Accelerating Graph Betweenness Centrality with CUDA

Originally published at:

Graph analysis is a fundamental tool for domains as diverse as social networks, computational biology, and machine learning. Real-world applications of graph algorithms involve tremendously large networks that cannot be inspected manually. Betweenness Centrality (BC) is a popular analytic that determines vertex influence in a graph. It has many practical use cases, including finding the…

I left this tab open overnight and my chrome memory usage went up to 1.5GB. None of my other tabs do this so I think that you have something allocating memory in the background?

This would probably be a better conversation to start via our contact form, but... We do nothing special (we're not knowingly allocating memory), but we do use Wordpress plugins including this Disqus plugin and the twitter feed plugin, which might be different from some sites. I will look into it. However in my experience Chrome can be a memory hog (still my preferred browser).

I have a question regarding paralleling graph operations. Can we find a simple path weight between one node to all other nodes of different type in a heterogeneous graph using similar strategy? Of course I intend to do that using the GPU.