CarbonSet: A Dataset to Analyze Trends and Benchmark the Sustainability of CPUs and GPUs
🤖 AI Summary
The growing tension between semiconductor performance enhancement and surging carbon emissions lacks a comprehensive, lifecycle-based sustainability quantification framework.
Method: We construct the first processor-level carbon footprint–performance dataset spanning ten years and covering mainstream CPUs and GPUs, enabling cross-architecture, time-series, and standardized full-lifecycle modeling. We further propose a sustainability benchmarking framework integrating life cycle assessment (LCA), carbon footprint modeling, and hardware performance normalization.
Results: Key findings reveal that carbon costs of advanced fabrication processes have risen substantially while energy efficiency gains lag; flagship chips introduced in the past three years exhibit over 50× higher total carbon emissions compared to earlier generations. Our work delivers a reproducible benchmark, diagnostic toolkit, and empirical foundation for green chip design—bridging critical gaps between sustainability metrics and hardware development.
Application Category
📝 Abstract
Over the years, the chip industry has consistently developed high-performance processors to address the increasing demands across diverse applications. However, the rapid expansion of chip production has significantly increased carbon emissions, raising critical concerns about environmental sustainability. While researchers have previously modeled the carbon footprint (CFP) at both system and processor levels, a holistic analysis of sustainability trends encompassing the entire chip lifecycle remains lacking. This paper presents CarbonSet, a comprehensive dataset integrating sustainability and performance metrics for CPUs and GPUs over the past decade. CarbonSet aims to benchmark and assess the design of next-generation processors. Leveraging this dataset, we conducted detailed analysis of flagship processors' sustainability trends over the last decade. This paper further highlights that modern processors are not yet sustainably designed, with total carbon emissions increasing more than 50$ imes$ in the past three years due to the surging demand driven by the AI boom. Power efficiency remains a significant concern, while advanced process nodes pose new challenges requiring to effectively amortize the dramatically increased manufacturing carbon emissions.
Problem
Research questions and friction points this paper is trying to address.
Analyze sustainability trends in CPU and GPU lifecycle
Benchmark carbon emissions and performance of modern processors
Address rising carbon emissions from AI-driven chip demand
Innovation
Methods, ideas, or system contributions that make the work stand out.
Comprehensive dataset for CPU and GPU sustainability
Analyzes decade-long sustainability trends in processors
Highlights rising carbon emissions in modern processors
🔎 Similar Papers
No similar papers found.
