Efficient parallelization of Bowtie 2 with OpenCL on GPU

OpenCL;Bowtie 2;Sequence Aligner;Smith-Waterman

Yan, Yan ; Chen ; Deming

关键词: OpenCL;    Bowtie 2;    Sequence Aligner;    Smith-Waterman;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/92977/YAN-THESIS-2016.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

As a crucial and computation-intensive aspect in bioinformatics, sequence alignment has gained considerable attention from researchers and developers. Among all the sequence aligners, Bowtie 2 is one of the most commonly used, due to its high speed and accuracy. This thesis presents a parallel implementation of Bowtie 2 with OpenCL, which is a parallel programming model that is becoming widely known and receiving great interest from researchers in recent years. This OpenCL implementation has high portability on various devices, such as multi-core CPU, GPU, and FPGA. This thesis focuses on an efficient and accurate parallelization on GPU. Optimizations that can be accommodated to any devices have been applied, as well as GPU-related optimizations.