MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI

2024-10-15

AI Summary

Lack of a unified benchmark for cross-scale (μW–MW) energy efficiency evaluation of machine learning systems hinders sustainable AI development. This paper introduces MLPerf Power—the first standardized, system-level energy efficiency benchmarking framework spanning IoT edge devices to hyperscale data centers—establishing a novel, multi-organization collaborative paradigm for reproducible power-performance co-analysis. Built upon MLPerf standard workloads, it integrates high-accuracy power measurement, fine-grained power modeling, cross-platform normalization, and rigorously defined experimental protocols. Empirical evaluation across 60 diverse systems yields 1,841 measurements, enabling the first systematic, quantitative characterization of trade-offs among model complexity, hardware performance, and energy efficiency. The results provide a reproducible benchmark, quantifiable insights, and practical guidelines for full-stack optimization across the edge-to-cloud continuum.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Human-in-the-loop Machine Learning
• Multiagent Systems: Multiagent Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Security and privacy of machine learning and AI applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Rapid adoption of machine learning (ML) technologies has led to a surge in power consumption across diverse systems, from tiny IoT devices to massive datacenter clusters. Benchmarking the energy efficiency of these systems is crucial for optimization, but presents novel challenges due to the variety of hardware platforms, workload characteristics, and system-level interactions. This paper introduces MLPerf Power, a comprehensive benchmarking methodology with capabilities to evaluate the energy efficiency of ML systems at power levels ranging from microwatts to megawatts. Developed by a consortium of industry professionals from more than 20 organizations, MLPerf Power establishes rules and best practices to ensure comparability across diverse architectures. We use representative workloads from the MLPerf benchmark suite to collect 1,841 reproducible measurements from 60 systems across the entire range of ML deployment scales. Our analysis reveals trade-offs between performance, complexity, and energy efficiency across this wide range of systems, providing actionable insights for designing optimized ML solutions from the smallest edge devices to the largest cloud infrastructures. This work emphasizes the importance of energy efficiency as a key metric in the evaluation and comparison of the ML system, laying the foundation for future research in this critical area. We discuss the implications for developing sustainable AI solutions and standardizing energy efficiency benchmarking for ML systems.

Problem

• Benchmarking energy efficiency of ML systems
• Evaluating ML systems from microwatts to megawatts
• Standardizing energy efficiency for sustainable AI

Innovation

• Benchmarks ML energy efficiency
• Covers microwatts to megawatts
• Ensures cross-architecture comparability