Multidestination Message Passing in Wormhole K-ary N-cube Networks with Base Routing Conformed Paths 1

This paper proposes a novel concept of multidestination message passing mechanism for wormhole k-ary n-cube networks. Similar to the familiar car-pool concept, this mechanism allows data to be delivered to or picked-up from multiple nodes with a single message-passing step. Such messages can propagate along any valid path in a wormhole network conforming to the underlying base routing scheme (deterministic or adaptive). The mechanism requires very little modiication to the existing routers and can have unicast message-passing as a subset operation. A base-routing-conformed-path (BRCP) model to implement this mechanism is presented. The model is illustrated for several commonly-used routing schemes and the associated deadlock-freedom properties are analyzed. Using this model a set of new algorithms are proposed and evaluated to implement broadcasting and multicasting. It is shown that these algorithms can considerably reduce the latency of these collective communication operations compared to the Umesh (unicast-based multicast) 22] and the Hamiltonian-Path-based 20] schemes. A very interesting and counter-intuitive result is presented which shows that a mul-ticast can be implemented with reduced or near-constant latency as the number of processors participating in the multicast increases beyond a certain number. It is also shown that the BRCP model can take advantage of routing-adaptivity to reduce the latency of these operations further. These results are the rst ones in the wormhole-routing literature to propose broadcasting and multicasting schemes with such reduced latency on networks with determinis-tic and adaptive routing. The multidestination mechanism and the BRCP model establish a new foundation to provide fast and scalable collective communication support on wormhole-routed systems.