TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
Abstract
Temporal Convolutional Networks (TCNs) are emerging lightweight Deep Learning models for Time Series analysis. We introduce an automated exploration approach and a library of optimized kernels to map TCNs on Parallel Ultra-Low Power (PULP) microcontrollers. Our approach minimizes latency and energy by exploiting a layer tiling optimizer to jointly find the tiling dimensions and select among alternative implementations of the causal and dilated 1D-convolution operations at the core of TCNs. We benchmark our approach on a commercial PULP device, achieving up to 103X lower latency and 20.3X lower energy than the Cube-AI toolkit executed on the STM32L4 and from 2.9X to 26.6X lower energy compared to commercial closed-source and academic open-source approaches on the same hardware target.
Cite
@article{arxiv.2203.12925,
title = {TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference},
author = {Alessio Burrello and Alberto Dequino and Daniele Jahier Pagliari and Francesco Conti and Marcello Zanghieri and Enrico Macii and Luca Benini and Massimo Poncino},
journal= {arXiv preprint arXiv:2203.12925},
year = {2022}
}