imec 与 VUB 研究：3D 集成可降低 GPU 扩展的隐含碳排放

3D Integration Reduces Embodied-Emissions Impact Of GPU Scaling (imec, VUB)

AI 导读

imec 与布鲁塞尔自由大学（VUB）研究人员发表论文名为《Embodied Emissions of 2.5D and 3D Scaling in Chipletized GPUs for Low-Carbon AI》的论文，使用 imec netzero 建模平台估算 chiplet 化 GPU 在 2.5D 和 3D 扩展下的隐含碳排放（EE）。

正文 · 原文

popularity

Researchers at imec and Vrije Universiteit Brussels published “Embodied Emissions of 2.5D and 3D Scaling in Chipletized GPUs for Low-Carbon AI.”

Abstract
“GPU compute resources are scaling to support growing AI workloads, leading to further rises in the climate change impact of hyperscale data centers that rely on high-performance GPUs. To model how packaging decisions impact the carbon footprint we have estimated the embodied emissions (EE) of a chiplet-based GPU that has been scaled in 2.5D and 3D using the imec netzero modeling platform. We doubled the number of compute units and high bandwidth memory (HBM) capacity in the 2.5D and 3D scaled systems and found that 3D scaling results in an 89% increase in EE, as compared to an increase of 141% for 2.5D scaling, positioning 3D scaling as an attractive solution to limit the embodied emissions due to GPU scaling.”

Find the technical paper here. October 2026

Watson, Hannah, Arjun Singh, Jennifer Stephenson, Job Soethoudt, Jonas Svedas, Debjyoti Bhattacharjee, and James Myers. “Embodied Emissions of 2.5D and 3D Scaling in Chipletized GPUs for Low-Carbon AI.” arXiv preprint arXiv:2610.32830 (2026).