A collaborative effort between Sandia National Laboratories and Kitware Inc., the Titan™ Informatics Toolkit
is a collection of scalable algorithms for data ingestion and analysis that
share a common set of data structures and a flexible, component-based
pipeline architecture. The algorithms in Titan span a broad range of
structured and unstructured analysis techniques, and
are particularly suited to parallel computation on distributed memory
supercomputers.
Titan components may be used by application developers using their native C++ API on all popular platforms, or using a broad set of language bindings that include Python, Java, TCL, and more. Developers will combine Titan components with their own application-specific business logic and user interface code to address problems in a specific domain. Titan is used in applications varying from command-line utilities and straightforward graphical user interface tools to sophisticated client-server applications and web services, on platforms ranging from individual workstations to some of the most powerful supercomputers in the world.
| Capability | Contacts |
|---|---|
| Parallel Latent Semantic Analysis | Daniel Dunlavy |
| Parallel Latent Dirichlet Allocation | Andy Wilson |
| Advanced Graph Algorithms | Will McLendon III |
| Streaming Machine Learning Algorithms | Warren Leon Davis IV |
| Parallel Canonical Correlation Analysis | Patricia Crossno |
©1997-2011 Sandia Corporation | Questions and Comments | Privacy and Security | 
News release RSS feed