An FPGA-based systolic array to accelerate the BWA-MEM genomic mapping algorithm

Ernst Houtgast, VM Sima, K Bertels, Z Al-Ars

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

29 Citations (Scopus)
88 Downloads (Pure)

Abstract

We present the first accelerated implementation of BWA-MEM, a popular genome sequence alignment algorithm widely used in next generation sequencing genomics pipelines. The Smith-Waterman-like sequence alignment kernel requires a significant portion of overall execution time. We propose and evaluate a number of FPGA-based systolic array architectures, presenting optimizations generally applicable to variable length Smith-Waterman execution. Our kernel implementation is up to 3x faster, compared to software-only execution. This translates into an overall application speedup of up to 45%, which is 96% of the theoretically maximum achievable speedup when accelerating only this kernel.
Original languageEnglish
Title of host publicationProceedings of the International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS XV
EditorsD Soudris, L Carro
Place of PublicationPiscataway, NJ, USA
PublisherIEEE Society
Pages221-227
Number of pages7
ISBN (Print)978-1-4673-7311-1
DOIs
Publication statusPublished - 28 Dec 2015
EventSAMOSXV, Samos, Greege - Piscataway
Duration: 19 Jul 201523 Jul 2015

Publication series

Name
PublisherIEEE

Conference

ConferenceSAMOSXV, Samos, Greege
Period19/07/1523/07/15

Keywords

  • Kernel
  • Arrays
  • Acceleration
  • Field programmable gate arrays
  • Bioinformatics
  • Genomics

Fingerprint Dive into the research topics of 'An FPGA-based systolic array to accelerate the BWA-MEM genomic mapping algorithm'. Together they form a unique fingerprint.

Cite this