processing costs in a standard multidatabase system. The costs and benefits of the SSM are discussed, and future research directions are presented.

Object-oriented database management systems: evolution and performance issues

Several research prototypes and commercial object-oriented database management systems (DBMSs) that emphasize the representation and manipulation of complex objects are reviewed. It is argued that clustering and buffering schemes tailored to typical complex object operations offer the best near-term means of improving the performance of databases and that research in clustering and buffering should address recent advances in disk technology: optical and parallel disks. The object-oriented DBMSs reviewed are Orion, Iris, GemStone, Encore, Ontos, Versant, and ObjectStore.<<ETX>>

Parallel Architectures for Database Systems

Publisher Summary This chapter examines the impact of current technology on the design of special-purpose database machines (DBMs) and provides a survey of the DBMs that focuses on the adaptability of the designs to the current technology. The computer architectures fall into four groups—namely, single instruction stream-single data stream (SISD), single instruction stream-multiple data stream (SIMD), multiple instruction stream-single data stream (MISD), and multiple instruction stream-multiple data stream (MIMD). Database computer (DBC) uses two forms of parallelism: an entire cylinder is processed in parallel and the system performs queries in a pipeline fashion by separate units around two rings. The systems in high very large scale integration (VLSI)-compatible database machines are designed based on the constraints imposed by technology. In general, they are highly parallel with regular and simple architectures. The future database machine designers ought to concentrate on two important issues: (1) the investigation of the effect and benefit of a specialized database operating system on their DBM designs and (2) the optimization of the system throughput rather than improving the response time of a single request.

Application for parallel disks for efficient handling of object-oriented databases

In todays workstation based environment, applications such as design databases, multimedia databases, and knowledge bases do not fit well into the relational data processing framework. The object-oriented data model has been proposed to model and process such complex databases. Due to the nature of the supported applications, object-oriented database systems need efficient mechanisms for the retrieval of complex objects and the navigation along the semantic links among objects. Object clustering and buffering have been suggested as efficient mechanisms for the retrieval of complex objects. However, to improve the efficiency of the aforementioned operations, one has to look at the recent advances in storage technology. This paper is an attempt to investigate the feasibility of using parallel disks for object-oriented databases. It analyzes the conceptual changes needed to map the clustering and buffering schemes proposed on the new underlying architecture. The simulation and performance evaluation of the proposed leveled-clustering and mapping schemes utilizing parallel I/O disks are presented and analyzed.<<ETX>>

Specialized Parallel Architectures for Textual Databases

Publisher Summary The chapter presents the concept of unformatted databases and parallel architectures, proposed to manipulate textual databases. Databases fall into two general categories—namely, formatted and unformatted structures. Formatted databases are mainly time variant entities and are subject to extensive alteration as well as search operations. Unformatted databases (bibliographic or full-text) are archival in nature and are processed by searching for a pattern or a combination of patterns. The problem of searching large textual databases is addressed in the chapter. To improve the performance of such a lengthy operation, two major directions are discussed: one based on the design of efficient algorithms for pattern matching operations, and the other based on the hardware implementation of the basic pattern matching operations. Both approaches have their own merits and are subject to further research and study. However, the major theme of this chapter is centered around the design of the hardware pattern matcher. Such an emphasis is mainly due to the current advances in technology that have enabled the migration of the software functions into the hardware. Three different schemes of hardware implementation of an efficient term comparator for specialized backend text retrieval architectures are also discussed.

Design and analysis of an intelligent support system for large databases

Maybe algebra and attribute maybe algebra operations have been studied to handle incomplete information in a relational database system. These operations give the user the opportunity to investigate the set of complete, as well as incomplete, data values which can not be obtained with traditional algebra operations. However, some of these operations may generate data which can be enormous in size, erroneous in semantics, and less informative. An intelligent support system is proposed to remedy some, if not all, of these problems in large databases. The proposed system functions as a filter. It has a strong learning capability which adjusts itself according to the specific characteristics of the underlying database and the requirement of the users query. The performance analysis has been carried out through simulation of the proposed system. To provide a test bed for the simulation, an incomplete database has been constructed.<<ETX>>

A reconfigurable MIMD back-end database machine

Abstract Society is experiencing an information explosion. The proliferation of data combined with higher performance requirements have forced the designers of database systems to look beyond software solutions. How to make the most of the available data automatically without a high degree of sophistication and complexity remains an important question. Since the early seventies, researchers have examined the use of special hardware to handle large databases—i.e., the database machine. The present work studies the extension of the ASLM database machine to a multiuser/multiprogram environment. This extension is possible via a set of simple algorithms which allows dynamic reconfigurability of the hardware resources among a set of concurrent queries. Incorporation of these algorithms in the design of ASLM has improved the throughput and the resource utilization while enhancing the fault-tolerant capability of our database machine. Analysis of these algorithms and their effect on the performance and the throughput of ASLM is the major theme of this article.

Design of a modular chip for a reconfigurable artificial neural network

This paper describes the design of the IBM fabricated basic neural unit (BNU) which can be used as a building block for a general-purpose reconfigurable artificial neural network (GRANNet). As a first step, a fully reconfigurable 2-BNU VLSI circuit is designed, implemented and tested. The hardware and software requirements of this implementation are presented. This paper also examines the issue of topological reconfigurability.<<ETX>>

Extended ASLM-a reconfigurable database machine

The architectural features of the ASLM database machine are explored, and the retrieval aspect of incorporating a comprehensive null value policy into the design of ASLM is examined. The join operation is used as a performance measure in the evaluation of ASLM. The extension of ASLM to a multiuser/multiprogram environment by dynamic reconfigurability of the hardware resources among a set of concurrent queries is discussed.<<ETX>>