SNE: an Energy-Proportional Digital Accelerator for Sparse Event-Based Convolutions
Abstract
Event-based sensors are drawing increasing attention due to their high temporal resolution, low power consumption, and low bandwidth. To efficiently extract semantically meaningful information from sparse data streams produced by such sensors, we present a 4.5TOP/s/W digital accelerator capable of performing 4-bits-quantized event-based convolutional neural networks (eCNN). Compared to standard convolutional engines, our accelerator performs a number of operations proportional to the number of events contained into the input data stream, ultimately achieving a high energy-to-information processing proportionality. On the IBM-DVS-Gesture dataset, we report 80uJ/inf to 261uJ/inf, respectively, when the input activity is 1.2% and 4.9%. Our accelerator consumes 0.221pJ/SOP, to the best of our knowledge it is the lowest energy/OP reported on a digital neuromorphic engine. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000543342Publication status
publishedExternal links
Book title
2022 Design, Automation & Test in Europe Conference & Exhibition (DATE 2022)Pages / Article No.
Publisher
IEEEEvent
Subject
Event-based computing; neuromorphic platform; edge-computingOrganisational unit
03996 - Benini, Luca / Benini, Luca
Funding
871669 - A Model-driven development framework for highly Parallel and EneRgy-Efficient computation supporting multi-criteria optimisation (EC)
Related publications and datasets
Is part of: https://doi.org/10.5555/3539845.3540041
Notes
Confereence lecture held on 22 March 2022More
Show all metadata
ETH Bibliography
yes
Altmetrics