Exploiting coarse grained parallelism in conceptual data mining: finding a needle in a haystack as a distributed effort

Blokpoel, Mark and Grootjen, Franc and Broek van den, Egon L. (2008) Exploiting coarse grained parallelism in conceptual data mining: finding a needle in a haystack as a distributed effort. In: 8th Dutch-Belgian Information Retrieval Workshop, DIR 2008, 14-15 April 2008, Maastricht, The Netherlands.

Preview

PDF
171Kb

Abstract:	A parallel implementation of Ganter’s algorithm to calculate concept lattices for Formal Concept Analysis is presented. A benchmark was executed to experimentally determine the algorithm’s performance, including an AMD Athlon64, Intel dual Xeon, and UltraSPARC T1, with respectively 1, 4, and 24 threads in parallel. Two subsets of Cranfield’s collection were chosen as document set. In addition, the theoretically maximum performance was determined. Due to scheduling problems, the performance of the UltraSPARC was disappointing. Two alternate schedulers are proposed to tackle this problem. It is shown that, given a good scheduler, the algorithm can massively exploit multi-threading architectures and so, substantially reduce the computational burden of Formal Concept Analysis.
Item Type:	Conference or Workshop Item
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/79113
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 252703