Optimizing exact computation of Betweenness Centrality for CUDA

Aakriti Gupta
Supercomputer Education and Research Centre, Indian Institute of Science, Bangalore, India
Indian Institute of Science, 2013


   title={Optimizing exact computation of Betweenness Centrality for CUDA},

   author={Gupta, Aakriti},



Download Download (PDF)   View View   Source Source   



Betweenness centrality is an important metric in the study of network analysis. This report discusses the problem of exact computation of betweenness cenrality index in network analysis. BC is an important metric in small world network analysis which is expensive to compute. A new strategy is presented to parallelize the best known serial algorithm for computing BC on CUDA architecture exploring parallelism at all the different levels of granularity offered in the algorithm. Further optimizations are made into this strategy by exploiting CUDA specific notions of coalesced memory accesses, warping, shared memory etc.
No votes yet.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: