Energy-Efficient Machine Learning on FPGA for Edge Devices: a Case Study - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2020

Energy-Efficient Machine Learning on FPGA for Edge Devices: a Case Study

Guillaume Devic
Gilles Sassatelli
Abdoulaye Gamatié

Abstract

This paper presents a case study on the combination of a few static code optimization with an FPGA prototype of heterogeneous multicore architecture to address the energy-efficient execution of machine learning algorithms at the edge computing nodes. Two kinds of optimizations are applied : usual compiler optimizations and real number representations (fixed-point versus floating-point). This study is conducted while accounting for the trade-off between training precision, performance, and energy.
Fichier principal
Vignette du fichier
Cortus_revised_Compas2020.pdf (602.58 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

lirmm-03041276 , version 1 (04-12-2020)
lirmm-03041276 , version 2 (02-01-2021)

Identifiers

  • HAL Id : lirmm-03041276 , version 1

Cite

Guillaume Devic, Gilles Sassatelli, Abdoulaye Gamatié. Energy-Efficient Machine Learning on FPGA for Edge Devices: a Case Study. Conférence francophone d'informatique en Parallélisme, Architecture et Système (Compas'2020), Jun 2020, Lyon, France. ⟨lirmm-03041276v1⟩
187 View
263 Download

Share

Gmail Facebook X LinkedIn More