Title :

Perfect Hashing Structures for Parallel Similarity Searches

Author(s) :

Tran, Tuan Tu [Auteur]
Giraud, Mathieu [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Bioinformatics and Sequence Analysis [BONSAI]
Varré, Jean-Stéphane [Auteur]
Bioinformatics and Sequence Analysis [BONSAI]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Conference title :

International Workshop on High Performance Computational Biology (HiCOMB 2015) / International Parallel and Distributed Processing Symposium (IPDPS 2015)

City :

Hyderabad

Country :

Inde

Start date of the conference :

2015

Publication date :

2015

English keyword(s) :

OpenCL
GPU
parallelism
perfect hash function
read mapper
seed-based heuristics

HAL domain(s) :

Informatique [cs]/Bio-informatique [q-bio.QM]
Informatique [cs]/Calcul parallèle, distribué et partagé [cs.DC]

English abstract : [en]

Seed-based heuristics have proved to be efficient for studying similarity between genetic databases with billions of base pairs. This paper focuses on algorithms and data structures for the filtering phase in seed-based ...
Show more >Seed-based heuristics have proved to be efficient for studying similarity between genetic databases with billions of base pairs. This paper focuses on algorithms and data structures for the filtering phase in seed-based heuristics, with an emphasis on efficient parallel GPU/manycores implementa- tion. We propose a 2-stage index structure which is based on neighborhood indexing and perfect hashing techniques. This structure performs a filtering phase over the neighborhood regions around the seeds in constant time and avoid as much as possible random memory accesses and branch divergences. Moreover, it fits particularly well on parallel SIMD processors, because it requires intensive but homogeneous computational operations. Using this data structure, we developed a fast and sensitive OpenCL prototype read mapper.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Nouvelles approches algorithmiques et bioinformatiques pour l'analyse des grandes masses de données issues des séquenceurs de nouvelle génération.

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL