We explore a novel, free-space optics based approach for building data center interconnects. It uses a digital micromirror device (DMD) and mirror assembly combination as a transmitter and a photodetector on top of the rack as a receiver (Figure 1). Our approach enables all pairs of racks to establish direct links, and we can reconfigure such links (i.e., connect different rack pairs) within 12 us. To carry traffic from a source to a destination rack, transmitters and receivers in our interconnect can be dynamically linked in millions of ways. We develop topology construction and routing methods to exploit this flexibility, including a flow scheduling algorithm that is a constant factor approximation to the offline optimal solution. Experiments with a small prototype point to the feasibility of our approach. Simulations using realistic data center workloads show that, compared to the conventional folded-Clos interconnect, our approach can improve mean flow completion time by 30-95% and reduce cost by 25-40%.
Optical-phased arrays (OPAs) enable complex beamforming, random-access beam pointing, and simultaneous scan and tracking of multiple targets by controlling the phases of two-dimensional (2D) coherent emitters. So far, no OPA can achieve all desirable features including large 2D arrays, high optical efficiency, wideband operation in wavelengths, fast response time, and large steering angles at the same time. Here, we report on a large-scale 2D OPA with novel microelectro-mechanical-system (MEMS)-actuated phase shifters. Wavelength-independent phase shifts are realized by physically moving a grating element in the lateral direction. The OPA has independent phase shifters across an aperture of . It has a measured beam divergence of , a field of view (FOV) of , and a response time of 5.7 μs. It is capable of providing about 25,600 rapidly steerable spots within its FOV. The grating phase shifters are optimized for the near-infrared telecom wavelength bands from 1200 to 1700 nm with 85% optical efficiency.
Combinatorial optimization problems over large and complex systems have many applications in social networks, image processing, artificial intelligence, computational biology and a variety of other areas. Finding the optimized solution for such problems in general are usually in non-deterministic polynomial time (NP)-hard complexity class. Some NP-hard problems can be easily mapped to minimizing an Ising energy function. Here, we present an analog all-optical implementation of a coherent Ising machine (CIM) based on a network of injection-locked multicore fiber (MCF) lasers. The Zeeman terms and the mutual couplings appearing in the Ising Hamiltonians are implemented using spatial light modulators (SLMs). As a proof-of-principle, we demonstrate the use of optics to solve several Ising Hamiltonians for up to thirteen nodes. Overall, the average accuracy of the CIM to find the ground state energy was ~90% for 120 trials. The fundamental bottlenecks for the scalability and programmability of the presented CIM are discussed as well.