Characterization of Off-wafer Pulse Communication in BrainScaleS Neuromorphic System

TL;DR

This paper systematically characterizes the off-wafer pulse communication infrastructure of the BrainScaleS neuromorphic system, focusing on throughput, delay, jitter, and pulse loss, and analyzes their impact on neural network performance.

Contribution

It provides a detailed evaluation of the communication infrastructure in BrainScaleS, offering insights into how distortions affect neural model accuracy and guiding hardware mapping strategies.

Findings

High bandwidth and temporal resolution are essential for accurate neural emulation.

Communication distortions like jitter and pulse loss significantly impact neural benchmark performance.

The evaluation methods are broadly applicable to neuromorphic hardware systems.

Abstract

Neuromorphic VLSI systems take inspiration from biology to enable efficient emulation of large-scale spiking neural networks and to explore new computational paradigms. To establish large neuromorphic systems, a sophisticated routing infrastructure is needed to communicate spikes between chips and to/from the host computer. For the BrainScaleS wafer-scale neuromorphic system considered in this work, especially the stimulation with input spikes and the recording of spikes is demanding, requiring high bandwidth and temporal resolution due to the accelerated emulation of neural dynamics 10.000 faster than biological real time. Here, we present a systematic characterization of the BrainScaleS off-wafer communication infrastructure implemented around Kintex7 FPGAs. The communication flow is characterized in terms of throughput, transmission delay, jitter and pulse loss. Further, we analyze the effect of the communication distortions (like pulse loss and jitter) on a neural benchmark model with highly varying spike activity. The presented methods and techniques for communication evaluation are general applicable and provide useful insights for the mapping of network models to the hardware such as the distribution of input spikes across communication channels.