提出分层能量估算模型，精准预测神经网络推理能耗。
WattLayer: Get Layers Right to Estimate Inference Energy of Neural Networks
- 基于分层分解方法，独立于具体任务估算能耗。
- 在超10万层数据上实现中位误差19.6%的高精度。
- 适用于新任务和硬件，助力绿色AI设计。
人工智能的广泛应用引发了对能耗的广泛关注，但缺乏标准化方法来准确估算不同任务与架构下的推理能耗。本文提出一种任务无关的分层能量估算模型，在3个主流任务、3种硬件平台上的295个神经网络架构、超过10万层数据上进行了评估。该方法达到19.6%的中位误差，优于现有最优方法。进一步证明，通过共享层结构，分层分解可泛化至新任务而无需重新训练。本研究为设计节能AI系统提供了工具、洞见与精确方法。
原文摘要 · Abstract (English)
The widespread adoption of Artificial Intelligence (AI) has led to increasing concerns about energy consumption, yet there is a lack of standardized methodologies to accurately estimate AI inference energy consumption, particularly across various tasks and architectures. In this study, we propose a task independent, layer-wise energy estimation model for AI architectures. Our model is evaluated on a large dataset of more than 100,000 layers for 295 neural network architectures across 3 widely-used tasks and 3 distinct hardware platforms. Our approach achieves a median error of 19.6%, outperforming state-of-the-art methods. We further show that layer-wise decomposition generalize to new tasks without complete retraining, by leveraging shared layers across architectures. It offer tools, insights and a precise methodology to empower stakeholders in designing energy-efficient AI systems.
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。