Tuesday, July 15, 2014

Fujitsu Develops Multi-layer, Full-mesh Cluster Topology

Fujitsu Laboratories has developed a technology that reduces the number of network switches used in a cluster supercomputer by 40%.

Instead of using a conventional, "fat tree" network topology, in which, for example, 6,000 servers would require about 800 switches, or possibly more than 2,000 switches, Fujitsu Labs is using a multi-layer full mesh topology in combination with a newly developed communications algorithm that controls transmission sequences to avoid data collisions.

Fujitsu said its approach can accommodate a large number of servers with relatively few switches by considering what would be an optimized data-exchange process, then connecting the cluster in a new way.  By using scheduling, servers connected to the various apex switches (A through F) will divert to a different apex, and also by avoid collisions within paths that traverse different layers (a1 through d3).


See also