Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

17

EVOW
2010
Springer

favoriteEmaildiscussreport

536views Artificial Intelligence» more EVOW 2010»

Parallel Genetic Algorithm on the CUDA Architecture

13 years 8 months ago

Parallel Genetic Algorithm on the CUDA Architecture

Download www.fit.vutbr.cz

Abstract. This paper deals with the mapping of the parallel islandbased genetic algorithm with unidirectional ring migrations to nVidia CUDA software model. The proposed mapping is tested using Rosenbrock's, Griewank's and Michalewicz's benchmark functions. The obtained results indicate that our approach leads to speedups up to seven thousand times higher compared to one CPU thread while maintaining a reasonable results quality. This clearly shows that GPUs have a potential for acceleration of GAs and allow to solve much complex tasks.

Petr Pospichal, Jirí Jaros, Josef Schwarz

Real-time Traffic

Artificial Intelligence | EVOW 2010 | Islandbased Genetic Algorithm | Nvidia Cuda Software | Unidirectional Ring Migrations |

claim paper

Related Content

» Parallel graph component labelling with GPUs and CUDA

» Lowcost highspeed computer vision using NVIDIAs CUDA architecture

» Faster matrixvector multiplication on GeForce 8800GTX

» Parallel reconstruction of neighborjoining trees for large multiple sequence alignments us...

» An Architecture for Massive Parallelization of the Compact Genetic Algorithm

» KMeans on Commodity GPUs with CUDA

» Regular Lattice and SmallWorld Spin Model Simulations Using CUDA and GPUs

» Molecular Dynamics Simulations on Commodity GPUs with CUDA

» PGAC A Parallel Genetic Algorithm for Data Clustering

Post Info
More Details (n/a)

Added	02 Sep 2010
Updated	02 Sep 2010
Type	Conference
Year	2010
Where	EVOW
Authors	Petr Pospichal, Jirí Jaros, Josef Schwarz

Comments (0)