COFFEE: A Carbon-Modeling and Optimization Framework for HZO-based FeFET eNVMs

2026-02-04

AI Summary

This study addresses the absence of a systematic methodology for evaluating the full lifecycle carbon footprint of hafnium zirconium oxide (HZO)-based ferroelectric field-effect transistor (FeFET) non-volatile memory. It presents the first comprehensive lifecycle carbon modeling and optimization framework tailored for HZO-FeFET embedded non-volatile memory (eNVM), integrating fab-measured data, device process parameters, and architecture-level design space exploration to quantify both embodied carbon from manufacturing and operational carbon during use. Results show that at a 2 MB capacity, HZO-FeFET exhibits 11% higher embodied carbon per unit area than CMOS but only 23.3% (i.e., 1/4.3) of the embodied carbon per megabyte compared to SRAM. Replacing SRAM with HZO-FeFET in edge ML accelerators reduces embodied carbon by 42.3% and can lower operational carbon by up to 70%.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Evolutionary Computation
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Information and communication technologies account for a growing portion of global environmental impacts. While emerging technologies, such as emerging non-volatile memories (eNVM), offer a promising solution to energy efficient computing, their end-to-end footprint is not well understood. Understanding the environmental impact of hardware systems over their life cycle is the first step to realizing sustainable computing. This work conducts a detailed study of one example eNVM device: hafnium-zirconium-oxide (HZO)-based ferroelectric field-effect transistors (FeFETs). We present COFFEE, the first carbon modeling framework for HZO-based FeFET eNVMs across life cycle, from hardware manufacturing (embodied carbon) to use (operational carbon). COFFEE builds on data gathered from a real semiconductor fab and device fabrication recipes to estimate embodied carbon, and architecture level eNVM design space exploration tools to quantify use-phase performance and energy. Our evaluation shows that, at 2 MB capacity, the embodied carbon per unit area overhead of HZO-FeFETs can be up to 11% higher than the CMOS baseline, while the embodied carbon per MB remains consistently about 4.3x lower than SRAM across different memory capacity. A further case study applies COFFEE to an edge ML accelerator, showing that replacing the SRAM-based weight buffer with HZO-based FeFET eNVMs reduces embodied carbon by 42.3% and operational carbon by up to 70%.

Problem

• carbon footprint
• emerging non-volatile memory
• HZO-based FeFET
• sustainable computing
• life cycle assessment

Innovation

• carbon modeling
• HZO-based FeFET
• embodied carbon
• sustainable computing
• eNVM