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

arXiv: https://arxiv.org/abs/2410.12032 · HTML: https://mlsanity.com/paper/2410.12032/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 91 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [Sustainable AI: Environmental Implications, Challenges and Opportunities](https://mlsanity.com/paper/2111.00364/) (2021)
- [TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings](https://mlsanity.com/paper/2304.01433/) (2023)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models](https://mlsanity.com/paper/2007.03051/) (2020)
- [Compute Trends Across Three Eras of Machine Learning](https://mlsanity.com/paper/2202.05924/) (2022)
- [On The Computational Complexity of Self-Attention](https://mlsanity.com/paper/2209.04881/) (2022)
- [MLPerf Tiny Benchmark](https://mlsanity.com/paper/2106.07597/) (2021)
- [MLPerf Training Benchmark](https://mlsanity.com/paper/1910.01500/) (2019)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training](https://mlsanity.com/paper/2208.06102/) (2022)
- [Deep Audio-Visual Learning: A Survey](https://mlsanity.com/paper/2001.04758/) (2020)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference](https://mlsanity.com/paper/2403.20306/) (2024)
- [MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection](https://mlsanity.com/paper/1909.09347/) (2019)

## Built on by (most cited first, 16 of 16)

- [The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization](https://mlsanity.com/paper/2505.06371/) (2025)
- [TokenPowerBench: Benchmarking the Power Consumption of LLM Inference](https://mlsanity.com/paper/2512.03024/) (2025)
- [Intelligence per Watt: Measuring Intelligence Efficiency of Local AI](https://mlsanity.com/paper/2511.07885/) (2025)
- [Where Do the Joules Go? Diagnosing Inference Energy Consumption](https://mlsanity.com/paper/2601.22076/) (2026)
- [Watt Counts: Energy-Aware Benchmark for Sustainable LLM Inference on Heterogeneous GPU Architectures](https://mlsanity.com/paper/2604.09048/) (2026)
- [AI Benchmark Democratization and Carpentry](https://mlsanity.com/paper/2512.11588/) (2025)
- [ELANA: A Simple Energy and Latency Analyzer for LLMs](https://mlsanity.com/paper/2512.09946/) (2025)
- [Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems](https://mlsanity.com/paper/2605.22883/) (2026)
- [WattGPU: Predicting Inference Power and Latency on Unseen GPUs and LLMs](https://mlsanity.com/paper/2607.02391/) (2026)
- [Lifetime-Aware Design for Item-Level Intelligence at the Extreme Edge](https://mlsanity.com/paper/2509.08193/) (2025)
- [Metrics and evaluations for computational and sustainable AI efficiency](https://mlsanity.com/paper/2510.17885/) (2025)
- [PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems](https://mlsanity.com/paper/2602.18900/) (2026)
- [Position Paper: From Edge AI to Adaptive Edge AI](https://mlsanity.com/paper/2604.07360/) (2026)
- [OpenG2G: A Simulation Platform for AI Datacenter-Grid Runtime Coordination](https://mlsanity.com/paper/2605.05519/) (2026)
- [Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment](https://mlsanity.com/paper/2606.07632/) (2026)
- [A Measurement Study of LLM Inference Trade-offs Across Edge Continuum Hardware](https://mlsanity.com/paper/2609.08307/) (2026)

## Abstract (arXiv)

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.