Work

Algorithmic Improvement and GPU Acceleration of the GenASM Algorithm

Year: 2022

Type: conference-paper

Abstract: We improve on GenASM, a recent algorithm for genomic sequence alignment, by significantly reducing its memory footprint and bandwidth requirement. Our algorithmic improvements reduce the memory footprint by 24 × and the number of memory accesses by 12 ×. We efficiently parallelize the algorithm for GPUs, achieving a 4.1 × speedup over a CPU implementation of the same algorithm, a 62× speedup over minimap2's CPU-based KSW2 and a 7.2 × speedup over the CPU-based Edlib for long reads.

Source: IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum

DOI: 10.1109/ipdpsw55747.2022.00038

Authors: Joel Lindegger, Damla Senol Cali, Mohammed Alser, Juan Gomez-Luna, Onur Mutlu

Institutions: ETH Zurich, BioNano Genomics (United States)

Language: English

Topic: Genomics and Phylogenetic Studies

Subfield: Molecular Biology

Field: Biochemistry, Genetics and Molecular Biology

Domain: Life Sciences

Open Access status: green

Funder: Nvidia

Award: G6496325548