A4 Refereed article in a conference publication
Heterogeneous Parallelization of Aho-Corasick Algorithm
Authors: Shima Soroushnia, Masoud Daneshtalab, Juha Plosila, Pasi Liljeberg
Editors: Julio Saez-Rodriguez, Miguel P. Rocha, Florentino Fdez-Riverola, Juan F. De Paz Santana
Conference name: International Conference on Practical Applications of Computational Biology
Publisher: SPRINGER-VERLAG NEW YORK, MS INGRID CUNNINGHAM, 175 FIFTH AVE, NEW YORK, NY 10010 USA
Publication year: 2014
Book title : 8th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2014)
Journal name in source: 8TH INTERNATIONAL CONFERENCE ON PRACTICAL APPLICATIONS OF COMPUTATIONAL BIOLOGY & BIOINFORMATICS (PACBB 2014)
Journal acronym: ADV INTELL SYST
Volume: 294
First page : 153
Last page: 160
Number of pages: 8
ISBN: 978-3-319-07580-8
ISSN: 2194-5357
DOI: https://doi.org/10.1007/978-3-319-07581-5_19
Pattern discovery is one of the fundamental tasks in bioinformatics and pattern recognition is a powerful technique for searching sequence patterns in the biological sequence databases. The significant increase in the number of DNA and protein sequences expands the need for raising the performance of pattern matching algorithms. For this purpose, heterogeneous architectures can be a good choice due to their potential for high performance and energy efficiency. In this paper we present an efficient implementation of Aho-Corasick (AC) and PFAC (Parallel Failureless Aho-Corasick) algorithm on a heterogeneous CPU/GPU architecture. We progressively redesigned the algorithms and data structures to fit on the GPU architecture. Our results on different protein sequence data sets show 15% speedup comparing to the original implementation of the PFAC algorithm.
