Performance analysis of an object-oriented approach to parallel query evaluation

Thyagaraju R. Poola, W. S. Lee, P. C.Y. Sheu

Research output: Contribution to journalConference article

Abstract

An object-oriented representation of databases which takes advantage of the structure of logical representation and an object-oriented algorithm that evaluates conjunctive queries in a massively parallel environment are reported and analyzed. The object-oriented representation is used to implement data level parallelism as data is encapsulated as an object. By distributing these objects in a database, parallel evaluation is achieved by a global pattern matching approach which is different from the conventional tuple-by-tuple, operation-by-operation evaluation strategy. This algorithm overcomes the data dependency imposed by shared variables which is a major problem in achieving AND-parallelism. Simulation results for 2 way and 3 way joins are analysed according to the effect of database size and join size. Results tend to show that the scheme proposed performs better for queries with large number of AND conjuncts.

Original languageEnglish
Pages (from-to)264-269
Number of pages6
JournalProceedings - IEEE Computer Society's International Computer Software & Applications Conference
Publication statusPublished - 1994 Dec 1
EventProceedings of the 18th Annual International Computer Software & Applications Conference (COMPSAC 94) - Taipei, Taiwan
Duration: 1994 Nov 91994 Nov 11

Fingerprint

Pattern matching

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications

Cite this

@article{463958c5e42c4761bfb7f65d05c08456,
title = "Performance analysis of an object-oriented approach to parallel query evaluation",
abstract = "An object-oriented representation of databases which takes advantage of the structure of logical representation and an object-oriented algorithm that evaluates conjunctive queries in a massively parallel environment are reported and analyzed. The object-oriented representation is used to implement data level parallelism as data is encapsulated as an object. By distributing these objects in a database, parallel evaluation is achieved by a global pattern matching approach which is different from the conventional tuple-by-tuple, operation-by-operation evaluation strategy. This algorithm overcomes the data dependency imposed by shared variables which is a major problem in achieving AND-parallelism. Simulation results for 2 way and 3 way joins are analysed according to the effect of database size and join size. Results tend to show that the scheme proposed performs better for queries with large number of AND conjuncts.",
author = "Poola, {Thyagaraju R.} and Lee, {W. S.} and Sheu, {P. C.Y.}",
year = "1994",
month = "12",
day = "1",
language = "English",
pages = "264--269",
journal = "Proceedings - IEEE Computer Society's International Computer Software and Applications Conference",
issn = "0730-6512",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Performance analysis of an object-oriented approach to parallel query evaluation. / Poola, Thyagaraju R.; Lee, W. S.; Sheu, P. C.Y.

In: Proceedings - IEEE Computer Society's International Computer Software & Applications Conference, 01.12.1994, p. 264-269.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Performance analysis of an object-oriented approach to parallel query evaluation

AU - Poola, Thyagaraju R.

AU - Lee, W. S.

AU - Sheu, P. C.Y.

PY - 1994/12/1

Y1 - 1994/12/1

N2 - An object-oriented representation of databases which takes advantage of the structure of logical representation and an object-oriented algorithm that evaluates conjunctive queries in a massively parallel environment are reported and analyzed. The object-oriented representation is used to implement data level parallelism as data is encapsulated as an object. By distributing these objects in a database, parallel evaluation is achieved by a global pattern matching approach which is different from the conventional tuple-by-tuple, operation-by-operation evaluation strategy. This algorithm overcomes the data dependency imposed by shared variables which is a major problem in achieving AND-parallelism. Simulation results for 2 way and 3 way joins are analysed according to the effect of database size and join size. Results tend to show that the scheme proposed performs better for queries with large number of AND conjuncts.

AB - An object-oriented representation of databases which takes advantage of the structure of logical representation and an object-oriented algorithm that evaluates conjunctive queries in a massively parallel environment are reported and analyzed. The object-oriented representation is used to implement data level parallelism as data is encapsulated as an object. By distributing these objects in a database, parallel evaluation is achieved by a global pattern matching approach which is different from the conventional tuple-by-tuple, operation-by-operation evaluation strategy. This algorithm overcomes the data dependency imposed by shared variables which is a major problem in achieving AND-parallelism. Simulation results for 2 way and 3 way joins are analysed according to the effect of database size and join size. Results tend to show that the scheme proposed performs better for queries with large number of AND conjuncts.

UR - http://www.scopus.com/inward/record.url?scp=0028713180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028713180&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0028713180

SP - 264

EP - 269

JO - Proceedings - IEEE Computer Society's International Computer Software and Applications Conference

JF - Proceedings - IEEE Computer Society's International Computer Software and Applications Conference

SN - 0730-6512

ER -