Cross-Layer Design for AI Acceleration with Non-Coherent Optical Computing
This addresses the problem of computational inefficiency in AI applications for researchers and engineers, but it appears incremental as it builds on existing optical computing approaches.
The paper tackles the challenge of accelerating AI workloads like ChatGPT and deep neural networks by proposing a cross-layer design for non-coherent optical computing platforms, aiming to overcome bottlenecks through device engineering, architectural innovations, and hardware/software co-design.
Emerging AI applications such as ChatGPT, graph convolutional networks, and other deep neural networks require massive computational resources for training and inference. Contemporary computing platforms such as CPUs, GPUs, and TPUs are struggling to keep up with the demands of these AI applications. Non-coherent optical computing represents a promising approach for light-speed acceleration of AI workloads. In this paper, we show how cross-layer design can overcome challenges in non-coherent optical computing platforms. We describe approaches for optical device engineering, tuning circuit enhancements, and architectural innovations to adapt optical computing to a variety of AI workloads. We also discuss techniques for hardware/software co-design that can intelligently map and adapt AI software to improve its performance on non-coherent optical computing platforms.