Title :
Accelerating Brain Simulations on Graphical Processing Units
Author :
Engin Kayraklioglu;Tarek El-Ghazawi;Zeki Bozkus
Author_Institution :
George Washington Univ., Washington, DC, USA
Abstract :
NEural Simulation Tool(NEST) is a large scale spiking neuronal network simulator of the brain. In this work, we present a CUDA® implementation of NEST. We were able to gain a speedup of factor 20 for the computational parts of NEST execution using a different data structure than NEST´s default. Our partial implementation shows the potential gains and limitations of such possible port. We discuss possible novel approaches to be able to adapt generic spiking neural network simulators such as NEST to run on commodity or high-end GPGPUs.
Keywords :
"Graphics processing units","Neurons","Biological neural networks","Instruction sets","Data structures","Layout","Brain modeling"
Conference_Titel :
Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 2015 IEEE International Conference on
DOI :
10.1109/CIT/IUCC/DASC/PICOM.2015.79