Information on running neuronal simulations on FPGAs¶

Background¶

…

Bluehive project¶

For more details, see here: http://www.opensourcebrain.org/projects/bluehive-showcase

Si Elegans project¶

For more details, see here: http://www.si-elegans.eu/

BrainFrame Project¶

The goal of the BrainFrame effort is creating a back-end hardware library of designs emulating the Cerebellum system, based on reconfigurable (DFEs in this case) platforms, as a practical simulation solution for real-time neuro-scientific experiments. Eventually also make a library of generic constructs that can used on general neuron model development. This backend will be combined with a PyNN front-end to implement the BrainFrame tool-flow. PyNN, a Python-based, simulator-independent language for specification of brain models, is a widely known and used framework by computational neuroscientists. PyNN is capable of achieving high-speed simulation and it already offers a common interface to popular simulation platforms such as NEURON and NEST as well as newly developing ones that show great future potetial, such as NeuroML.

For More Details See here: http://erasmusbrainproject.com/index.php/themes/brainframe

Other systems¶

A Large-Scale Spiking Neural Network Accelerator for FPGA Systems Systems
Kit Cheung, Simon R. Schultz, Wayne Luk, Imperial College London

A Biologically Plausible Real-time Spiking Neuron Simulation Environment Based on a Multiple-FPGA Platform
Shufan Yang, TM McGinnity, University of Ulster

An FPGA-based approach to high-speed simulation of conductance-based neuron models
E. L. Graas, E. A. Brown, Robert H. Lee, Emory University/Georgia Institute of Technology

FPGA-based Biophysically-Meaningful Modeling of Olivocerebellar Neurons
Georgios Smaragdos, Sebastian Isaza, Martijn Van Eijk, Ioannis Sourdis and Christos Strydis