Job-level Carbon and Water Footprint Estimation for HPC: Bias Assessment from Runtime to Full Life Cycle

2026/07/21 by Xi Chen, Chris Broekema, Rob van Nieuwpoort · 1 voice · 1 citation
#cs.PF

paper · pdf

Abstract

High performance computing evaluation has traditionally focused on performance and energy, but these metrics alone cannot capture the sustainability cost of runtime configurations. We proposes a unified job-level water and carbon accounting framework with both operational and embodied impacts. Results show that higher thread counts generally reduce total footprint, but the benefit diminishes at higher thread counts. Water is mainly dominated by embodied impact, whereas carbon is mainly dominated by operational impact.

Citations

• More than Carbon: Cradle-to-Grave environmental impacts of GenAI training on the Nvidia A100 GPU

Cited by

• Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy

Discussions

• Xi Chen, Chris Broekema, Rob van Nieuwpoort: Job-level Carbon and Water Footprint Estimation for HPC: Bias Assessment from Runtime to Full Life Cycle https://arxiv.org/abs/2607.19150 https://arxiv.org [bsky, 0 points, 0 comments]

Related

• ThirstyFLOPS: Water Footprint Modeling and Analysis Toward Sustainable HPC Systems
• Analysis of the carbon footprint of HPC
• WaterWise: Co-optimizing Carbon- and Water-Footprint Toward Environmentally Sustainable Cloud Computing
• Modeling the Carbon Footprint of HPC: The Top 500 and EasyC
• How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference