Performance impact of dynamic parallelism on different clustering algorithms

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 8752, Issue , 2013, Pages

  DiMarco, Jeffrey ^a   Taufer, Michela ^a  

^a University of Delaware   (United States)

Author keywords

CUDA 5.0; Divisive hierarchical clustering; K means

Indexed keywords

CUDA 5.0; DATA DEPENDENCIES; DATA-DEPENDENT ALGORITHMS; DIVISIVE HIERARCHICAL CLUSTERING; HIER-ARCHICAL CLUSTERING; K-MEANS; K-MEANS CLUSTERING; PERFORMANCE IMPACT;

COMPUTER SIMULATION;

CLUSTERING ALGORITHMS;

EID: 84881116805     PISSN: 0277786X     EISSN: 1996756X     Source Type: Conference Proceeding    
DOI: 10.1117/12.2018069     Document Type: Conference Paper

References (5)

1. NVIDIA, Cuda Dynamic Parallelism Programming Guide. URL: http://docs.nvidia.com/cuda/pdf/CUDA-Dynamic-Parallelism-Programming-Guide.pdf (August 2012).
2. Steinbach, M., Karypis, G., and Kumar, V., "A comparison of document clustering techniques, " KDD Workshop on Text Mining, 400(1), 525-526 (2000).
3. Jain, A. K., "Data clustering: 50 years beyond K-means., " Pattern Recognition Letters, 31(8), 651-666 (2010).
4. Farivar, R., Rebolledo, D., Chan, E., and Campbell, R., "A parallel implementation of k-means clustering on GPUs, " In Proceedings of International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA), 340-345 (July 2008).
5. Chang, D., Kantardzic, M., and Ouyang, M., "Hierarchical clustering with CUDA/GPU, " In Proceedings of the 22nd International Conference on Parallel and Distributed Computing and Communication Systems (ISCA), 7- 12 (2009).