GraphLab is a free, open-source graph-based, distributed computation framework written in C++.
Originally, GraphLab was created for Machine Learning tasks, but it has found great success at a broad range of other data-mining tasks; out-performing other abstractions by orders of magnitude.
Furthermore, GraphLab is the culmination of 4 years of research and development into graph computation, distributed computing, and machine learning.
What is extraordinary is that GraphLab scales to graphs with billions of vertices and edges easily, performing orders of magnitude faster than competing systems.
In addition, GraphLab mixes advances in machine learning algorithms, asynchronous distributed graph computation, prioritized scheduling, and graph placement with optimized low-level system design and efficient data-structures.
This way, GraphLab achieves unmatched performance and scalability in challenging machine learning tasks.
Detailed instructions on how to install and use the GraphLab utility on your Mac are available HERE.
GraphLab is cross-platform and it works on Mac OS X and Linux.
Here are some key features of "GraphLab":
Unified multicore/distributed API:
· write once run anywhere
Tuned for performance:
· optimized C++ execution engine leverages extensive multi-threading and asynchronous IO
· Run on large cluster deployments by intelligently placing data and computation
· Access your data directly from HDFS
Powerful Machine Learning Toolkits:
· Tackle challenging machine learning problems with ease
What's New in This Release: [ read full changelog ]
· Many bug fixes and several serious performance enhancements especially in the asynchronous engine.