Abstract: Multiple Pairwise Sequence Alignments with the Needleman-Wunsch Algorithm on GPU

Pairwise sequence alignment is a method used in bioinformatics to determine the similarity between DNA, RNA and protein sequences. The Needleman-Wunsch algorithm is typically used to perform global alignment, and has been accelerated on Graphics Processing Units (GPUs) on single pairs of sequences. Many applications require multiple pairwise comparisons over sets of sequences. The large sizes of modern bioinformatics datasets leads to a need for efficient tools that allow a large number of pairwise comparisons. Because of their massive parallelism, GPUs are an appealing choice for accelerating these computations. In this paper, we propose an efficient GPU implementation of multiple pairwise sequence alignments based on the Needleman-Wunsch algorithm. Compared to a well-known existing solution, our implementation improves the memory transfer time by a factor 2X, and achieves a ~3X speedup in kernel execution time.