Experience of parallel AI programming with parallel Lisp

Research output: Contribution to journalArticle

Abstract

Parallelism or parallel execution is expected to improve the performance of Artificial Intelligence (AI) systems so that they can be applied to much wider areas. One of the major problems with parallelizing AI systems is the lack of methodology for parallel AI programming. This paper discusses key issues in parallel AI programming with parallel Lisp. By implementing two AI systems, OPS5 (a rule-based system) and ATMS (an intelligent database system), three main problems are observed: difficulty in identifying the most time-consuming small tasks, frequent access to global data, and over-sequential execution. Solutions to these problems are presented, including hierarchical decomposition of tasks, runtime control of multiprocessing, reader-writer locks and lazy and speculative computations.

Original languageEnglish
Pages (from-to)211-219
Number of pages9
JournalFuture Generation Computer Systems
Volume7
Issue number2-3
DOIs
Publication statusPublished - 1992
Externally publishedYes

Fingerprint

Artificial intelligence
Knowledge based systems
Decomposition

Keywords

  • ATMS
  • dynamic spawning
  • hierarchical decomposition
  • OPS5
  • parallel AI
  • Parallel Lisp
  • reader-writer lock
  • run-time control

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Experience of parallel AI programming with parallel Lisp. / Okuno, Hiroshi G.

In: Future Generation Computer Systems, Vol. 7, No. 2-3, 1992, p. 211-219.

Research output: Contribution to journalArticle

@article{3636846729134acbb69d75aa66c591ff,
title = "Experience of parallel AI programming with parallel Lisp",
abstract = "Parallelism or parallel execution is expected to improve the performance of Artificial Intelligence (AI) systems so that they can be applied to much wider areas. One of the major problems with parallelizing AI systems is the lack of methodology for parallel AI programming. This paper discusses key issues in parallel AI programming with parallel Lisp. By implementing two AI systems, OPS5 (a rule-based system) and ATMS (an intelligent database system), three main problems are observed: difficulty in identifying the most time-consuming small tasks, frequent access to global data, and over-sequential execution. Solutions to these problems are presented, including hierarchical decomposition of tasks, runtime control of multiprocessing, reader-writer locks and lazy and speculative computations.",
keywords = "ATMS, dynamic spawning, hierarchical decomposition, OPS5, parallel AI, Parallel Lisp, reader-writer lock, run-time control",
author = "Okuno, {Hiroshi G.}",
year = "1992",
doi = "10.1016/0167-739X(92)90008-Y",
language = "English",
volume = "7",
pages = "211--219",
journal = "Future Generation Computer Systems",
issn = "0167-739X",
publisher = "Elsevier",
number = "2-3",

}

TY - JOUR

T1 - Experience of parallel AI programming with parallel Lisp

AU - Okuno, Hiroshi G.

PY - 1992

Y1 - 1992

N2 - Parallelism or parallel execution is expected to improve the performance of Artificial Intelligence (AI) systems so that they can be applied to much wider areas. One of the major problems with parallelizing AI systems is the lack of methodology for parallel AI programming. This paper discusses key issues in parallel AI programming with parallel Lisp. By implementing two AI systems, OPS5 (a rule-based system) and ATMS (an intelligent database system), three main problems are observed: difficulty in identifying the most time-consuming small tasks, frequent access to global data, and over-sequential execution. Solutions to these problems are presented, including hierarchical decomposition of tasks, runtime control of multiprocessing, reader-writer locks and lazy and speculative computations.

AB - Parallelism or parallel execution is expected to improve the performance of Artificial Intelligence (AI) systems so that they can be applied to much wider areas. One of the major problems with parallelizing AI systems is the lack of methodology for parallel AI programming. This paper discusses key issues in parallel AI programming with parallel Lisp. By implementing two AI systems, OPS5 (a rule-based system) and ATMS (an intelligent database system), three main problems are observed: difficulty in identifying the most time-consuming small tasks, frequent access to global data, and over-sequential execution. Solutions to these problems are presented, including hierarchical decomposition of tasks, runtime control of multiprocessing, reader-writer locks and lazy and speculative computations.

KW - ATMS

KW - dynamic spawning

KW - hierarchical decomposition

KW - OPS5

KW - parallel AI

KW - Parallel Lisp

KW - reader-writer lock

KW - run-time control

UR - http://www.scopus.com/inward/record.url?scp=44049121358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=44049121358&partnerID=8YFLogxK

U2 - 10.1016/0167-739X(92)90008-Y

DO - 10.1016/0167-739X(92)90008-Y

M3 - Article

AN - SCOPUS:44049121358

VL - 7

SP - 211

EP - 219

JO - Future Generation Computer Systems

JF - Future Generation Computer Systems

SN - 0167-739X

IS - 2-3

ER -