Implementing parallel hmm-pfam on the EARTH multithreaded architecture

Author

Zhu, Weirong ; Niu, Yanwei ; Lu, Jizhu ; Gao, Guang R.

Author_Institution

Dept. of Electr. & Comput. Eng., Delaware Univ., Newark, DE, USA

fYear

2003

fDate

11-14 Aug. 2003

Firstpage

549

Lastpage

550

Abstract

Hmmpfam is a widely used computation-intensive bioinformatics software for sequence classification. This poster describes a new parallel implementation of hmmpfam on EARTH, which is an event-driven fine-grain multithreaded programming execution model. The comparison results of the original PVM implementation and our implementation shows notable improvements on absolute speedup and scalability. On a cluster of 128 dual-CPU nodes, the execution time of a representative testbench is reduced from 15.9 hours to 4.3 minutes.

Keywords

hidden Markov models; multi-threading; virtual machines; 15.9 hour; 4.3 min; PVM implementation; computation-intensive bioinformatics software; dual-CPU nodes; event-driven fine-grain multithreaded programming; execution model; execution time; hmmpfam; multithreaded architecture; scalability; sequence classification; speedup; testbench; Bioinformatics; Concurrent computing; Databases; Earth; Hidden Markov models; Load management; Master-slave; Programming profession; Scalability; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics Conference, 2003. CSB 2003. Proceedings of the 2003 IEEE

Print_ISBN

0-7695-2000-6

Type

conf

DOI

10.1109/CSB.2003.1227404

Filename

1227404