{"id":"https://openalex.org/W2790571449","doi":"https://doi.org/10.1145/3178442.3178450","title":"Extending ILUPACK with a Task-Parallel Version of BiCG for Dual-GPU Servers","display_name":"Extending ILUPACK with a Task-Parallel Version of BiCG for Dual-GPU Servers","publication_year":2018,"publication_date":"2018-02-16","ids":{"openalex":"https://openalex.org/W2790571449","doi":"https://doi.org/10.1145/3178442.3178450","mag":"2790571449"},"language":"en","primary_location":{"id":"doi:10.1145/3178442.3178450","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178442.3178450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080285682","display_name":"Jos\u00e9 I. Aliaga","orcid":"https://orcid.org/0000-0001-8469-764X"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 I. Aliaga","raw_affiliation_strings":["Dpto. de Ingenier\u00eda y Ciencia de Computadores, Universitat Jaume I, Castell\u00f3n, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpto. de Ingenier\u00eda y Ciencia de Computadores, Universitat Jaume I, Castell\u00f3n, Spain","institution_ids":["https://openalex.org/I10902133"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009824948","display_name":"Matthias Bollh\u00f6fer","orcid":"https://orcid.org/0000-0002-8093-5812"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Bollh\u00f6fer","raw_affiliation_strings":["Institute of Computational Mathematics, TU Braunschweig, Braunschweig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Mathematics, TU Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020768637","display_name":"Ernesto Dufrechou","orcid":"https://orcid.org/0000-0003-4971-340X"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Ernesto Dufrechou","raw_affiliation_strings":["Instituto de Computaci\u00f3n - Universidad de la Rep\u00fablica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Computaci\u00f3n - Universidad de la Rep\u00fablica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039665879","display_name":"Pablo Ezzatti","orcid":"https://orcid.org/0000-0002-2368-8907"},"institutions":[{"id":"https://openalex.org/I180910786","display_name":"Universidad de la Rep\u00fablica de Uruguay","ror":"https://ror.org/030bbe882","country_code":"UY","type":"education","lineage":["https://openalex.org/I180910786"]}],"countries":["UY"],"is_corresponding":false,"raw_author_name":"Pablo Ezzatti","raw_affiliation_strings":["Instituto de Computaci\u00f3n - Universidad de la Rep\u00fablica, Montevideo, Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Computaci\u00f3n - Universidad de la Rep\u00fablica, Montevideo, Uruguay","institution_ids":["https://openalex.org/I180910786"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012806004","display_name":"Enrique S. Quintana\u2013Ort\u0301\u0131","orcid":"https://orcid.org/0000-0002-5454-165X"},"institutions":[{"id":"https://openalex.org/I10902133","display_name":"Universitat Jaume I","ror":"https://ror.org/02ws1xc11","country_code":"ES","type":"education","lineage":["https://openalex.org/I10902133"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enrique S. Quintana-Ort\u00ed","raw_affiliation_strings":["Dpto. de Ingenier\u00eda y Ciencia de Computadores, Universitat Jaume I, Castell\u00f3n, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpto. de Ingenier\u00eda y Ciencia de Computadores, Universitat Jaume I, Castell\u00f3n, Spain","institution_ids":["https://openalex.org/I10902133"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2145,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52705035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7555607557296753},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6984487771987915},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.6972392201423645},{"id":"https://openalex.org/keywords/krylov-subspace","display_name":"Krylov subspace","score":0.6658488512039185},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6626940965652466},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6360701322555542},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6131811141967773},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5943043231964111},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5675766468048096},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5669237375259399},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5600141286849976},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4179179072380066},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.3379781246185303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24400007724761963},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.15698635578155518},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0959637463092804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09346863627433777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07794949412345886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7555607557296753},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6984487771987915},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.6972392201423645},{"id":"https://openalex.org/C147060835","wikidata":"https://www.wikidata.org/wiki/Q1757151","display_name":"Krylov subspace","level":3,"score":0.6658488512039185},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6626940965652466},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6360701322555542},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6131811141967773},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5943043231964111},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5675766468048096},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5669237375259399},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5600141286849976},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4179179072380066},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3379781246185303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24400007724761963},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.15698635578155518},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0959637463092804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09346863627433777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07794949412345886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178442.3178450","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178442.3178450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th International Workshop on Programming Models and Applications for Multicores and Manycores","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1252502350","https://openalex.org/W1506342804","https://openalex.org/W1523532434","https://openalex.org/W1552030768","https://openalex.org/W1575701986","https://openalex.org/W1579402588","https://openalex.org/W1965034778","https://openalex.org/W1968758409","https://openalex.org/W2011508376","https://openalex.org/W2025033760","https://openalex.org/W2035080386","https://openalex.org/W2073555064","https://openalex.org/W2124870011","https://openalex.org/W2128853364","https://openalex.org/W2130128444","https://openalex.org/W2140233454","https://openalex.org/W2154118576","https://openalex.org/W2170079961","https://openalex.org/W2181846018","https://openalex.org/W2199705654","https://openalex.org/W2271304962","https://openalex.org/W2619241543","https://openalex.org/W2738880986","https://openalex.org/W2763753778","https://openalex.org/W2997945685","https://openalex.org/W4230252700","https://openalex.org/W6629619268"],"related_works":["https://openalex.org/W3046775784","https://openalex.org/W2382988560","https://openalex.org/W2024149451","https://openalex.org/W2977980606","https://openalex.org/W3031624508","https://openalex.org/W2033698563","https://openalex.org/W2265737839","https://openalex.org/W94752050","https://openalex.org/W4322732133","https://openalex.org/W2106635645"],"abstract_inverted_index":{"We":[0,42],"target":[1],"the":[2,15,34,44,47,51,55,65,71],"solution":[3],"of":[4,33,38,46,54,64],"sparse":[5],"linear":[6],"systems":[7],"via":[8],"iterative":[9],"Krylov":[10],"subspace-based":[11],"methods":[12],"enhanced":[13],"with":[14,30,81,90],"ILUPACK":[16,29],"preconditioner":[17],"on":[18,78],"graphics":[19],"processing":[20],"units":[21],"(GPUs).":[22],"Concretely,":[23],"in":[24,57],"this":[25],"work":[26],"we":[27],"extend":[28],"an":[31],"implementation":[32],"BiCG":[35,48],"solver":[36,56],"capable":[37],"exploiting":[39],"dual-GPU":[40],"systems.":[41],"leverage":[43],"structure":[45],"to":[49,69,92],"execute":[50],"main":[52],"stages":[53],"a":[58,79,93],"concurrent":[59],"manner,":[60],"and":[61],"take":[62],"advantage":[63],"extended":[66],"memory":[67],"space":[68],"improve":[70],"data":[72],"access":[73],"patterns.":[74],"The":[75],"experimental":[76],"results":[77],"server":[80],"two":[82],"NVIDIA":[83],"K40":[84],"GPUs":[85],"show":[86],"important":[87],"acceleration":[88],"factors":[89],"respect":[91],"previous":[94],"single":[95],"GPU":[96],"variant.":[97]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}