Title :
Pattern recognition with OpenCL heterogeneous platform
Author :
Vrtanoski, J. ; Stojanovski, Toni Draganov
Author_Institution :
Ericsson AB, Dubai, United Arab Emirates
Abstract :
OpenCL platform provides unified development environment for various multicore processors. In this paper, we evaluate the OpenCL framework for application in pattern recognition. We have selected the most common algorithm for Artificial Neural Networks (ANN) training - the backpropagation algorithm for parallelization with OpenCL because of its high demand for processing resources. We will show a SIMD version of the algorithm suitable for OpenCL implementation. Our OpenCL implementation showed 25.8 speedup of execution on ATI 5870 GPU compared to OpenCL execution on Intel Xeon W3530 when training on MNIST handwritten digits data set.
Keywords :
application program interfaces; backpropagation; graphics processing units; neural nets; parallel processing; pattern recognition; ANN training; ATI 5870 GPU; OpenCL heterogeneous platform; SIMD version; artificial neural network; backpropagation algorithm; pattern recognition; Back propagation; HPC; OpenCL; Pattern Recognition; Perceptron;
Conference_Titel :
Telecommunications Forum (TELFOR), 2012 20th
Conference_Location :
Belgrade
Print_ISBN :
978-1-4673-2983-5
DOI :
10.1109/TELFOR.2012.6419306
