Parallel processing is efficient form of information processing which means to implement high performance computing systems. A communication network that links processors and memory modules determines the efficiency of these parallel systems. To provide the required connectivity and performance at reasonable cost, an interconnection network is used. Hence, multistage interconnection networks ar...

ÐAll-to-all personalized exchange is one of the most dense collective communication patterns and occurs in many important applications in parallel computing. Previous all-to-all personalized exchange algorithms were mainly developed for hypercube and mesh/torus networks. Although the algorithms for a hypercube may achieve optimal time complexity, the network suffers from unbounded node degrees ...

Hardware implementations of the Cube, Shuffle-Exchange, and Plus-Mi us-2 (PM2I) networks are examined. An analysis is made of recirculating (single stage) networks, multistage networks of combinational logic, and pipelined multistage networks. An expanded control structure for recirculating networks is introduced. It allows each processor to select its interconnection function independently of ...

We present a new multiple ring network for multiprocessors, called the Multistage Ring Network(MRN). The MRN has a 2-level hierarchy of register insertion rings, and its interconnection of global rings forms a type of the multistage network. The architecture of the MRN is effective at diffusing the global traffic to all global rings and the bandwidth of the network increases proportionally with...