Benchmarking Highly Parallel Hardware for Spiking Neural Networks in Robotics

Abstract

Animal brains still outperform even the most performant machines with significantly lower speed. Nonetheless, impressive progress has been made in robotics in the areas of vision, motion- and path planning in the last decades. Brain-inspired Spiking Neural Networks (SNN) and the parallel hardware necessary to exploit their full potential have promising features for robotic application. Besides the most obvious platform for deploying SNN, brain-inspired neuromorphic hardware, Graphical Processing Units (GPU) are well capable of parallel computing as well. Libraries for generating CUDA-optimized code, like GeNN and affordable embedded systems make them an attractive alternative due to their low price and availability. While a few performance tests exist, there has been a lack of benchmarks targeting robotic applications. We compare the performance of a neural Wavefront algorithm as a representative of use cases in robotics on different hardware suitable for running SNN simulations. The SNN used for this benchmark is modeled in the simulator-independent declarative language PyNN, which allows using the same model for different simulator backends. Our emphasis is the comparison between Nest, running on serial CPU, SpiNNaker, as a representative of neuromorphic hardware, and an implementation in GeNN. Beyond that, we also investigate the differences of GeNN deployed to different hardware. A comparison between the different simulators and hardware is performed with regard to total simulation time, average energy consumption per run, and the length of the resulting path. We hope that the insights gained about performance details of parallel hardware solutions contribute to developing more efficient SNN implementations for robotics.

A scalable implementation of the recursive least-squares algorithm for training spiking neural networks

“…Spiking neural networks can also be implemented in neuromorphic hardware as demonstrated in SpiNNaker (Furber et al, 2014 ), Intel's Loihi (Davies et al, 2018 ), and TrueNorth (Merolla et al, 2014 ). See Steffen et al ( 2021 ) and references therein for benchmarks for these systems. We note that, although the aforementioned systems allow for biologically plausible plasticity (Stimberg et al, 2020 ) and for learning complex tasks (Merolla et al, 2014 ; Davies et al, 2018 ), the contribution of our work is different in that we developed an efficient algorithm for learning to generate activity patterns in recurrently connected spiking neural networks.…”

Efficient parameter calibration and real-time simulation of large scale spiking neural networks with GeNN and NEST

“…To fully exploit their capabilities in a benchmark comparison one needs to optimize for each simulator and use case. Second, the community has not agreed on standardized benchmark models (Albers et al, 2022; Ostrau et al, 2022; Kulkarni et al, 2021; Steffen et al, 2021). The RBN is widely used in computational neuroscience.…”

A scalable implementation of the recursive least-squares algorithm for training spiking neural networks

“…Spiking neural networks can also be implemented in neuromorphic hardware as demonstrated in SpiNNaker [32], Intel’s Loihi [33] and TrueNorth [34]. See [35] and references therein for benchmarks for these systems. We note that, although the aforementioned systems allow for biologically plausible plasticity [30] and for learning complex tasks [33, 34], the contribution of our work is different in that we developed an efficient algorithm for learning to generate recurrent activity patterns in spiking neural networks.…”