Bioinformatics Advance Access originally published online on November 16, 2006
Bioinformatics 2007 23(2):156-161; doi:10.1093/bioinformatics/btl582
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Striped SmithWaterman speeds database searches six times over other SIMD implementations
| Abstract |
|---|
Motivation: The only algorithm guaranteed to find the optimal local alignment is the SmithWaterman. It is also one of the slowest due to the number of computations required for the search. To speed up the algorithm, Single-Instruction Multiple-Data (SIMD) instructions have been used to parallelize the algorithm at the instruction level.
Results: A faster implementation of the SmithWaterman algorithm is presented. This algorithm achieved 28 times performance improvement over other SIMD based SmithWaterman implementations. On a 2.0 GHz Xeon Core 2 Duo processor, speeds of >3.0 billion cell updates/s were achieved.
Availability: http://farrar.michael.googlepages.com/Smith-waterman
Contact: farrar.michael{at}gmail.com
Associate Editor: Nikolaus Rajewsky
Received on June 22, 2006; revised on November 13, 2006; accepted on November 14, 2006