GPU boosted cnn simulator library for graphical flow-based programmability

Abstract

A graphical environment for CNN algorithm development is presented. The new generation of graphical cards with many general purpose processing units introduces the massively parallel computing into PC environment. Universal Machine on Flows- (UMF) like notation, highlighting image flows and operations, is a useful tool to describe image processing algorithms. This documentation step can be turned into modeling using our framework backed with MATLAB Simulink and the power of a video card. This latter relatively cheap extension enables a convenient and fast analysis of CNN dynamics and complex algorithms. Comparison with other PC solutions is also presented. For single template execution, our approach yields run times 40x faster than that of the widely used Candy simulator. In the case of simpler algorithms, real-time execution is also possible. Copyright © 2009 Vincent Auvray et al.