 |
| ||||
GraphChi is a free and open-source project that allows you to process computation on very large graphs by using a novel Parallel Sliding Windows -algorithm.
The graph will be split into P shards, each containing roughly the same number of edges in sorted order.
In other words, GraphChi is able to run very large graph computations on just a single machine, by using a novel algorithm for processing the graph from disk (SSD or hard drive).
The applications for GraphChi are written in the vertex-centric model, proposed by GraphLab and Google's Pregel.
Furthermore, GraphChi runs vertex-centric programs asynchronously (i.e changes written to edges are immediately visible to subsequent computation), and in parallel.
In addition, GraphChi supports streaming graph updates and removal of edges from the graph. Section 'Performance' contains some examples of applications implemented for GraphChi and their running times on GraphChi.
GraphChi is cross-platform and it works on Mac OS X and Linux.
Detailed instructions on how to install and use the GraphChi utility on your Mac are available HERE.
Here are some key features of "GraphChi":
· Vertex-centric computation model
· Wrapper for GraphLab 2.1 API
· Synchronous, parallel execution, with (optional) deterministic scheduling
· Runsgraphs with billions of edges, with linear scalability, on a standard consumer grade machine
· Uses large amounts of memory by preloading (caching), making it competitive on large servers: UsingMoreMemory
· Multidisk striping - RAID-style operation, see MultipleDisksSupports
· Functions well on both hard-drive and SSD.
· Evolving graphs, streaming graph updates (can add and delete edges): EvolvingAndStreamingGraphs
· Easy to install, no dependencies, headers-only
What's New in This Release: [ read full changelog ]
· Fixed problems with builds on some Ubuntus.
· Dynamic vertex data support http://code.google.com/p/graphchi/wiki/DynamicVertexData
Via: GraphChi 0.2b
No comments:
Post a Comment