An efficient implementation of Smith Waterman algorithm on GPU using CUDA, for massively parallel scanning of sequence databases

Abstract

Abstract-The Smith Waterman algorithm for sequence alignment is one of the main tools of bioinformatics. It is used for sequence similarity searches and alignment of similar sequences. The high end Graphical Processing Unit (GPU), used for processing graphics on desktop computers, deliver computational capabilities exceeding those of CPUs by an order of magnitude. Recently these capabilities became accessible for general purpose computations thanks to CUDA programming environment on Nvidia GPUs and ATI Stream Computing environment on ATI GPUs. Here we present an efficient implementation of the Smith Waterman algorithm on the Nvidia GPU. The algorithm achieves more than 3.5 times higher per core performance than previously published implementation of the Smith Waterman algorithm on GPU, reaching more than 70% of theoretical hardware performance. The differences between current and earlier approaches are described showing the example for writing efficient code on GPU.

Accelerating Smith-Waterman Algorithm for Biological Database Search on CUDA-Compatible GPUs

“…For example, their implementation exploits on-chip shared memory to save the bandwidth between the GPU and off-chip video memory. Similar approaches are reported in [1], [13], [14].…”

“…Some recent methods [1], [13], [14], [19] exploit onchip shared memory to achieve higher performance than the SSE-optimized implementation. The performance of these methods roughly ranges from 5.6 GCUPS to 9.6 GCUPS, depending on the employed graphics card.…”

A Shared Memory Based Implementation of Needleman-Wunsch Algorithm Using Skewing Transformation

“…CS-BLAST [7] a protein sequence search tool is an extension of BLAST, which is based on context-specific mutation probabilities. Several researchers have developed parallel versions of the Smith-Waterman algorithm that are suitable for Graphics Processing Units (GPUs) [8], [9], [10], [11], [12]. Zheng et.…”

G-DNA – a highly efficient multi-GPU/MPI tool for aligning nucleotide reads

“…At the time SW-CUDA was able to achieve up to 3.5 GCUPS on two NVIDIA GeForce 8800GTX graphics cards. Another milestone was reached by Ligowski L. et al [6], who employed the shared memory to attain up to 14.5 GCUPS on two GPUs of the GeForce 9800 GX2. Liu Y. et al [20], in turn, developed the CUDASW++ algorithm achieving up to 16GCUPS on a dual-GPU GeForce GTX 295.…”

“…In contrast to the already available implementations, e.g. [6][7][8][9], our solution is highly optimized for reads from modern sequencers (Roche/454, Illumina/Solexa and AB/SOLiD) and, unlike cited works, directly targets the described problem. The software may prove to be useful especially in processing data from Roche/454, where the overlap-layout-consensus method is the most commonly employed.…”