Americanae. Sistema de Difusión y Recolección de colecciones americanistas

Está en:  › Datos de registro

SWIMM 2.0: Enhanced Smith–Waterman on Intel’s Multicore and Manycore Architectures Based on AVX-512 Vector Extensions

Identificadores del recurso

http://sedici.unlp.edu.ar/handle/10915/82888

issn:1573-7640

Procedencia

(LA Referencia)

Ficha

Título:: SWIMM 2.0: Enhanced Smith–Waterman on Intel’s Multicore and Manycore Architectures Based on AVX-512 Vector Extensions
Tema:: Ciencias Informáticas; Bioinformatics; Smith-Waterman; Xeon-Phi; Intel-KNL; SIMD; Intel-AVX512
Descripción:: The well-known Smith–Waterman (SW) algorithm is the most commonly used method for local sequence alignments, but its acceptance is limited by the computational requirements for large protein databases. Although the acceleration of SW has already been studied on many parallel platforms, there are hardly any studies which take advantage of the latest Intel architectures based on AVX-512 vector extensions. This SIMD set is currently supported by Intel’s Knights Landing (KNL) accelerator and Intel’s Skylake (SKL) general purpose processors. In this paper, we present an SW version that is optimized for both architectures: the renowned SWIMM 2.0. The novelty of this vector instruction set requires the revision of previous programming and optimization techniques. SWIMM 2.0 is based on a massive multi-threading and SIMD exploitation. It is competitive in terms of performance compared with other state-of-the-art implementations, reaching 511 GCUPS on a single KNL node and 734 GCUPS on a server equipped with a dual SKL processor. Moreover, these successful performance rates make SWIMM 2.0 the most efficient energy footprint implementation in this study achieving 2.94 GCUPS/Watts on the SKL processor.; Facultad de Informática
Fuente:: reponame:SEDICI (UNLP); instname:Universidad Nacional de La Plata; instacron:UNLP
Idioma:: English
Relación:: info:eu-repo/semantics/altIdentifier/doi/10.1007/s10766-018-0585-7
Autor/Productor:: Rucci, Enzo; García Sánchez, Carlos; Botella, Guillermo; De Giusti, Armando Eduardo; Naiouf, Marcelo; Prieto-Matias, Manuel
Derechos:: info:eu-repo/semantics/openAccess; http://creativecommons.org/licenses/by-nc-nd/4.0/; Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)
Fecha:: 2018-07-10
Tipo de recurso:: info:eu-repo/semantics/article; info:eu-repo/semantics/publishedVersion; Articulo; http://purl.org/coar/resource_type/c_6501; info:ar-repo/semantics/articulo
Formato:: application/pdf; 296-316
About:: http://sedici.unlp.edu.ar/oai/snrdoai:sedici.unlp.edu.ar:10915/828882022-06-09T12:14:51Zhttp://www.openarchives.org/OAI/2.0/oai_dc/opendoar:1329SEDICI (UNLP) - Universidad Nacional de La Plata

oai_dc

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<oai_dc:dc schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
1. <dc:title>SWIMM 2.0: Enhanced Smith–Waterman on Intel’s Multicore and Manycore Architectures Based on AVX-512 Vector Extensions</dc:title>
2. <dc:creator>Rucci, Enzo</dc:creator>
3. <dc:creator>García Sánchez, Carlos</dc:creator>
4. <dc:creator>Botella, Guillermo</dc:creator>
5. <dc:creator>De Giusti, Armando Eduardo</dc:creator>
6. <dc:creator>Naiouf, Marcelo</dc:creator>
7. <dc:creator>Prieto-Matias, Manuel</dc:creator>
8. <dc:subject>Ciencias Informáticas</dc:subject>
9. <dc:subject>Bioinformatics</dc:subject>
10. <dc:subject>Smith-Waterman</dc:subject>
11. <dc:subject>Xeon-Phi</dc:subject>
12. <dc:subject>Intel-KNL</dc:subject>
13. <dc:subject>SIMD</dc:subject>
14. <dc:subject>Intel-AVX512</dc:subject>
15. <dc:description>The well-known Smith–Waterman (SW) algorithm is the most commonly used method for local sequence alignments, but its acceptance is limited by the computational requirements for large protein databases. Although the acceleration of SW has already been studied on many parallel platforms, there are hardly any studies which take advantage of the latest Intel architectures based on AVX-512 vector extensions. This SIMD set is currently supported by Intel’s Knights Landing (KNL) accelerator and Intel’s Skylake (SKL) general purpose processors. In this paper, we present an SW version that is optimized for both architectures: the renowned SWIMM 2.0. The novelty of this vector instruction set requires the revision of previous programming and optimization techniques. SWIMM 2.0 is based on a massive multi-threading and SIMD exploitation. It is competitive in terms of performance compared with other state-of-the-art implementations, reaching 511 GCUPS on a single KNL node and 734 GCUPS on a server equipped with a dual SKL processor. Moreover, these successful performance rates make SWIMM 2.0 the most efficient energy footprint implementation in this study achieving 2.94 GCUPS/Watts on the SKL processor.</dc:description>
16. <dc:description>Facultad de Informática</dc:description>
17. <dc:date>2018-07-10</dc:date>
18. <dc:type>info:eu-repo/semantics/article</dc:type>
19. <dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
20. <dc:type>Articulo</dc:type>
21. <dc:type>http://purl.org/coar/resource_type/c_6501</dc:type>
22. <dc:type>info:ar-repo/semantics/articulo</dc:type>
23. <dc:identifier>http://sedici.unlp.edu.ar/handle/10915/82888</dc:identifier>
24. <dc:identifier>issn:1573-7640</dc:identifier>
25. <dc:language>eng</dc:language>
26. <dc:relation>info:eu-repo/semantics/altIdentifier/doi/10.1007/s10766-018-0585-7</dc:relation>
27. <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
28. <dc:rights>http://creativecommons.org/licenses/by-nc-nd/4.0/</dc:rights>
29. <dc:rights>Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)</dc:rights>
30. <dc:format>application/pdf</dc:format>
31. <dc:format>296-316</dc:format>
32. <dc:source>reponame:SEDICI (UNLP)</dc:source>
33. <dc:source>instname:Universidad Nacional de La Plata</dc:source>
34. <dc:source>instacron:UNLP</dc:source>
35. <about>
  1. <provenance>
    1. <originDescription altered="false" harvestDate="2022-06-09 12:14:53.145">
      1. <baseURL>http://sedici.unlp.edu.ar/oai/snrd</baseURL>
      2. <identifier>oai:sedici.unlp.edu.ar:10915/82888</identifier>
      3. <datestamp>2022-06-09T12:14:51Z</datestamp>
      4. <metadataNamespace>http://www.openarchives.org/OAI/2.0/oai_dc/</metadataNamespace>
      5. <repositoryID>opendoar:1329</repositoryID>
      6. <repositoryName>SEDICI (UNLP) - Universidad Nacional de La Plata</repositoryName>
      </originDescription>
    </provenance>
  </about>
</oai_dc:dc>

xoai

Descargar XML

<?xml version="1.0" encoding="UTF-8" ?>

<metadata schemaLocation="http://www.lyncode.com/xoai http://www.lyncode.com/xsd/xoai.xsd">
1. <element name="dc">
  1. <element name="title">
    1. <element name="none">
      1. <field name="value">SWIMM 2.0: Enhanced Smith–Waterman on Intel’s Multicore and Manycore Architectures Based on AVX-512 Vector Extensions</field>
      </element>
    </element>
  2. <element name="creator">
    1. <element name="none">
      1. <field name="value">Rucci, Enzo</field>
      2. <field name="value">García Sánchez, Carlos</field>
      3. <field name="value">Botella, Guillermo</field>
      4. <field name="value">De Giusti, Armando Eduardo</field>
      5. <field name="value">Naiouf, Marcelo</field>
      6. <field name="value">Prieto-Matias, Manuel</field>
      </element>
    </element>
  3. <element name="subject">
    1. <element name="none">
      1. <field name="value">Ciencias Informáticas</field>
      2. <field name="value">Bioinformatics</field>
      3. <field name="value">Smith-Waterman</field>
      4. <field name="value">Xeon-Phi</field>
      5. <field name="value">Intel-KNL</field>
      6. <field name="value">SIMD</field>
      7. <field name="value">Intel-AVX512</field>
      </element>
    </element>
  4. <element name="description">
    1. <element name="none">
      1. <field name="value">The well-known Smith–Waterman (SW) algorithm is the most commonly used method for local sequence alignments, but its acceptance is limited by the computational requirements for large protein databases. Although the acceleration of SW has already been studied on many parallel platforms, there are hardly any studies which take advantage of the latest Intel architectures based on AVX-512 vector extensions. This SIMD set is currently supported by Intel’s Knights Landing (KNL) accelerator and Intel’s Skylake (SKL) general purpose processors. In this paper, we present an SW version that is optimized for both architectures: the renowned SWIMM 2.0. The novelty of this vector instruction set requires the revision of previous programming and optimization techniques. SWIMM 2.0 is based on a massive multi-threading and SIMD exploitation. It is competitive in terms of performance compared with other state-of-the-art implementations, reaching 511 GCUPS on a single KNL node and 734 GCUPS on a server equipped with a dual SKL processor. Moreover, these successful performance rates make SWIMM 2.0 the most efficient energy footprint implementation in this study achieving 2.94 GCUPS/Watts on the SKL processor.</field>
      2. <field name="value">Facultad de Informática</field>
      </element>
    </element>
  5. <element name="date">
    1. <element name="none">
      1. <field name="value">2018-07-10</field>
      </element>
    </element>
  6. <element name="type">
    1. <element name="none">
      1. <field name="value">info:eu-repo/semantics/article</field>
      2. <field name="value">info:eu-repo/semantics/publishedVersion</field>
      3. <field name="value">Articulo</field>
      4. <field name="value">http://purl.org/coar/resource_type/c_6501</field>
      5. <field name="value">info:ar-repo/semantics/articulo</field>
      </element>
    </element>
  7. <element name="format">
    1. <element name="none">
      1. <field name="value">application/pdf</field>
      2. <field name="value">296-316</field>
      </element>
    </element>
  8. <element name="identifier">
    1. <element name="none">
      1. <field name="value">http://sedici.unlp.edu.ar/handle/10915/82888</field>
      2. <field name="value">issn:1573-7640</field>
      </element>
    </element>
  9. <element name="language">
    1. <element name="none">
      1. <field name="value">eng</field>
      </element>
    </element>
  10. <element name="relation">
    1. <element name="none">
      1. <field name="value">info:eu-repo/semantics/altIdentifier/doi/10.1007/s10766-018-0585-7</field>
      </element>
    </element>
  11. <element name="rights">
    1. <element name="none">
      1. <field name="value">info:eu-repo/semantics/openAccess</field>
      2. <field name="value">http://creativecommons.org/licenses/by-nc-nd/4.0/</field>
      3. <field name="value">Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)</field>
      </element>
    </element>
  12. <element name="source">
    1. <element name="none">
      1. <field name="value">reponame:SEDICI (UNLP)</field>
      2. <field name="value">instname:Universidad Nacional de La Plata</field>
      3. <field name="value">instacron:UNLP</field>
      </element>
    </element>
  </element>
2. <element name="bundles" />
3. <element name="others">
  1. <field name="handle" />
  2. <field name="lastModifyDate">2022-06-09T12:14:51Z</field>
  3. <field name="identifier">oai:sedici.unlp.edu.ar:10915/82888</field>
  </element>
4. <element name="repository">
  1. <field name="repositoryType">Institucional</field>
  2. <field name="repositoryURL">http://sedici.unlp.edu.ar/</field>
  3. <field name="institutionType">Universidad pública</field>
  4. <field name="institutionURL">No corresponde</field>
  5. <field name="baseURL">http://sedici.unlp.edu.ar/oai/snrd</field>
  6. <field name="mail">alira@sedici.unlp.edu.ar</field>
  7. <field name="country">Argentina</field>
  8. <field name="DOI">No corresponde</field>
  9. <field name="ISSN">No corresponde</field>
  10. <field name="ISSN_L">No corresponde</field>
  11. <field name="repositoryID">opendoar:1329</field>
  12. <field name="harvestDate">2022-06-09 12:14:53.145</field>
  13. <field name="name">SEDICI (UNLP) - Universidad Nacional de La Plata</field>
  14. <field name="altered">false</field>
  </element>
</metadata>

Biblioteca AECID
Av. Reyes Católicos, nº 4. 28040 Madrid.
biblio.cooperacion@aecid.es
(+34) 91 583 81 75 - (+34) 91 583 81 64