|
|
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Pellentesque eu lorem eu tellus tempor eleifend. Morbi suscipit eu neque sollicitudin posuere. Suspendisse vel imperdiet velit. Aliquam nibh lectus, viverra sagittis ullamcorper at, molestie a dui. Vestibulum nec nulla elit. Sed mollis lacinia bibendum. Aenean tortor odio, varius non placerat eu, sodales in ipsum. Praesent finibus nisl eget hendrerit euismod. Morbi sit amet libero eget ante blandit lobortis. Nullam porttitor ac quam sed mattis. Aliquam id varius nulla.
|
|
SpiNNaker is a biologically inspired, massively parallel computing system optimized for modeling and simulating large-scale real-time networks. In this work, we use the SpiNN-5 (SpiNNaker 103) board [^1] [^2], which consists of 48 SpiNNaker chips. Each chip contains 18 ARM cores with a 32 kB ITCM (instruction tightly coupled memory) and a 64 kB DTCM (data tightly coupled memory) per core. Moreover, a 128 MB SDRAM is shared between the 18 cores. To imitate the high connectivity of the brain, the cores are interconnected by an asynchronous Network-on-Chip (NoC) through a multicast packet-routing mechanism. In addition, SpiNN-5 uses three Xilinx Spartan-6 FPGAs for high-speed serial links.
|
|
|
|
|
|
|
|
Nam sagittis augue vel imperdiet rutrum. Ut ornare est quis feugiat placerat. Praesent lacus massa, posuere non diam accumsan, posuere sollicitudin purus. Fusce pharetra nunc quis dolor gravida, ut faucibus enim venenatis. Nam ultricies ex ac risus tincidunt pellentesque. Nam facilisis dui quis leo porta mollis. Curabitur a feugiat ipsum. Suspendisse potenti. Fusce suscipit sem nec placerat vehicula. Suspendisse mauris diam, imperdiet ac suscipit quis, semper ac sem. Vivamus porta, dolor vel mattis rutrum, nisi lorem sodales eros, id congue dolor erat sit amet lectus. Sed vitae quam eu magna aliquam iaculis sit amet et justo. Nam scelerisque laoreet justo, ac mattis est finibus sed.
|
|
A 100 MB Ethernet controller handles the connection between the SpiNNaker board and the computer. We use it to load data to the SpiNNaker memory to perform a real-time simulation. Furthermore, the sPyNNaker [^3] is a software package used to define models in PyNN script [^4] and translates models into a suitable form for SpiNNaker.
|
|
|
|
|
|
|
|
Aenean purus nunc, cursus nec purus sit amet, pharetra rhoncus ligula. Curabitur feugiat sed nulla eu semper. Nulla eget ipsum sit amet metus lacinia lacinia. Aenean imperdiet enim mauris, nec pellentesque mauris iaculis sed. Ut accumsan quam vel congue egestas. Nullam pretium diam vel sagittis maximus. Etiam vestibulum suscipit facilisis. Nulla id iaculis neque. Fusce leo elit, vulputate et risus et, consequat venenatis metus. Praesent ultrices ligula quis faucibus viverra. Duis pretium tellus metus, non egestas nulla condimentum ut. Cras tincidunt mauris eget aliquet faucibus. Duis at ex id ligula iaculis tristique et a nulla. Proin hendrerit pellentesque dolor, sit amet ultrices est venenatis nec. Duis vehicula ligula sit amet vehicula viverra. Sed facilisis tellus dolor, a molestie libero iaculis vel. |
|
<div style="width:100%; text-align:center;">
|
|
\ No newline at end of file |
|
<img src="img/Spinn-5.jpg" width="50%"><br>
|
|
|
|
Spinn-5
|
|
|
|
</div>
|
|
|
|
|
|
|
|
## Usefull Scripts
|
|
|
|
To facilitate the use of the board, a couple of scripts are available for use:
|
|
|
|
|
|
|
|
- [Weights extractor](#Usefull-Scripts)
|
|
|
|
- [Activity visualizer](#Usefull-Scripts)
|
|
|
|
- [CSNN-to-Spinn5 weight transfer](#Usefull-Scripts)
|
|
|
|
- [Spinn-5 classification accuracy](#Usefull-Scripts)
|
|
|
|
|
|
|
|
In addition, example of use are alos avialable here:
|
|
|
|
|
|
|
|
## Official Documentation
|
|
|
|
|
|
|
|
Software for SpiNNaker: <br>
|
|
|
|
https://spinnakermanchester.github.io/
|
|
|
|
|
|
|
|
PyNN: A Python package for simulator-independent specification of neuronal network models: <br>
|
|
|
|
https://neuralensemble.org/PyNN/
|
|
|
|
|
|
|
|
[^1]: Painkras et al., 2013
|
|
|
|
[^2]: Furber et al., 2012
|
|
|
|
[^3]: Rhodes et al., 2018
|
|
|
|
[^4]: Davison et al., 2009 |
|
|
|
\ No newline at end of file |
