GPU Toolchains

Controlling a flying robot with realistic brain models requires a very fast execution of the simulations. Our models run on GPUs for parallel execution which drastically speeds up the execution time compared to conventional CPUs.

Spineml logo large.pngIn collaboration between the Sheffield and Sussex teams, we developed an interface that combines high-level abstraction via the SpineCreator Graphical User Interface for model creation, and a code-generation framework via GeNN for implementation on the GPUs.  The models defined in SpineCreator are saved in the SpineML XML format. We use XML Translation to turn this model description in C++ code. These files can then be used in GeNN to create GPU code that is optimised for the model and the types of GPUs that we use. This combination provides portability and flexibility and allows us to test our models on different platforms.


GeNN is a GPU enhanced Neuronal Network simulation environment based on NVIDIA CUDA technology. Learn more at the GeNN Homepage:


The Spiking Neural Mark-up Language (SpineML) is a declarative XML based model description language for large scale neural network models. Learn more at the SpineML Homepage: