Simulating large topologies in ns-3 using BRITE and CUDA driven global routing

Authors:
Brian Paul Swenson;George F. Riley
Affiliations:
Georgia Institute of Technology, Atlanta, GA;Georgia Institute of Technology, Atlanta, GA
Venue:
Proceedings of the 6th International ICST Conference on Simulation Tools and Techniques
Year:
2013

Citing 10
Cited 0

Introduction to Algorithms

Introduction to Algorithms
Stateless Routing in Network Simulations

MASCOTS '00 Proceedings of the 8th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems
BRITE: A Flexible Generator of Internet Topologies

BRITE: A Flexible Generator of Internet Topologies
A blocked all-pairs shortest-paths algorithm

Journal of Experimental Algorithmics (JEA)
Optimization principles and application performance evaluation of a multithreaded GPU using CUDA

Proceedings of the 13th ACM SIGPLAN Symposium on Principles and practice of parallel programming
All-pairs shortest-paths for large graphs on the GPU

Proceedings of the 23rd ACM SIGGRAPH/EUROGRAPHICS symposium on Graphics hardware
Accelerating large graph algorithms on the GPU using CUDA

HiPC'07 Proceedings of the 14th international conference on High performance computing
Solving path problems on the GPU

Parallel Computing
Modeling Internet topology

IEEE Communications Magazine
Routing of multipoint connections

IEEE Journal on Selected Areas in Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present two new modules for ns-3. The first is a BRITE module that allows ns-3 users to take advantage of the topology generation features of the BRITE topology generator. This module allows users to quickly create highly customizable, large scale topologies for simulation within ns-3. The second module is a new global routing module specifically designed to work with large ns-3 network topologies. This module leverages the parallel processing abilities of GPUs using CUDA. Using this new routing module on large topologies, we measured speedups of over three orders of magnitude compared to ns-3's current global routing protocol when performing global route computations.