8664

Acceleration of multivariate analysis techniques in TMVA using GPUs

A. Hoecker, H. McKendrick, J. Therhaag, A. Washbrook
CERN, Switzerland
Journal of Physics: Conference Series Volume 396, Part 2, 2012

@article{1742-6596-396-2-022055,

   author={A Hoecker and H McKendrick and J Therhaag and A Washbrook},

   title={Acceleration of multivariate analysis techniques in TMVA using GPUs},

   journal={Journal of Physics: Conference Series},

   volume={396},

   number={2},

   pages={022055},

   url={http://stacks.iop.org/1742-6596/396/i=2/a=022055},

   year={2012}

}

Download Download (PDF)   View View   Source Source   

877

views

A feasibility study into the acceleration of multivariate analysis techniques using Graphics Processing Units (GPUs) will be presented. The MLP-based Artificial Neural Network method contained in the TMVA framework has been chosen as a focus for investigation. It was found that the network training time on a GPU was lower than for CPU execution as the complexity of the network was increased. In addition, multiple neural networks can be trained simultaneously on a GPU within the same time taken for single network training on a CPU. This could be potentially leveraged to provide a qualitative performance gain in data classification.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: