The Tech Download: How chip companies are looking to use light to solve this major AI bottleneck (www.cnbc.com)

AI companies are increasingly turning to photonics technology as a means to address the bottleneck of data transfer between AI chips and systems, which currently relies heavily on copper wires. By utilizing light to transmit data—an approach that can enhance both speed and energy efficiency—companies like Nvidia are investing billions into photonics development. This could significantly boost the performance of AI models, as faster communication between chips speeds up task execution, which is crucial for the fast-paced demands of AI applications. Nvidia has committed substantial funds, including $2 billion to firms like Lumentum, Coherent, and Marvell, aiming to scale its silicon photonics technology and enhance its networking and GPU-to-GPU interconnect capabilities. However, the transition to widespread photonics adoption presents challenges, including supply chain constraints and the necessity to redesign existing product roadmaps to incorporate optical components. As AI continues to shape the tech landscape, the integration of photonics could be pivotal in overcoming current limitations and driving the next wave of AI innovation.