Decoupled Access-Execute enabled DVFS for tinyML deployments on STM32 microcontrollers

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alvanaki, Elisavet Lydia, Katsaragakis, Manolis, Masouros, Dimosthenis, Xydis, Sotirios, Soudris, Dimitrios
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909241555550208
author Alvanaki, Elisavet Lydia
Katsaragakis, Manolis
Masouros, Dimosthenis
Xydis, Sotirios
Soudris, Dimitrios
author_facet Alvanaki, Elisavet Lydia
Katsaragakis, Manolis
Masouros, Dimosthenis
Xydis, Sotirios
Soudris, Dimitrios
contents Over the last years the rapid growth Machine Learning (ML) inference applications deployed on the Edge is rapidly increasing. Recent Internet of Things (IoT) devices and microcontrollers (MCUs), become more and more mainstream in everyday activities. In this work we focus on the family of STM32 MCUs. We propose a novel methodology for CNN deployment on the STM32 family, focusing on power optimization through effective clocking exploration and configuration and decoupled access-execute convolution kernel execution. Our approach is enhanced with optimization of the power consumption through Dynamic Voltage and Frequency Scaling (DVFS) under various latency constraints, composing an NP-complete optimization problem. We compare our approach against the state-of-the-art TinyEngine inference engine, as well as TinyEngine coupled with power-saving modes of the STM32 MCUs, indicating that we can achieve up to 25.2% less energy consumption for varying QoS levels.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Decoupled Access-Execute enabled DVFS for tinyML deployments on STM32 microcontrollers
Alvanaki, Elisavet Lydia
Katsaragakis, Manolis
Masouros, Dimosthenis
Xydis, Sotirios
Soudris, Dimitrios
Hardware Architecture
Over the last years the rapid growth Machine Learning (ML) inference applications deployed on the Edge is rapidly increasing. Recent Internet of Things (IoT) devices and microcontrollers (MCUs), become more and more mainstream in everyday activities. In this work we focus on the family of STM32 MCUs. We propose a novel methodology for CNN deployment on the STM32 family, focusing on power optimization through effective clocking exploration and configuration and decoupled access-execute convolution kernel execution. Our approach is enhanced with optimization of the power consumption through Dynamic Voltage and Frequency Scaling (DVFS) under various latency constraints, composing an NP-complete optimization problem. We compare our approach against the state-of-the-art TinyEngine inference engine, as well as TinyEngine coupled with power-saving modes of the STM32 MCUs, indicating that we can achieve up to 25.2% less energy consumption for varying QoS levels.
title Decoupled Access-Execute enabled DVFS for tinyML deployments on STM32 microcontrollers
topic Hardware Architecture
url https://arxiv.org/abs/2407.03711