VCSEL-based CPO for Scale-Up in A.I. Datacenter. Status and Perspectives

TL;DR

This paper discusses the importance of VCSEL-based co-packaged optics for scaling up AI datacenter networks, emphasizing energy efficiency, high bandwidth density, and the transition from copper interconnects.

Contribution

It highlights the suitability of VCSEL technology as a low-cost, reliable, and energy-efficient solution for high-speed optical interconnects in AI datacenters.

Findings

VCSEL technology offers high wall-plug efficiency at all bitrates.

Co-packaged optics are essential for scaling bandwidth in AI datacenters.

VCSELs provide a versatile and reliable optical solution.

Abstract

The drastic increase of bandwidth demands in AI datacenters requires new solutions with low power consumption and high bandwidth densities. Further increasing the total bandwidth with copper interconnects is challenging, thus it is crucial to introduce optics into the scale-up network. For this purpose, the most important metrics are the energy efficiency of the total link in addition to the spatial bandwidth-density and reach. With the inefficiency of copper traces at high speeds, transitioning to co-packaged optics is no longer optional but essential. Here, we show that the mature VCSEL technology offers the ideal combination of low-cost, low-latency, high-reliability, and energy efficiency at all bitrates, thanks to their unique versatility and high wall-plug-efficiency. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.