Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching

Chao-Chin Wu, Lien-Fu Lai, Yu Shuo Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

CLIPS is a non-algorithmic language designed especially for developing expert systems. To address the problem that CLIPS suffers from long execution time because of the characteristics of rule-based language, previously we have proposed a Grid-enabled parallel CLIPS language and a dynamic load balancing programming model that can parallelize the execution of a CLIPS program automatically if the data can be inferred independently. In this paper, we investigate how to apply the idea of automatic parallelization to other kinds of applications. For instance, a rule usually requires choosing multiple data items from the knowledge base to match with. This kind of matching is a permutation problem. All the different permutations must be divided into partitions and assigned to slaves for independent inferences. A programmer only needs to use three simple directives to provide necessary information to automatically parallelize the execution of an application. Experiment results show that the best speedup is 10.38 when executing a knowledge management system in a heterogeneous cluster system with 12 processor cores.

Original languageEnglish
Title of host publication2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010
Pages214-218
Number of pages5
Volume1
DOIs
Publication statusPublished - 2010 May 28
Event2nd International Conference on Computer Engineering and Applications, ICCEA 2010 - , Indonesia
Duration: 2010 Mar 192010 Mar 21

Other

Other2nd International Conference on Computer Engineering and Applications, ICCEA 2010
CountryIndonesia
Period10-03-1910-03-21

Fingerprint

Pattern matching
Expert systems
Knowledge management
Dynamic loads
Resource allocation
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Software

Cite this

Wu, C-C., Lai, L-F., & Chang, Y. S. (2010). Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching. In 2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010 (Vol. 1, pp. 214-218). [5445835] https://doi.org/10.1109/ICCEA.2010.49
Wu, Chao-Chin ; Lai, Lien-Fu ; Chang, Yu Shuo. / Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching. 2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010. Vol. 1 2010. pp. 214-218
@inproceedings{69cc73512de74d6dac18078220f1d250,
title = "Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching",
abstract = "CLIPS is a non-algorithmic language designed especially for developing expert systems. To address the problem that CLIPS suffers from long execution time because of the characteristics of rule-based language, previously we have proposed a Grid-enabled parallel CLIPS language and a dynamic load balancing programming model that can parallelize the execution of a CLIPS program automatically if the data can be inferred independently. In this paper, we investigate how to apply the idea of automatic parallelization to other kinds of applications. For instance, a rule usually requires choosing multiple data items from the knowledge base to match with. This kind of matching is a permutation problem. All the different permutations must be divided into partitions and assigned to slaves for independent inferences. A programmer only needs to use three simple directives to provide necessary information to automatically parallelize the execution of an application. Experiment results show that the best speedup is 10.38 when executing a knowledge management system in a heterogeneous cluster system with 12 processor cores.",
author = "Chao-Chin Wu and Lien-Fu Lai and Chang, {Yu Shuo}",
year = "2010",
month = "5",
day = "28",
doi = "10.1109/ICCEA.2010.49",
language = "English",
isbn = "9780769539829",
volume = "1",
pages = "214--218",
booktitle = "2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010",

}

Wu, C-C, Lai, L-F & Chang, YS 2010, Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching. in 2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010. vol. 1, 5445835, pp. 214-218, 2nd International Conference on Computer Engineering and Applications, ICCEA 2010, Indonesia, 10-03-19. https://doi.org/10.1109/ICCEA.2010.49

Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching. / Wu, Chao-Chin; Lai, Lien-Fu; Chang, Yu Shuo.

2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010. Vol. 1 2010. p. 214-218 5445835.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching

AU - Wu, Chao-Chin

AU - Lai, Lien-Fu

AU - Chang, Yu Shuo

PY - 2010/5/28

Y1 - 2010/5/28

N2 - CLIPS is a non-algorithmic language designed especially for developing expert systems. To address the problem that CLIPS suffers from long execution time because of the characteristics of rule-based language, previously we have proposed a Grid-enabled parallel CLIPS language and a dynamic load balancing programming model that can parallelize the execution of a CLIPS program automatically if the data can be inferred independently. In this paper, we investigate how to apply the idea of automatic parallelization to other kinds of applications. For instance, a rule usually requires choosing multiple data items from the knowledge base to match with. This kind of matching is a permutation problem. All the different permutations must be divided into partitions and assigned to slaves for independent inferences. A programmer only needs to use three simple directives to provide necessary information to automatically parallelize the execution of an application. Experiment results show that the best speedup is 10.38 when executing a knowledge management system in a heterogeneous cluster system with 12 processor cores.

AB - CLIPS is a non-algorithmic language designed especially for developing expert systems. To address the problem that CLIPS suffers from long execution time because of the characteristics of rule-based language, previously we have proposed a Grid-enabled parallel CLIPS language and a dynamic load balancing programming model that can parallelize the execution of a CLIPS program automatically if the data can be inferred independently. In this paper, we investigate how to apply the idea of automatic parallelization to other kinds of applications. For instance, a rule usually requires choosing multiple data items from the knowledge base to match with. This kind of matching is a permutation problem. All the different permutations must be divided into partitions and assigned to slaves for independent inferences. A programmer only needs to use three simple directives to provide necessary information to automatically parallelize the execution of an application. Experiment results show that the best speedup is 10.38 when executing a knowledge management system in a heterogeneous cluster system with 12 processor cores.

UR - http://www.scopus.com/inward/record.url?scp=77952595024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952595024&partnerID=8YFLogxK

U2 - 10.1109/ICCEA.2010.49

DO - 10.1109/ICCEA.2010.49

M3 - Conference contribution

SN - 9780769539829

VL - 1

SP - 214

EP - 218

BT - 2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010

ER -

Wu C-C, Lai L-F, Chang YS. Parallelizing CLIPS-based expert systems by the permutation feature of pattern matching. In 2010 2nd International Conference on Computer Engineering and Applications, ICCEA 2010. Vol. 1. 2010. p. 214-218. 5445835 https://doi.org/10.1109/ICCEA.2010.49