An efficient Manhattan‐distance‐constrained disjoint paths algorithm for incomplete mesh network

Abstract

Finding link/node-disjoint paths between a pair of nodes is capable of providing Quality of Service and reliable routing which is very critical for mesh-connected Network-on-Chip. State-of-art works usually aim at random topologies and multiple constraints. Therefore, it is difficult to optimize their time complexity. In this paper, MDPPIM (Manhattan-distance-constrained Disjoint Path Pair Problem in Incomplete Mesh) problem is presented based on Network-on-Chip application scenarios. Then, PCDP (Path-Counting Disjoint Path) algorithm is proposed to solve the MDPPIM problem with low time complexity. Compared with previous disjoint path algorithms, PCDP algorithm does not have to use Dijkstra's algorithm to find a shortest path. It is optimized according to the feature of incomplete mesh such as the regularity of mesh and Manhattan-distance constraint. Therefore, it is with low time complexity. Numerical results demonstrate the proposed PCDP algorithm's effectiveness and low time complexity.