Skip to main content
Open Access Publications from the University of California

UC San Diego

UC San Diego Previously Published Works bannerUC San Diego

Silicon Photonics with Applications to Data Center Networks


In data center applications, fiber-based optical interconnects can be used to provide point-to-point links enabling high-bandwidth, inter-rack, data communications. In order to provide for future network scalability, which must be able to handle ultra-large data flows and bandwidth-intensive requests, optical technologies are increasingly introduced to different levels of the data center architecture to enable a variety of transparent network or all-optical networking schemes. However, the use of bulk optical components, which take up valuable rack-space real estate, can be extremely energy and cost prohibitive, especially when scaled up to the size of industrial warehouse-scale computing and considering that predictions of future data center networks are expected to contain millions of nodes. As such, we study chip-scale, silicon photonic, integrated circuits and their use as the optical hardware in future data center implementations. This work describes aspects of the design and integration of silicon photonic devices, which can be used for high-bandwidth, multi-channel, wavelength division multiplexed, optical communications. Examples of silicon photonic subsystems are discussed, including the realization of an on-chip channelized spectrum monitor and a network-node-on-a-chip. These optical integrated circuits are meant to replace bulk optical components with their functional equivalents on monolithic silicon. This work demonstrates that silicon photonics may be advantageous in meeting the urgent hardware-scaling demands of high-bandwidth, multi-user, communication networks.

Many UC-authored scholarly publications are freely available on this site because of the UC's open access policies. Let us know how this access is important for you.

Main Content
For improved accessibility of PDF content, download the file to your device.
Current View