A GPU-CPU heterogeneous algorithm for NGS read alignment Academic Article uri icon

abstract

  • Copyright © 2018 Inderscience Enterprises Ltd. In the next generation sequencing (NGS) read alignment problem, millions of deoxyribonucleic acid (DNA) fragments, called reads, are mapped to a reference genome. Read alignment is typically carried out using traditional computing platforms, which have become a limiting factor in the speed of the process. The massive scale of the problem makes it an attractive target for acceleration. In this paper, we design a read alignment algorithm designed to run on a heterogeneous system composed of a graphics processing unity (GPU) and a multicore central processing unit (CPU). We introduce novel techniques for the alignment process and construct a computational pipeline of overlapped CPU and GPU stages. We compare our tool with the BWA-mem alignment tool, and the results show substantial speedups.

author list (cited authors)

  • Kawam, A. A., Khatri, S., & Datta, A.

citation count

  • 0

publication date

  • January 2018