Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning
Abstract
The progress of some AI paradigms such as deep learning is said to be linked to an exponential growth in the number of parameters. There are many studies corroborating these trends, but does this translate into an exponential increase in energy consumption? In order to answer this question we focus on inference costs rather than training costs, as the former account for most of the computing effort, solely because of the multiplicative factors. Also, apart from algorithmic innovations, we account for more specific and powerful hardware (leading to higher FLOPS) that is usually accompanied with important energy efficiency optimisations. We also move the focus from the first implementation of a breakthrough paper towards the consolidated version of the techniques one or two year later. Under this distinctive and comprehensive perspective, we analyse relevant models in the areas of computer vision and natural language processing: for a sustained increase in performance we see a much softer growth in energy consumption than previously anticipated. The only caveat is, yet again, the multiplicative factor, as future AI increases penetration and becomes more pervasive.
- Publication:
-
Sustainable Computing: Informatics and Systems
- Pub Date:
- April 2023
- DOI:
- arXiv:
- arXiv:2109.05472
- Bibcode:
- 2023SCIS...3800857D
- Keywords:
-
- Artificial Intelligence;
- Deep learning;
- Inference;
- Energy consumption;
- Performance analysis;
- Performance evaluation;
- AI progress;
- Computer Science - Machine Learning;
- Computer Science - Artificial Intelligence
- E-Print:
- For a revised version and its published version refer to: Desislavov, Radosvet, Fernando Mart\'inez-Plumed, and Jos\'e Hern\'andez-Orallo. Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning. Sustainable Computing: Informatics and Systems, Volume 38, April 2023. (https://doi.org/10.1016/j.suscom.2023.100857)