“…These enhancements, in combination with parallel computing (Bower and Beeman, 1998; Migliore et al, 2006), have become a necessity to cope with the higher computational and the communication demands of neuroapplications. Recently, a number of developers have investigated the possibility of simulating spiking neural networks on a single Graphical Processing Unit (GPU) (Bernhard and Keriven, 2005; Fernandez et al, 2008; Fidjeland et al, 2009; Nageswaran et al, 2009a,b; Tiesel and Maida, 2009; Bhuiyan et al, 2010; Fidjeland and Shanahan, 2010; Han and Taha, 2010a,b; Hoffmann et al, 2010; Mutch et al, 2010; Scorciono, 2010; Yudanov et al, 2010; Nowotny, 2011; Ahmadi and Soleimani, 2011; Igarashi et al, 2011; Thibeault et al, 2011; Wang et al, 2011) or on multiple Graphics Processing Units (GPUs) (Brette and Goodman, 2012b). All these current simulators have shown significant improvements over their CPU only counterparts by integrating the utilization of GPUs.…”