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

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

Houtgast, E.J. (TU Delft Computer Engineering)
Sima, V.M. (TU Delft Computer Engineering)
Bertels, K.L.M. (TU Delft Computer Engineering)
Al-Ars, Z. (TU Delft Computer Engineering)

Soudris, D (editor)
Carro, L (editor)

2015-12-28

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.

Kernel
Arrays
Acceleration
Field programmable gate arrays
Bioinformatics
Genomics

http://resolver.tudelft.nl/uuid:eab31b94-0c3d-4315-85a7-3f888f97d70e

https://doi.org/10.1109/SAMOS.2015.7363679

IEEE Society, Piscataway, NJ, USA

978-1-4673-7311-1

Proceedings of the International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, SAMOS XV

SAMOSXV, Samos, Greege, 2015-07-19 → 2015-07-23, Piscataway

Accepted Author Manuscript

Institutional Repository

conference paper

© 2015 E.J. Houtgast, V.M. Sima, K.L.M. Bertels, Z. Al-Ars