Enhancing the simulation of membrane system on the GPU for the n-queens problem

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Previous approaches using active membrane systems to solve the N-queens problem defined many membranes with just one rule inside them. This resulted in many communication rules utilised to communicate between membranes, which made communications between the cores and the threads a very time-consuming process. The proposed approach reduces unnecessary membranes and communication rules by defining two membranes with many objects and rules inside each membrane. With this structure, objects and rules can evolve concurrently in parallel, which makes the model suitable for implementation on a Graphics processing unit (GPU). The speedup using a GPU with global memory for N=10 is 10.6 times, but using tiling and shared memory, it is 33 times.

Original languageEnglish
Pages (from-to)740-743
Number of pages4
JournalChinese Journal of Electronics
Volume24
Issue number4
DOIs
Publication statusPublished - 10 Oct 2015

Fingerprint

Graphics Processing Unit
Membrane
Membranes
Simulation
Communication
Data storage equipment
Shared Memory
Tiling
Thread
Graphics processing unit
Speedup

Keywords

  • Graphics processing unit (GPU)
  • Membrane computing
  • N-queens problem
  • Parallel processing

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Applied Mathematics

Cite this

Enhancing the simulation of membrane system on the GPU for the n-queens problem. / Muniyandi, Ravie Chandren; Maroosi, Ali.

In: Chinese Journal of Electronics, Vol. 24, No. 4, 10.10.2015, p. 740-743.

Research output: Contribution to journalArticle

@article{a5bceef1b2934a30ad83baace4b281c7,
title = "Enhancing the simulation of membrane system on the GPU for the n-queens problem",
abstract = "Previous approaches using active membrane systems to solve the N-queens problem defined many membranes with just one rule inside them. This resulted in many communication rules utilised to communicate between membranes, which made communications between the cores and the threads a very time-consuming process. The proposed approach reduces unnecessary membranes and communication rules by defining two membranes with many objects and rules inside each membrane. With this structure, objects and rules can evolve concurrently in parallel, which makes the model suitable for implementation on a Graphics processing unit (GPU). The speedup using a GPU with global memory for N=10 is 10.6 times, but using tiling and shared memory, it is 33 times.",
keywords = "Graphics processing unit (GPU), Membrane computing, N-queens problem, Parallel processing",
author = "Muniyandi, {Ravie Chandren} and Ali Maroosi",
year = "2015",
month = "10",
day = "10",
doi = "10.1049/cje.2015.10.012",
language = "English",
volume = "24",
pages = "740--743",
journal = "Chinese Journal of Electronics",
issn = "1022-4653",
publisher = "Chinese Institute of Electronics",
number = "4",

}

TY - JOUR

T1 - Enhancing the simulation of membrane system on the GPU for the n-queens problem

AU - Muniyandi, Ravie Chandren

AU - Maroosi, Ali

PY - 2015/10/10

Y1 - 2015/10/10

N2 - Previous approaches using active membrane systems to solve the N-queens problem defined many membranes with just one rule inside them. This resulted in many communication rules utilised to communicate between membranes, which made communications between the cores and the threads a very time-consuming process. The proposed approach reduces unnecessary membranes and communication rules by defining two membranes with many objects and rules inside each membrane. With this structure, objects and rules can evolve concurrently in parallel, which makes the model suitable for implementation on a Graphics processing unit (GPU). The speedup using a GPU with global memory for N=10 is 10.6 times, but using tiling and shared memory, it is 33 times.

AB - Previous approaches using active membrane systems to solve the N-queens problem defined many membranes with just one rule inside them. This resulted in many communication rules utilised to communicate between membranes, which made communications between the cores and the threads a very time-consuming process. The proposed approach reduces unnecessary membranes and communication rules by defining two membranes with many objects and rules inside each membrane. With this structure, objects and rules can evolve concurrently in parallel, which makes the model suitable for implementation on a Graphics processing unit (GPU). The speedup using a GPU with global memory for N=10 is 10.6 times, but using tiling and shared memory, it is 33 times.

KW - Graphics processing unit (GPU)

KW - Membrane computing

KW - N-queens problem

KW - Parallel processing

UR - http://www.scopus.com/inward/record.url?scp=84942753000&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942753000&partnerID=8YFLogxK

U2 - 10.1049/cje.2015.10.012

DO - 10.1049/cje.2015.10.012

M3 - Article

AN - SCOPUS:84942753000

VL - 24

SP - 740

EP - 743

JO - Chinese Journal of Electronics

JF - Chinese Journal of Electronics

SN - 1022-4653

IS - 4

ER -