Performance of hypercube routing schemes with or without buffering

Considers two different hypercube routing schemes, which are called the simple and the priority schemes. The authors evaluate the throughput of both the unbuffered and the buffered version of these schemes for random multiple node-to-node communications. The results obtained are approximate, but very accurate as simulations indicate, and are given in particularly interesting forms. They find that little buffer space (between one and three packets per link) is necessary to achieve throughput close to that of the infinite buffer case. They also consider two deflection routing schemes, called the simple nonwasting deflection and the priority nonwasting deflection schemes. They evaluate their throughput-using simulations, and compare them to the priority scheme. >