Fault-tolerant method with distributed monitoring and management technique for 3D stacked meshes

Abstract

In this paper, we present a fully adaptive routing algorithm for 3D stacked mesh, called 3D-FAR. This algorithm utilizes two, two, and four virtual channels along the X, Y, and Z dimensions, respectively. It allows packets to take any shortest paths between the source and destination routers. 3D-FAR divides the network into four disjoint subnetworks. To improve the fault-tolerant capability of the network, packets are able to switch between subnetworks in an ascending order. In this paper, we also propose a fault-tolerant algorithm for 3D mesh network, called 3D-FT. This method is discussed both for tolerating faulty routers and links in the network. For tolerating faulty routers, only the shortest paths are taken while for tolerating faulty links, the non-minimal paths are used only when the source and destination routers are located in the same dimension with a faulty link between them. 3D-FT utilizes a distributed monitoring and management technique to distribute the fault statuses among the surrounding routers.