Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning

Desislavov, Radosvet; Martínez‐Plumed, Fernando; Hernández‐Orallo, José

doi:10.1016/j.suscom.2023.100857

articleSustainable Computing Informatics and SystemsFeb 26, 2023HYBRID OA

Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning

RDRadosvet Desislavov FMFernando Martínez‐Plumed JHJosé Hernández‐Orallo

Universitat Politècnica de València

Indexed incrossref

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…

Citation impact

204

total citations

FWCI: 23.17
Percentile: 100%
References: 85

Citations per year

Authors

3

Topics & keywords

Topics

Keywords

Inference
FLOPS
Energy consumption
Computer science
Multiplicative function
Deep learning
Artificial intelligence
Consumption (sociology)

UN Sustainable Development Goals

Affordable and clean energy

No related works found for this paper.