Simulation Studies of Gigabit Ethernet Versus Myrinet Using Real Application Cores

Parallel cluster computing projects use a large number of commodity PCs to provide cost-e ective computational power to run parallel applications. Because properly load-balanced distributed parallel applications tend to send messages synchronously, minimizing blocking is as crucial a requirement for the network fabric as are those of high bandwidth and low latency. We consider the selection of an optimal, commodity-based, interconnect network technology and topology to provide high bandwidth, low latency, and reliable delivery. Since our network design goal is to facilitate the performance of real applications, we evaluated the performance of myrinet and gigabit ethernet technologies in the context of working algorithms using modeling and simulation tools developed for this work. Our simulation results show that myrinet behaves well in the absence of congestion. Under heavy load, its latency su ers due to blocking in the distributed wormhole routing scheme. Conventional gigabit ethernet switches can not scale to support more than 64 gigabit ethernet ports today which leads to the use of cascaded switches. Bandwidth limitation in the interswitch links and extra storeand-forward delays limit aggregate performance of this con guration. The Avici switch router uses six 40 Gbps internal links to connect individual switching nodes in a wormhole-routed three-dimensional torus. Additionaly, the fabric's large speed-up factor and its per-connection bu er management scheme provides for non-blocking deliveries under heavy load.