The DRAM interconnect has been considered to be one of the main roadblocks lurking ahead in the technology evolution of current computing devices and architectures. With the advent of silicon photonics, it became technically feasible to implement the DRAM interconnect optically by embedding photonic integrated circuits right on the DRAMs. The optical interconnects have been irreversibly penetrating from the telecoms to the datacoms, and may continue to go deeper eventually down to the DRAMs. However, it is not yet clear when and how such further penetration will occur and find the right balance with legacies. This talk presents Samsung's feasibility effort in bringing light down to the 65-nm DRAMs. It will also share some lessons and insights learned from the effort, and hopefully address some of causes and constraints surrounding the when and how questions.
Dr. Dongjae Shin is a principal researcher at Samsung Advanced Institute of Technology, and is currently working on silicon photonics to leverage the silicon infrastructure of Samsung for emerging applications. Since 2002, he has been with Samsung for silicon photonics and optical communication R&D. Prior to Samsung, he was with Bell Labs, NJ for optical crossconnect R&D. He has two decades of industrial R&D experiences with 1 book, 50+ papers, and 100+ patents on silicon photonics, WDM-PON, VLC, and near-field optics.