Faster and Simpler SNN Simulation with Work Queues

TL;DR

This paper introduces a clock-driven SNN simulator utilizing work queues, achieving up to 3x faster performance than existing methods while simplifying implementation and increasing generality.

Contribution

The paper proposes a novel simulation pipeline based on work queues that enhances speed, reduces complexity, and improves flexibility over prior SNN simulators.

Findings

Up to 3x faster simulation performance

Simpler implementation process

More general and flexible simulation pipeline

Abstract

We present a clock-driven Spiking Neural Network simulator which is up to 3x faster than the state of the art while, at the same time, being more general and requiring less programming effort on both the user's and maintainer's side. This is made possible by designing our pipeline around "work queues" which act as interfaces between stages and greatly reduce implementation complexity. We evaluate our work using three well-established SNN models on a series of benchmarks.