为嵌入式AI模型提供能效与精度平衡的优化方案
Pareto Optimal Benchmarking of AI Models on ARM Cortex Processors for Sustainable Embedded Systems
- 构建自动化测试框架，系统评估不同处理器与模型组合
- 发现浮点运算量与推理时间近似线性相关，可预测计算需求
- 推荐M7用于短周期任务，M4适合长时推理，M0+适配简单任务
本文提出一种面向ARM Cortex处理器（M0+, M4, M7）的实用基准测试框架，聚焦嵌入式系统中AI模型的能效、精度与资源利用。通过设计自动化测试平台，系统评估关键性能指标（KPI），识别处理器与模型的最佳组合。研究发现浮点运算量（FLOPs）与推理时间呈近似线性关系，可作为计算需求的可靠估计指标。基于帕累托分析，实现能耗与模型精度间的权衡，确保应用在满足性能要求的同时兼顾可持续性。结果显示，M7处理器适用于短推理周期，M4在长时间任务中更具能效优势，而M0+虽不适用于复杂模型，但适合轻量级任务。本研究为开发者提供了设计高效能、低功耗嵌入式AI系统的实用指导。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。