GPU powered CNN simulator (SIMCNN) with graphical flow based programmability Export

@proceedings{citeulike:4644750, abstract = {In this paper, we introduce an innovative CNN algorithm development environment that significantly assists algorithmic design. The introduced graphical user interface uses Matlab Simulink with UMF-like program description, where direct functionality accompanies better accessability. The new generation of graphical cards incorporate many general purpose graphics processing units, giving the power of parallel computing to a simple PC environment cheaply. Therefore, analysis of CNN dynamics become more feasible with a common hardware setup. Our measurements demonstrate the efficiency of the realized system. In the case of simpler algorithms, real-time execution is also possible.}, author = {Soos, B. G. and Rak, A. and Veres, J. and Cserey, G.}, booktitle = {Cellular Neural Networks and Their Applications, 2008. CNNA 2008. 11th International Workshop on}, citeulike-article-id = {4644750}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/CNNA.2008.4588671}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4588671}, doi = {10.1109/CNNA.2008.4588671}, journal = {Cellular Neural Networks and Their Applications, 2008. CNNA 2008. 11th International Workshop on}, keywords = {ann, cnn, gpu, matlab}, pages = {163--168}, posted-at = {2009-05-27 13:59:26}, priority = {2}, title = {GPU powered CNN simulator (SIMCNN) with graphical flow based programmability}, url = {http://dx.doi.org/10.1109/CNNA.2008.4588671}, year = {2008} }

TY - CONF ID - citeulike:4644750 L3 - citeulike-article-id:4644750 N2 - In this paper, we introduce an innovative CNN algorithm development environment that significantly assists algorithmic design. The introduced graphical user interface uses Matlab Simulink with UMF-like program description, where direct functionality accompanies better accessability. The new generation of graphical cards incorporate many general purpose graphics processing units, giving the power of parallel computing to a simple PC environment cheaply. Therefore, analysis of CNN dynamics become more feasible with a common hardware setup. Our measurements demonstrate the efficiency of the realized system. In the case of simpler algorithms, real-time execution is also possible. JF - Cellular Neural Networks and Their Applications, 2008. CNNA 2008. 11th International Workshop on EP - 168 TI - GPU powered CNN simulator (SIMCNN) with graphical flow based programmability T2 - Cellular Neural Networks and Their Applications, 2008. CNNA 2008. 11th International Workshop on SP - 163 KW - ann KW - cnn KW - gpu KW - matlab AU - Soos, BG AU - Rak, A AU - Veres, J AU - Cserey, G PY - 2008/// UR - http://dx.doi.org/10.1109/CNNA.2008.4588671 ER -