A principled approach for energy-efficient training via phase-aware GPU frequency tuning

2026-09-21

AI Summary

为解决AI模型训练中的能源效率问题，提出PAFT系统，通过动态调整GPU频率以适应训练瓶颈，减少能耗而不影响性能。

Abstract

Modern AI model training imposes unprecedented computational demands, making it a key contributor to datacenter energy consumption. Yet a significant fraction of the energy consumed during training does not translate to useful computation due to bottlenecks throughout the training pipeline. We present PAFT, a phase-aware, dynamically adaptable GPU frequency tuning system that reduces energy consumption of training workloads with minimal performance overhead. The key insight behind PAFT is that bottlenecks represent an energy optimization opportunity, rather than purely a performance problem: when GPUs are bound to stall, PAFT opportunistically reduces their clock frequencies to match the pace of bottlenecked devices, saving energy without impacting execution time. PAFT achieves this by continuously monitoring pipeline behavior and applying fine-grained frequency adjustments, adapting to workload and system changes. Experiments conducted on twelve widely used models show that PAFT consistently outperforms all baselines, achieving energy savings of up to 46% with an average overhead of 4%.

Problem

• energy consumption
• training workloads
• bottlenecks

Innovation

• phase-aware
• GPU frequency tuning
• energy efficiency
• bottleneck identification
• dynamic adjustment