No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Binary Relational Processing on Wavefront Array Processors.
Abstract
Object-oriented databases provide rich abstraction facilities for the representation of complex application objects together with their properties and behaviour. Query processing in these databases is quite different from the processing of the corresponding relational databases. Pairs of application objects having at least a connection (relation) between their members can be interpreted as conceptual binary relations. Object-oriented queries can be processed handling uniformly these relations using the binary relational algebra, which provides an algebraic framework [7] that is analogous [8], [10] to the relational algebra for relational databases [1],[2]. However, query-processing efficiency cannot be easily achieved in these very large object-oriented databases using traditional methods and techniques. In such advanced databases the system's performance can be improved using wavefront algorithms and parallel processing techniques. In this paper wavefront array processors are investigated for the purpose of object pair composition, which takes place during the query-processing phase in object-oriented databases that their functionality is based upon binary relational algebra.
... In this paper, instead of using graphs, an extension to the ODMG's object data standard 3.0 for incorporating binary relational expressions and a dewavefront algorithm for query declaration and efficient query execution purposes are proposed, respectively. The dewavefront algorithm uses wavefront array processors, which are the mappings (Fountoukis et al. 2004) of the operators of the binary relational algebra. The wavefront array processor can be VHDL designed and FPGA -253 -implemented, resulting in a hybrid microsurgery object oriented database system, composed by both software and hardware (middleware). ...
... Derived relations are required in queries like the one illustrated in the previous example. The dewavefront algorithm uses a wavefront array processor, which is the mapping (Fountoukis et al. 2004) of the binary relational operators. A general description of the algorithm, using a more general complex example is given here. ...
This book constitutes the proceedings of the 2nd International Conference on Information Communication Technologies in Health (ICICTH), held in Samos, Greece, in July 2004.
... This algorithm (and engine) processes the simple and multiple merged chains of binary relations introduced in the OQL extension and stated in queries. The basic elements of the multi-functional engine architecture can be of two types of array processors: a (synchronous) square systolic device for wavefront-like computations -S 2 DWC (Fountoukis, 2004) or a bidirectional parallel cubic engine -BPCE (Fountoukis, 2005). ...
... Two types of processors can be used by the processing nodes: a (synchronous) square systolic device for wavefrontlike computations -S 2 DWC (Fountoukis, 2004) or a bidirectional parallel cubic engine -BPCE (Fountoukis, 2005). Both these processors synthesize a relation from two existing ones applying the composition operator (Section 3) defined by the algebra of binary relations. ...
Herein, an extension to the object query language (OQL) for incorporating binary relational expressions is investigated. The extended query language is suitable for query submissions to an object oriented database, whose functionality is based upon the algebra of binary relations. Algebraic expressions, consisting of simple and multiple merged chains of binary relations, are stated in SQL syntax-based object queries, which are utilized by a multiwavefront algorithm mapped on a multi-directional multi-functional engine(M 2FE), for object oriented parallel query processing. The proposed extension also attempts to solve other object oriented database issues, such as inheritance, relationships between objects and literals, and recursive queries.
The principal theme herein is the direct hardware implementation on a special-purpose network of processors, the Wavefront Array Processor (WAP), of an alternate matrix procedure for the solution of linear systems Ax = b, where A is a compact dense (n × n) matrix. The method is based on the factorization of the coefficient matrix into components which are of ‘butterfly’ form, i.e., interlocking matrix quadrants, and for its implementation the concept of computational ‘dewavefronts’ is investigated.
Three principal types of language for data base manipulation are identified: the low-level, procedure-oriented (typified by the CODASYL-proposed DML), the intermediate level, algebraic (typified by the Project MAC MacAIMS language), and the high level, relational calculus-based data sublanguage, an example of which is described in this paper. The language description is informal and stresses concepts and principles. Following this, arguments are presented for the superiority of the calculus-based type of data base sub-language over the algebraic, and for the algebraic over the low-level procedural. These arguments are particularly relevant to the questions of inter-system compatibility and standardization.