Low-Power Deep Learning Inference using the SpiNNaker Neuromorphic Platform

Technical Report · 23 January 2021

DOI:https://doi.org/10.2172/1761866· OSTI ID:1761866

Vineyard, Craig Michael ^[1]; Dellana, Ryan ^[1]; Aimone, James Bradley ^[1]; Severa, William Mark ^[1]

---

1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

n this presentation we will discuss recent results on using the SpiNNaker neuromorphic platform (48-chip model) for deep learning neural network inference. We use the Sandia Labs developed Whet stone spiking deep learning library to train deep multi-layer perceptrons and convolutional neural networks suitable for the spiking substrate on the neural hardware architecture. By using the massively parallel nature of SpiNNaker, we are able to achieve, under certain network topologies, substantial network tiling and consequentially impressive inference throughput. Such high-throughput systems may have eventual application in remote sensing applications where large images need to be chipped, scanned, and processed quickly. Additionally, we explore complex topologies that push the limits of the SpiNNaker routing hardware and investigate how that impacts mapping software-implemented networks to on-hardware instantiations.

• Research Organization: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
• Sponsoring Organization: USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
• DOE Contract Number: AC04-94AL85000; NA0003525
• OSTI ID: 1761866
• Report Number(s): SAND--2019-2471R; 673192
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING