Tu(r)ning AI Green: Exploring Energy Efficiency Cascading with Orthogonal Optimizations

TL;DR

This paper advocates for a holistic, pipeline-wide approach to optimize AI energy efficiency, demonstrating that strategic, orthogonal combinations of optimizations can drastically reduce energy use while maintaining high performance.

Contribution

It introduces a comprehensive framework for energy-efficient AI pipeline design, emphasizing the importance of orthogonal optimization combinations across multiple pipeline phases.

Findings

Orthogonal optimization combinations can reduce energy consumption by up to 94.6%.

Energy efficiency improvements preserve over 95% of original model performance.

Treating energy efficiency as a primary design goal enhances sustainability in AI workflows.

Abstract

AI's exponential growth intensifies computational demands and energy challenges. While practitioners employ various optimization techniques, that we refer as "knobs" in this paper, to tune model efficiency, these are typically afterthoughts and reactive ad-hoc changes applied in isolation without understanding their combinatorial effects on energy efficiency. This paper emphasizes on treating energy efficiency as the first-class citizen and as a fundamental design consideration for a compute-intensive pipeline. We show that strategic selection across five AI pipeline phases (data, model, training, system, inference) creates cascading efficiency. Experimental validation shows orthogonal combinations reduce energy consumption by up to $94.6$% while preserving $95.95$% of the original F1 score of non-optimized pipelines. This curated approach provides actionable frameworks for informed sustainable AI that balance efficiency, performance, and environmental responsibility.