Seamless Optical Cloud Computing across Edge-Metro Network for Generative AI
🤖 AI Summary
Generative AI deployment in cloud computing faces critical bottlenecks in energy efficiency and computational security. Method: This project proposes a photonic cloud computing architecture tailored for generative AI, establishing an optical computing center enabling seamless integration across edge and metropolitan-area networks. It innovatively implements optical-domain input encoding, optical neural network (ONN) model modulation, and parallel matrix multiplication, achieving the first native deployment of photonic computing at the edge–metropolitan network layer. Leveraging ONN modulation and wavelength-division-multiplexed (WDM) optical interconnects, it overcomes fundamental energy-efficiency and data-security limitations of conventional electronic cloud architectures. Contribution/Results: Experimental evaluation demonstrates an energy efficiency of 118.6 mW/TOPs—two orders of magnitude higher than state-of-the-art electronic solutions. End-to-end execution of complex generative models—including Stable Diffusion—is successfully realized, empirically validating the feasibility and practicality of photonic acceleration for generative AI workloads.
Application Category
📝 Abstract
The rapid advancement of generative artificial intelligence (AI) in recent years has profoundly reshaped modern lifestyles, necessitating a revolutionary architecture to support the growing demands for computational power. Cloud computing has become the driving force behind this transformation. However, it consumes significant power and faces computation security risks due to the reliance on extensive data centers and servers in the cloud. Reducing power consumption while enhancing computational scale remains persistent challenges in cloud computing. Here, we propose and experimentally demonstrate an optical cloud computing system that can be seamlessly deployed across edge-metro network. By modulating inputs and models into light, a wide range of edge nodes can directly access the optical computing center via the edge-metro network. The experimental validations show an energy efficiency of 118.6 mW/TOPs (tera operations per second), reducing energy consumption by two orders of magnitude compared to traditional electronic-based cloud computing solutions. Furthermore, it is experimentally validated that this architecture can perform various complex generative AI models through parallel computing to achieve image generation tasks.
Problem
Research questions and friction points this paper is trying to address.
Reducing power consumption in cloud computing for generative AI
Enhancing computational scale and security in optical networks
Deploying seamless optical computing across edge-metro networks
Innovation
Methods, ideas, or system contributions that make the work stand out.
Optical cloud computing across edge-metro network
Modulating inputs and models into light
High energy efficiency with 118.6 mW/TOPs
🔎 Similar Papers
No similar papers found.
