General-purpose Dataflow Model with Neuromorphic Primitives

TL;DR

This paper introduces a neuromorphic dataflow model with new primitives that enhances programmability and control logic deployment on neuromorphic hardware, bridging the gap between versatility and efficiency.

Contribution

It proposes a novel neuromorphic dataflow model with 'when' and 'where' primitives, enabling general-purpose program execution with control flow on neuromorphic hardware.

Findings

Enables deployment of general-purpose programs on neuromorphic hardware.

Provides a compact and neuromorphic-compatible control logic representation.

Maintains hardware's plasticity and performance benefits.

Abstract

Neuromorphic computing exhibits great potential to provide high-performance benefits in various applications beyond neural networks. However, a general-purpose program execution model that aligns with the features of neuromorphic computing is required to bridge the gap between program versatility and neuromorphic hardware efficiency. The dataflow model offers a potential solution, but it faces high graph complexity and incompatibility with neuromorphic hardware when dealing with control flow programs, which decreases the programmability and performance. Here, we present a dataflow model tailored for neuromorphic hardware, called neuromorphic dataflow, which provides a compact, concise, and neuromorphic-compatible program representation for control logic. The neuromorphic dataflow introduces "when" and "where" primitives, which restructure the view of control. The neuromorphic dataflow embeds these primitives in the dataflow schema with the plasticity inherited from the spiking algorithms. Our method enables the deployment of general-purpose programs on neuromorphic hardware with both programmability and plasticity, while fully utilizing the hardware's potential.