HAMA is a distributed computing framework based on BSP (Bulk Synchronous Parallel) computing techniques for massive scientific computations (e.g., matrix, graph, network, ..., etc), Currently being incubated as one of the incubator project by the Apache Software Foundation.
The greatest benefit of adoption of BSP computing techniques is the opportunity to speed up iteration loops during the iterative process which requires several passes of messages before final processed output is available. (especially, such as finding the shortest path, and so on.)
Hama also provides an easy-to-program and flexible programming model as compared with traditional model of Message Passing, and also compatible with any distributed storage (e.g., HDFS, HBase, …, etc), so you can use the Hama BSP on your existing Hadoop clusters.
General Information
- Hama Official Website
- Hama Official Blog
- Presentations and Articles about Hama
- PoweredBy, a list of sites and applications powered by Hama
- Hama Architecture – Work in progress
User Documentation
- Hama User Guide Documents
- Getting Started with Hama
- Command Line Interfaces for hama shell script.
- BSP Programming Model
- Examples
Developer Documentation
- Roadmap, listing release plans
- How to contribute to Hama
- How to commit