Hybrid CPU-GPU model based simulation of spiking neural networks using a look-up table

Abstract

Brain is one of the most complex human organs. For long this has intrigued a number of researchers from various disciplines in the world. A lot of research has been done on brain since early days especially from the physiological, psychological angle. However, the advances in the computing technologies especially the High Performance Computing platform has opened several new avenues for researchers to carry out their research. In the in-silico approach of modelling the brain, the simulation is performed by constructing the networks which draw inspiration from the simple neuron model. We have performed a study on the hybrid CPU-GPU model based simulation of Spiking Neural Network. Our current work is to study the scalability by simulating the entire pipeline on a GPU.