Analytic Framework for Estimating Memory Cost
Anirudh Shankar, Avhishek Chatterjee, and Anjan Chakravorty

TL;DR
This paper introduces a generalized analytical framework to quantify the environmental energy costs of AI models, aiding in sustainable AI development.
Contribution
It provides a foundational method to estimate AI's ecological footprint based on memory and compute requirements.
Findings
Framework quantifies energy costs of AI models.
Facilitates development of sustainable AI architectures.
Addresses environmental impact of large-scale AI deployment.
Abstract
As artificial intelligence (AI) models quickly spread and become more advanced, they are requiring an ever-increasing amount of data and compute capability, leading to a significant energy cost. Training and inference of AI models including the large language models (LLMs) and deep neural networks (DNNs) are contributing to a large carbon footprint owing to the massive amount of memory they consume in data centers. In this article, we present a generalized framework that quantifies these energy costs incurred to the environment. This framework provides a foundational quantification of AI's ecological footprint, facilitating the development of sustainable architectural strategies for future models.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
