Published December 26, 2019 | Version v1
Conference paper Open

GPU Implementation of Neural-Network Simulations based on Adaptive-Exponential Models

  • 1. School of Electrical and Computer Engineering, National Technical University of Athens, Greece
  • 2. Neuroscience dept., Erasmus Medical Center, The Netherlands

Description

Detailed brain modeling has been presenting significant challenges to the world of high-performance computing (HPC), posing computational problems that can benefit from modern hardware-acceleration technologies. We explore the capacity of GPUs for simulating large-scale neuronal networks based on the Adaptive Exponential neuron-model, which is widely used in the neuroscientific community. Our GPU-powered simulator acts as a benchmark to evaluate the strengths and limitations of modern GPUs, as well as to explore their scaling properties when simulating large neural networks. This work presents an optimized GPU implementation that outperforms a reference multicore implementation by 50x, whereas utilizing a dual-GPU configuration can deliver a speedup of 90x for networks of 20,000 fully interconnected AdEx neurons.

Files

12_GPU_acceleration.pdf

Files (629.9 kB)

Name Size Download all
md5:9b39c4c2d60cdb8cd4726ae4ca6ac177
629.9 kB Preview Download

Additional details

Funding

EXA2PRO – Enhancing Programmability and boosting Performance Portability for Exascale Computing Systems 801015
European Commission