A copy network with shared buffers for large multicast ATM switches

Abstract

This paper proposes a new architecture for the copy network which is an integral part of multicast ATM switches. The new architecture makes use of the property that the Broadcast Banyan Network (BBN) is non-blocking if the active inputs are cyclically concentrated and the outputs are monotone. In the new architecture, by employing a token ring reservation scheme, the outputs of the copy network are reserved before a multicast cell is replicated. By the new copy principle, the number of copies requested by a multicast call is not limited by the size of the copy network so that very large multicast switches can be configured in a modular fashion. The sequence of cells is preserved in the new structure. Though physically separated, buffers within the copy network are completely shared, so that the throughput can reach loo%, and the cell delay and the cell loss probability can be made to be very small.

FPGA implementation of a multicasting crossbar switch

“…The switch fabric forwards the packets to the output ports with different scheduling methods and forwarding techniques. The multicasting switch networks can be classified into input queue switch networks [1,5,6], output queue switch networks [9] and shared switch networks [10] by the types of queues. Many researchers have proposed several (N,N) multicasting switch networks with N input ports, N output ports and N 2 cross points [3,4,7,8].…”