Documentation

From KDTWiki
Jump to: navigation, search

Contents

Obtaining and Installing KDT

Download
Installation

KDT is open-source under the BSD License and is available on our Download page.

While KDT is a Python module, it is backed by a high performance C++/MPI backend and thus must be compiled. Like most Python modules, we've provided a setup.py script which installs the KDT module, but some additional requirements exist. Please see the Installation page for instructions as well as examples of what was actually required to install KDT on particular machines.

Using KDT

  • Tutorials to illustrate KDT's ease-of-use, flexibility, and features.
  • If you'd like to use KDT on your own data, you may find the File Format Guide useful.

Combinatorial BLAS

KDT's high-performance backend is the Combinatorial BLAS, which is a separate project. The Combinatorial BLAS is included in KDT and does NOT need to be installed separately.

Publications

Please cite us in your work by citing our SDM'12 paper (below).


  • KDT overview, performance comparisons with other packages. Please cite this to cite KDT. Also available as a UCSB CS Tech Report

Adam Lugowski, David Alber, Aydın Buluç, John R. Gilbert, Steve Reinhardt, Yun Teng, Andrew Waranis - A Flexible Open-Source Toolbox for Scalable Complex Graph Analysis

Proceedings of the Twelfth SIAM International Conference on Data Mining (SDM12) pp. 930--941, April 2012
[  BibTeX  |  PDF  ]


  • KDT v0.2 filtering


Adam Lugowski, Aydın Buluç, John Gilbert, Steve Reinhardt - Scalable Complex Graph Analysis with the Knowledge Discovery Toolbox

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) pp. 5345--5348, March 2012
[  BibTeX  |  PDF  |  URL  ]



Aydın Buluç, Erika Duriakova, Armando Fox, John R. Gilbert, Shoaib Kamil, Adam Lugowski, Leonid Oliker, Samuel Williams - High-Productivity and High-Performance Analysis of Filtered Semantic Graphs

27th IEEE International Symposium on Parallel and Distributed Processing (IPDPS 2013) , May 2013
[  BibTeX  ]


Also a 2-page abstract:

Aydın Buluç, Armando Fox, John R. Gilbert, Shoaib Kamil, Adam Lugowski, Leonid Oliker, Samuel Williams - High-Performance Analysis of Filtered Semantic Graphs

Proceedings of the 21st international conference on Parallel architectures and compilation techniques pp. 463--464, New York, NY, USA, 2012
[  BibTeX  |  URL  ]

Personal tools
Namespaces
Variants
Actions
KDT
Toolbox