Publication Date


Publication Title

Proceedings of the 15th IPDPS 2000 Workshops on Parallel and Distributed Processing


Many common implementations of Message Passing Inter- face (MPI) implement collective operations over point-to-point operations. This work examines IP multicast as a framework for collective operations. IP multicast is not reliable. If a receiver is not ready when a message is sent via IP multicast, the message is lost. Two techniques for ensuring that a message is not lost due to a slow receiving process are examined. The techniques are implemented and compared experimentally over both a shared and a switched Fast Ethernet. The average performance of collective operations is improved as a function of the number of participating processes and message size for both networks.