A grid network is a kind of computer network consisting of a number of (computer) systems connected in a grid topology.
In a regular grid topology, each node in the network is connected with two neighbors along one or more dimensions. If the network is onedimensional, and the chain of nodes is connected to form a circular loop, the resulting topology is known as a ring. Network systems such as FDDI use two counterrotating tokenpassing rings to achieve high reliability and performance. In general, when an ndimensional grid network is connected circularly in more than one dimension, the resulting network topology is a torus, and the network is called "toroidal". When the number of nodes along each dimension of a toroidal network is 2, the resulting network is called a hypercube.
A parallel computing cluster or multicore processor is often connected in regular interconnection network such as a de Bruijn graph ^{[1]}, a hypercube graph, a hypertree network, a fat tree network, a torus, or cubeconnected cycles.
Note that a grid network is not the same as a grid computer (or computational grid) (even though the nodes in a grid network are usually computers, and grid computing obviously requires some kind of computer network to interconnect the computers).
References
"A Networkbased Asynchronous Architecture for Cryptographic Devices" by Ljiljana Spadavecchia 2005. section "5.6.1.2 De Bruijn graphs", and section "5.6.2.2 Randomised routing in de Bruijn graphs".
See also
Full article ▸
