Beyond Efficiency: Scaling AI Sustainably
- URL: http://arxiv.org/abs/2406.05303v2
- Date: Sat, 22 Jun 2024 00:33:22 GMT
- Title: Beyond Efficiency: Scaling AI Sustainably
- Authors: Carole-Jean Wu, Bilge Acun, Ramya Raghavendra, Kim Hazelwood,
- Abstract summary: Modern AI applications have driven ever-increasing demands in computing.
This paper characterizes the carbon impact of AI, including both operational carbon emissions from training and inference as well as embodied carbon emissions from hardware manufacturing.
- Score: 4.711003829305544
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Barroso's seminal contributions in energy-proportional warehouse-scale computing launched an era where modern datacenters have become more energy efficient and cost effective than ever before. At the same time, modern AI applications have driven ever-increasing demands in computing, highlighting the importance of optimizing efficiency across the entire deep learning model development cycle. This paper characterizes the carbon impact of AI, including both operational carbon emissions from training and inference as well as embodied carbon emissions from datacenter construction and hardware manufacturing. We highlight key efficiency optimization opportunities for cutting-edge AI technologies, from deep learning recommendation models to multi-modal generative AI tasks. To scale AI sustainably, we must also go beyond efficiency and optimize across the life cycle of computing infrastructures, from hardware manufacturing to datacenter operations and end-of-life processing for the hardware.
Related papers
- Game-Theoretic Deep Reinforcement Learning to Minimize Carbon Emissions and Energy Costs for AI Inference Workloads in Geo-Distributed Data Centers [3.3379026542599934]
This work introduces a unique approach combining Game Theory (GT) and Deep Reinforcement Learning (DRL) for optimizing the distribution of AI inference workloads in geo-distributed data centers.
The proposed technique integrates the principles of non-cooperative Game Theory into a DRL framework, enabling data centers to make intelligent decisions regarding workload allocation.
arXiv Detail & Related papers (2024-04-01T20:13:28Z) - Green Edge AI: A Contemporary Survey [49.47249665895926]
We present a contemporary survey on green edge AI.
Despite its potential, edge AI faces substantial challenges, mostly due to the dichotomy between the resource limitations of wireless edge networks and the resource-intensive nature of deep learning (DL)
We explore energy-efficient design methodologies for the three critical tasks in edge AI systems, including training data acquisition, edge training, and edge inference.
arXiv Detail & Related papers (2023-12-01T04:04:37Z) - CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data
Centers [18.54380015603228]
Training large-scale artificial intelligence (AI) models demands significant computational power and energy, leading to increased carbon footprint with potential environmental repercussions.
This paper delves into the challenges of training AI models across geographically distributed (geo-distributed) data centers, emphasizing the balance between learning performance and carbon footprint.
We propose a new framework called CAFE (short for Carbon-Aware Federated Learning) to optimize training within a fixed carbon footprint budget.
arXiv Detail & Related papers (2023-11-06T23:59:22Z) - Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks.
Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios.
New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
arXiv Detail & Related papers (2023-08-27T03:55:28Z) - Efficiency Pentathlon: A Standardized Arena for Efficiency Evaluation [82.85015548989223]
Pentathlon is a benchmark for holistic and realistic evaluation of model efficiency.
Pentathlon focuses on inference, which accounts for a majority of the compute in a model's lifecycle.
It incorporates a suite of metrics that target different aspects of efficiency, including latency, throughput, memory overhead, and energy consumption.
arXiv Detail & Related papers (2023-07-19T01:05:33Z) - Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A
Multi-Agent Reinforcement Learning Approach [48.18355658448509]
Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption.
Scheduling training jobs among geographically distributed cloud data centers unveils the opportunity to optimize the usage of computing capacity powered by inexpensive and low-carbon energy.
We propose an algorithm based on multi-agent reinforcement learning and actor-critic methods to learn the optimal collaborative scheduling strategy through interacting with a cloud system built with real-life workload patterns, energy prices, and carbon intensities.
arXiv Detail & Related papers (2023-04-17T02:12:30Z) - Measuring the Carbon Intensity of AI in Cloud Instances [91.28501520271972]
We provide a framework for measuring software carbon intensity, and propose to measure operational carbon emissions.
We evaluate a suite of approaches for reducing emissions on the Microsoft Azure cloud compute platform.
arXiv Detail & Related papers (2022-06-10T17:04:04Z) - Sustainable AI: Environmental Implications, Challenges and Opportunities [13.089123643565724]
We characterize the carbon footprint of AI computing by examining the model development cycle across industry-scale machine learning use cases.
We present an end-to-end analysis for what and how hardware-software design and at-scale optimization can help reduce the overall carbon footprint of AI.
arXiv Detail & Related papers (2021-10-30T23:36:10Z) - AI-based Modeling and Data-driven Evaluation for Smart Manufacturing
Processes [56.65379135797867]
We propose a dynamic algorithm for gaining useful insights about semiconductor manufacturing processes.
We elaborate on the utilization of a Genetic Algorithm and Neural Network to propose an intelligent feature selection algorithm.
arXiv Detail & Related papers (2020-08-29T14:57:53Z) - Convergence of Artificial Intelligence and High Performance Computing on
NSF-supported Cyberinfrastructure [3.4291439418246177]
Artificial Intelligence (AI) applications have powered transformational solutions for big data challenges in industry and technology.
As AI continues to evolve into a computing paradigm endowed with statistical and mathematical rigor, it has become apparent that single- GPU solutions for training, validation, and testing are no longer sufficient.
This realization has been driving the confluence of AI and high performance computing to reduce time-to-insight.
arXiv Detail & Related papers (2020-03-18T18:00:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.