At the core of some of the latest generation of internet routers is a hardware switch that transports packets between the line cards. A central scheduler is required to select a set of packets from queues on the line cards that can be connected to the correct outputs simultaneously without blocking [1]. The larger the set chosen, the greater the throughput, but the decision must be made within the cycle time of the switch. This assignment of outputs to inputs subject to constraints imposed by the switch fabric is an example of a resource allocation problem which cans be solved by a Hopfield neural network [2,3]. We have implemented a Hopfield network as a parallel optical system incorporating a diffractive optical element (DOE) and measured its performance as a scheduler for both crossbar and self-routing switch fabrics.
展开▼
