Embodied Emissions of 2.5D and 3D Scaling in Chipletized GPUs for Low-Carbon AI
By Hannah Watson 1, Arjun Singh 1, Jennifer Stephenson 2,3, Job Soethoudt 2, Debjyoti Bhattacharjee 2, James Myers 1
1 imec, Cambridge, UK
2 imec, Leuven, Belgium,
3 Vrije Universiteit Brussel, Brussels, Belgium

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 theimec.netzero modelling 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.
To read the full article, click here
Related Chiplet
- Optical Chiplet
- Reverse Gearbox Chiplet
- FlexGen Multi-Die Smart Network-on-Chip (NoC) IP
- Ncore Multi-Die Interconnect IP
- Integrated voltage regulator (IVR) chiplet
Related Technical Papers
- Generative Design of Liquid-Cooling Channels for Thermal Management of 2.5D and 3D Integrated Advanced Packaging
- CHICO-Agent: An LLM Agent for the Cross-layer Optimization of 2.5D and 3D Chiplet-based Systems
- Wafer Warpage of Silicon Interposer in Manufacturing Processes for High Density 2.5D Advanced Packaging: Causes, Measurement, Analysis and Optimization
- FAPlace: Joint Optimization of Chiplet Placement and Interposer Footprint for 2.5D Systems
Latest Technical Papers
- Technical Challenges for Ultra Fine Pitch Hybrid Bonding
- DT-MATCH: Defect- and Topology-Aware Chiplet Matching for Yield Optimization in Heterogeneous Integration
- Starscream: Reimagining LLM Sharding on AMD Instinct GPUs with GPU Partitioning
- Tri-Stack-PIM: A Heterogeneous Multi-Die 3D-Integrated Processing-in-Memory Architecture for Efficient LLM Inference
- CU-3D: A Scalable Legality-Aware RTL-to-GDS Flow for 3D-IC Physical Design