Accelerating Complex Brain-Model Simulations on GPU Platforms
H.A. Du Nguyen1,a, Zaid Al-Ars1,b, Georgios Smaragdos2,c and Christos Strydis2,d
1Laboratory of Computer Engineering, Faculty of EE, Mathematics and CS, Delft University of Technology, Delft, The Netherlands.
2Neuroscience Department, Erasmus Medical Center, Rotterdam, The Netherlands.
The Inferior Olive (IO) in the brain, in conjunction with the cerebellum, is responsible for crucial sensorimotorintegration functions in humans. In this paper, we simulate a computationally challenging IO neuron model consisting of three compartments per neuron in a network arrangement on GPU platforms. Several GPU platforms of the two latest NVIDIA GPU architectures (Fermi, Kepler) have been used to simulate largescale IO-neuron networks. These networks have been ported on 4 diverse GPU platforms and implementation has been optimized, scoring 3x speedups compared to its unoptimized version. The effect of GPU L1-cache and thread block size as well as the impact of numerical precision of the application on performance have been evaluated and best configurations have been chosen. In effect, a maximum speedup of 160x has been achieved with respect to a reference CPU platform.
Full Text (PDF)