Research

Paper

AI LLM February 19, 2026

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

Authors

Pranay Jain, Maximilian Kasper, Göran Köber, Axel Plinge, Dominik Seuß

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.

Metadata

arXiv ID: 2602.17508
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17508v1</id>\n    <title>Pareto Optimal Benchmarking of AI Models on ARM Cortex Processors for Sustainable Embedded Systems</title>\n    <updated>2026-02-19T16:21:47Z</updated>\n    <link href='https://arxiv.org/abs/2602.17508v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17508v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-19T16:21:47Z</published>\n    <arxiv:comment>11 pages, 7 figures, Funding: GreenICT@FMD (BMFTR grant 16ME0491K)</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <arxiv:journal_ref>EEAI 2025</arxiv:journal_ref>\n    <author>\n      <name>Pranay Jain</name>\n    </author>\n    <author>\n      <name>Maximilian Kasper</name>\n    </author>\n    <author>\n      <name>Göran Köber</name>\n    </author>\n    <author>\n      <name>Axel Plinge</name>\n    </author>\n    <author>\n      <name>Dominik Seuß</name>\n    </author>\n  </entry>"
}