OpenSpike: An OpenRAM SNN Accelerator

TL;DR

OpenSpike is an open-source, fully open-source EDA tool-based SNN accelerator in 130 nm process, featuring reprogrammability, high throughput, and competitive performance with state-of-the-art SNNs.

Contribution

It demonstrates a fully open-source, reprogrammable SNN accelerator with integrated memory macros and high performance in a standard process.

Findings

Operates at 40 MHz with 48,262 images/sec throughput

Integrates over 1 million synaptic weights in 130 nm process

Achieves 56.8 GOPS/W efficiency

Abstract

This paper presents a spiking neural network (SNN) accelerator made using fully open-source EDA tools, process design kit (PDK), and memory macros synthesized using OpenRAM. The chip is taped out in the 130 nm SkyWater process and integrates over 1 million synaptic weights, and offers a reprogrammable architecture. It operates at a clock speed of 40 MHz, a supply of 1.8 V, uses a PicoRV32 core for control, and occupies an area of 33.3 mm^2. The throughput of the accelerator is 48,262 images per second with a wallclock time of 20.72 us, at 56.8 GOPS/W. The spiking neurons use hysteresis to provide an adaptive threshold (i.e., a Schmitt trigger) which can reduce state instability. This results in high performing SNNs across a range of benchmarks that remain competitive with state-of-the-art, full precision SNNs. The design is open sourced and available online: https://github.com/sfmth/OpenSpike