I/O induced scalability limits of bioinformatics applications. Henschel, R. & Müller, M., S. In Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE, pages 609-613, 2007.
I/O induced scalability limits of bioinformatics applications [link]Website  doi  abstract   bibtex   
The growing size of sequence, protein and other biological databases results in an increased computational complexity of the analysis process. Often parallelization is the only solution to limit the turnaround time within reasonable limits. Most scalability studies focus on the parallel algorithm and the resulting communication and synchronization patterns of the implementations. In this paper we examine to what extend I/O bottlenecks limit the scalability on current and future architectures. We study the behavior of two different bioinformatics applications (THREADER, HMMER) and show that these applications are representatives of two different classes with distinct I/O profiles and demands. ©2007 IEEE.
@inproceedings{
 title = {I/O induced scalability limits of bioinformatics applications},
 type = {inproceedings},
 year = {2007},
 keywords = {Analysis processes; Bioinformatics applications;,Applications; Bioinformatics; Computational comple,Turnaround time},
 pages = {609-613},
 websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-47649107840&doi=10.1109%2FBIBE.2007.4375623&partnerID=40&md5=d1ed9dbcdb7f6edcd910df282bebb07e},
 city = {Boston, MA},
 id = {df0f757d-27e4-3001-bc85-2db140570197},
 created = {2018-02-27T18:07:31.531Z},
 file_attached = {false},
 profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
 group_id = {27e0553c-8ec0-31bd-b42c-825b8a5a9ae8},
 last_modified = {2018-02-27T18:07:31.531Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Henschel2007609},
 source_type = {conference},
 notes = {cited By 1; Conference of 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE ; Conference Date: 14 January 2007 Through 17 January 2007; Conference Code:72698},
 private_publication = {false},
 abstract = {The growing size of sequence, protein and other biological databases results in an increased computational complexity of the analysis process. Often parallelization is the only solution to limit the turnaround time within reasonable limits. Most scalability studies focus on the parallel algorithm and the resulting communication and synchronization patterns of the implementations. In this paper we examine to what extend I/O bottlenecks limit the scalability on current and future architectures. We study the behavior of two different bioinformatics applications (THREADER, HMMER) and show that these applications are representatives of two different classes with distinct I/O profiles and demands. ©2007 IEEE.},
 bibtype = {inproceedings},
 author = {Henschel, R and Müller, M S},
 doi = {10.1109/BIBE.2007.4375623},
 booktitle = {Proceedings of the 7th IEEE International Conference on Bioinformatics and Bioengineering, BIBE}
}

Downloads: 0