Carbon-Efficient 3D DNN Acceleration: Optimizing Performance and Sustainability
By: Aikaterini Maria Panteleaki , Konstantinos Balaskas , Georgios Zervakis and more
Potential Business Impact:
Makes AI chips with less pollution.
As Deep Neural Networks (DNNs) continue to drive advancements in artificial intelligence, the design of hardware accelerators faces growing concerns over embodied carbon footprint due to complex fabrication processes. 3D integration improves performance but introduces sustainability challenges, making carbon-aware optimization essential. In this work, we propose a carbon-efficient design methodology for 3D DNN accelerators, leveraging approximate computing and genetic algorithm-based design space exploration to optimize Carbon Delay Product (CDP). By integrating area-efficient approximate multipliers into Multiply-Accumulate (MAC) units, our approach effectively reduces silicon area and fabrication overhead while maintaining high computational accuracy. Experimental evaluations across three technology nodes (45nm, 14nm, and 7nm) show that our method reduces embodied carbon by up to 30% with negligible accuracy drop.
Similar Papers
Accelerating shape optimization by deep neural networks with on-the-fly determined architecture
Computational Engineering, Finance, and Science
Makes designs faster by using smart computer guesses.
Accelerating shape optimization by deep neural networks with on-the-fly determined architecture
Computational Engineering, Finance, and Science
Makes designs faster by learning from tests.
Carbon Aware Transformers Through Joint Model-Hardware Optimization
Machine Learning (CS)
Makes AI use less energy and be greener.