We introduce a new technique for generating more efficient networks by systematically interlacing bypass rings to torus networks (iBT networks). The resulting network can improve the original torus network by reducing the network diameter, node-to-node distances, and by increasing the bisection width without increasing wiring and other engineering complexity. We present and analyze the statement that a 3D iBT network proposed by our technique outperforms 4D torus networks of the same node degree. We found that interlacing rings of sizes 6 and 12 to all three dimensions of a torus network with meshes 30 × 30 × 36 generate the best network of all possible networks, including 4D torus and hypercube of approximately 32,000 nodes. This demonstrates that strategically interlacing bypass rings into a 3D torus network enhances the torus network more effectively than adding a fourth dimension, although we may generalize the claim. We also present a node-to-node distance formula for the iBT networks.

Interlacing Bypass Rings to Torus Networks for More Efficient Networks

In this work, we have proposed a new token based Fairness Algorithm for Priority Processes (FAPP) that addresses both the issues and keeps the control message traffic reasonably low. One major limitation of the token based mutual exclusion algorithms for distributed environment like Raymond’s well-known work on invertedtree topology lies in the lack of fairness. Another aspect of the problem is in handling the prioritized processes. In one of our earlier works, both fairness and priority have been addressed in proposing an algorithm MRA-P. However, MRA-P suffered from some major shortcomings like lack of liveness, high message complexity, etc. The proposed FAPP algorithm, in spite of considering priority of processes, ensures liveness in terms of token requests from low priority processes. Formal verification on FAPP justify properties like correctness of the algorithm, low message complexity, and fairness in token allocation.

FAPP: A New Fairness Algorithm for Priority Process Mutual Exclusion in Distributed Systems

An analysis of the topological properties of the interlaced bypass torus (iBT) networks

Logical or virtual topology design problem in optical networking has emerged as a potential area of research due to its immense capability of reconfiguring the physical topology of the network to some optimal one satisfying the constraints imposed from various dimensions. This work is aimed towards designing an optimal logical topology for optical networks. The authors propose a regular, logical topology named Scalable Barrel Shifter network (SBS-net) to be used over an all-optical network using WDM. The major emphasis of the present work is to improve upon the scalability issue. The SBS-net connects any arbitrary numbers of nodes as opposed to standard regular topologies like the regular Barrel Shifter, de Bruijn graph, Shuffle-net and many others. The average hopping distance between two nodes using SBS-net topology is also found to be smaller compared to that in other logical interconnection networks.

A Scalable Barrel Shifter topology for all optical networks

Tree-based mutual exclusions

This paper presents a new logical topology SBS-net, a scalable barrel shifter network to be used as a logical topology over an all-optical network using WDM. The major emphasis of the present work is to improve upon the scalability issue. This SBS-net connects any arbitrary numbers of nodes as opposed to the barrel shifter, de Bruijn graph and Shufflenet. The average hopping distance between two nodes using this topology is smaller compared to that in de Bruijn graph, Shufflenet & GEM net.

T. Chattopadhyay

Papers

A new logical topology based on barrel shifter network over an all optical network