@inproceedings{30b474daf5e7402093293e7e6b20c2ee,
title = "DSA: Scalable distributed sequence alignment system using SIMD Instructions",
abstract = "Sequence alignment algorithms are a basic and critical component of many bioinformatics fields. With rapid development of sequencing technology, the fast growing reference database volumes and longer length of query sequence become new challenges for sequence alignment. However, the algorithms have prohibitively high time and space complexity. In this paper, we present DSA, a scalable distributed sequence alignment system that employs Apache Spark to process sequences data in a horizontally scalable distributed environment, and leverages data parallel strategy based on Single Instruction Multiple Data (SIMD) instruction to parallelize the algorithms in each core of worker node. The experimental results demonstrate that 1) DSA has outstanding performance and achieves up to 201x speedup over SparkSW. 2) DSA has excellent scalability and achieves near linear speedup when increasing the number of nodes in cluster.",
keywords = "Alluxio, Apache Spark, Distributed sequence alignment, SIMD instruction, Scalability",
author = "Bo Xu and Changlong Li and Hang Zhuang and Jiali Wang and Qingfeng Wang and Jinhong Zhou and Xuehai Zhou",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2017 ; Conference date: 14-05-2017 Through 17-05-2017",
year = "2017",
month = jul,
day = "10",
doi = "10.1109/CCGRID.2017.74",
language = "英语",
series = "Proceedings - 2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "758--761",
booktitle = "Proceedings - 2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, CCGRID 2017",
address = "美国",
}