Optimizing Random Forest-Based Inference on RISC-V MCUs at the Extreme Edge
METADATA ONLY
Loading...
Author / Producer
Date
2022-11
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Random forests (RFs) use a collection of decision trees (DTs) to perform the classification or regression. RFs are adopted in a wide variety of machine learning (ML) applications, and they are finding increasing use also in scenarios at the extreme edge of the Internet of Things (TinyML) where memory constraints are particularly tight. This article addresses the optimization of the computational and storage costs for running DTs on the microcontroller units (MCUs) typically deployed in TinyML scenarios. We introduce three alternative DT kernels optimized for memory- and compute-limited MCUs, providing insight into the key memory-latency tradeoffs on an open-source RISC-V platform. We identify key bottlenecks and demonstrate that SW optimizations enable up to significant memory footprint and latency decrease. Experimental results show that the optimized kernels achieve up to 4.5 $\mu \text{s}$ latency, $4.8\times $ speedup, and 45% storage reduction against the widely-adopted naive DT design. We carry out a detailed performance and energy cost analysis of various optimized DT variants: the best approach requires just 8 instructions and 0.155 pJ per decision.
Permanent link
Publication status
published
External links
Editor
Book title
Volume
41 (11)
Pages / Article No.
4516 - 4526
Publisher
IEEE
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Decision tree (DT); edge-computing; machine learning (ML); random forest (RF); reduced instruction set computer (RISC)-V
Organisational unit
03996 - Benini, Luca / Benini, Luca
Notes
Funding
101034126 - Pilot using Independent Local & Open Technologies (EC)