Pareto Optimal Benchmarking of AI Models on ARM Cortex Processors for Sustainable Embedded Systems

TL;DR

This paper introduces a benchmarking framework for AI models on ARM Cortex processors, optimizing for energy efficiency, accuracy, and resource use in embedded systems, using Pareto analysis to guide sustainable AI deployment.

Contribution

It presents a systematic, automated benchmarking approach with Pareto analysis for balancing energy, accuracy, and performance of AI models on ARM Cortex processors.

Findings

M7 processor excels for short inference cycles

M4 processor offers better energy efficiency for longer tasks

M0+ suitable for simple AI tasks

Abstract

This work presents a practical benchmarking framework for optimizing artificial intelligence (AI) models on ARM Cortex processors (M0+, M4, M7), focusing on energy efficiency, accuracy, and resource utilization in embedded systems. Through the design of an automated test bench, we provide a systematic approach to evaluate across key performance indicators (KPIs) and identify optimal combinations of processor and AI model. The research highlights a nearlinear correlation between floating-point operations (FLOPs) and inference time, offering a reliable metric for estimating computational demands. Using Pareto analysis, we demonstrate how to balance trade-offs between energy consumption and model accuracy, ensuring that AI applications meet performance requirements without compromising sustainability. Key findings indicate that the M7 processor is ideal for short inference cycles, while the M4 processor offers better energy efficiency for longer inference tasks. The M0+ processor, while less efficient for complex AI models, remains suitable for simpler tasks. This work provides insights for developers, guiding them to design energy-efficient AI systems that deliver high performance in realworld applications.