Data reordering for minimizing threads divergence in GPU-based evaluating association rules
Loading...
Date
2015-03-26
Journal Title
Journal ISSN
Volume Title
Publisher
CERIST
Abstract
This last decade, the success of Graphics Processor Units (GPUs) has led
researchers to launch a lot of works on solving large complex problems by using these
cheap and powerful architecture. Association Rules Mining (ARM) is one of these hard
problems requiring a lot of computational resources. Due to the exponential increase of data
bases size, existing algorithms for ARM problem become more and more inefficient. Thus,
research has been focusing on parallelizing these algorithms. Recently, GPUs are starting to
be used to this task. However, their major drawback is the threads divergence problem. To
deal with this issue, we propose in this paper an intelligent strategy called Transactions-
based Reordering "TR" allowing an efficient evaluation of association rules on GPU by
minimizing threads divergence. This strategy is based on data base re-organization. To
validate our proposition, theoretical and experimental studies have been carried out using
well-known synthetic data sets. The results are very promising in terms of minimizing the
number of threads divergence.
Description
Keywords
Association Rules Mining, GPU Computing, Threads Divergence