Artificial neural network simulation on CUDA

Research output: Chapter in Book/Report/Conference proceedingsChapterpeer-review

Abstract

The advent of low cost GPU hardware and user friendly parallel programming APIs, such as NVIDIA CUDA means that affordable, programmable, high-performance computing environments for simulation are now attainable for development of scientific simulations. In this paper the authors present the Mine Hunter program, a parallel simulation of neural networks on NVIDIA CUDA. The simulation consists of 128 mine hunters in a mine field of 8192 mines, running on an Intel Quad Core i5-2500 3.3GHz 2 x Nvidia GeForce GTX 480. The results presented demonstrate that CUDA improves performance by up to 80% compared with the equivalent CPU implementation.

Original languageEnglish
Title of host publicationProceedings - 2012 IEEE/ACM 16th International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2012
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages228-233
Number of pages6
ISBN (Print)9780769548463
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event2012 IEEE/ACM 16th International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2012 - Dublin, Ireland
Duration: 25 Oct 201227 Oct 2012

Publication series

NameProceedings - IEEE International Symposium on Distributed Simulation and Real-Time Applications, DS-RT
ISSN (Print)1550-6525

Conference

Conference2012 IEEE/ACM 16th International Symposium on Distributed Simulation and Real Time Applications, DS-RT 2012
Country/TerritoryIreland
CityDublin
Period25/10/1227/10/12

Keywords

  • CUDA
  • GPU
  • Neural-Networks
  • Simulation

Fingerprint

Dive into the research topics of 'Artificial neural network simulation on CUDA'. Together they form a unique fingerprint.

Cite this