CarbonPATH: Carbon-aware pathfinding and architecture optimization for chiplet-based AI systems

2026-03-04

AI Summary

This work addresses the challenge of jointly optimizing performance, cost, and carbon footprint in heterogeneous AI chip design by introducing CarbonPATH, a novel framework that treats sustainability as a first-class design constraint. CarbonPATH systematically co-optimizes across application, architecture, chiplet, and packaging levels through multi-objective optimization. Leveraging simulated annealing, it efficiently explores a high-dimensional design space encompassing compute/memory scale, process node, interconnect type, and integration strategy (2D/2.5D/3D), while explicitly modeling both operational and embodied carbon emissions. Experimental results demonstrate that CarbonPATH uncovers system-level configurations overlooked by conventional approaches, achieving significant reductions in total carbon footprint without compromising performance or cost targets.

Technology Category

• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The exponential growth of AI has created unprecedented demand for computational resources, pushing chip designs to the limit while simultaneously escalating the environmental footprint of computing. As the industry transitions toward heterogeneous integration (HI) to address the yield and cost challenges of monolithic scaling, minimizing the carbon cost of these complex HI systems becomes critical. To fully exploit HI, a co-design approach spanning application, architecture, chip, and packaging is essential. However, this creates a vast design space with competing objectives, specifically the trade-offs between performance, cost, and carbon footprint (CFP) for sustainability. CarbonPATH is an early-stage pathfinding framework designed to address this multi-objective challenge. It identifies optimized HI systems by co-designing workload mapping, architectural parameters, and packaging technologies, while treating sustainability as a first-class design constraint. The framework accounts for a wide range of factors, including compute and memory sizes, chiplet technology nodes, communication protocols, integration style (2D, 2.5D, 3D), operational CFP, embodied CFP, and interconnect type. Using simulated annealing, CarbonPATH explores this high-dimensional space to identify solutions that balance traditional metrics against environmental impact. By capturing interactions across applications, architectures, chiplets, and packaging, CarbonPATH uncovers system-level solutions that traditional methods often miss due to restrictive assumptions or limited scope.

Problem

• carbon footprint
• heterogeneous integration
• chiplet-based AI systems
• sustainability
• multi-objective optimization

Innovation

• carbon-aware design
• heterogeneous integration
• chiplet-based systems
• multi-objective co-design
• sustainability optimization