Metadata only
Date
2022Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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 24x and the number of memory accesses by 12x. We efficiently parallelize the algorithm for GPUs, achieving a 4.1 x speedup over a CPU implementation of the same algorithm, a 62x speedup over minimap2's CPU-based KSW2 and a 7.2x speedup over the CPU-based Edlib for long reads. Show more
Publication status
publishedExternal links
Book title
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)Pages / Article No.
Publisher
IEEEEvent
Subject
read mapping; sequence alignment; GPU; memoryOrganisational unit
09483 - Mutlu, Onur / Mutlu, Onur
More
Show all metadata
ETH Bibliography
yes
Altmetrics