Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations

TLDR

Neuromorphic systems emulate biological neural structure, and designers must choose how to emulate neural elements, whether to use analog or digital circuits, and how to interconnect silicon neurons. The paper presents the design of Neurogrid, a neuromorphic system for real‑time simulation of large‑scale neural models. Neurogrid uses shared circuits for all elements except the soma, implements most circuits analogly to maximize energy efficiency, and connects neural arrays in a tree network to maximize throughput. The design enables real‑time simulation of one million neurons with billions of synapses on 16 Neurocores consuming only three watts.

Abstract

In this paper, we describe the design of Neurogrid, a neuromorphic system for simulating large-scale neural models in real time. Neuromorphic systems realize the function of biological neural systems by emulating their structure. Designers of such systems face three major design choices: 1) whether to emulate the four neural elements-axonal arbor, synapse, dendritic tree, and soma-with dedicated or shared electronic circuits; 2) whether to implement these electronic circuits in an analog or digital manner; and 3) whether to interconnect arrays of these silicon neurons with a mesh or a tree network. The choices we made were: 1) we emulated all neural elements except the soma with shared electronic circuits; this choice maximized the number of synaptic connections; 2) we realized all electronic circuits except those for axonal arbors in an analog manner; this choice maximized energy efficiency; and 3) we interconnected neural arrays in a tree network; this choice maximized throughput. These three choices made it possible to simulate a million neurons with billions of synaptic connections in real time-for the first time-using 16 Neurocores integrated on a board that consumes three watts.