{"id":"https://openalex.org/W4298039161","doi":null,"title":"Task-based hybrid linear solver for distributed memory heterogeneous architectures","display_name":"Task-based hybrid linear solver for distributed memory heterogeneous architectures","publication_year":2016,"publication_date":"2016-05-17","ids":{"openalex":"https://openalex.org/W4298039161"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-01316783v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01316783","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-8913, Inria Bordeaux Sud-Ouest. 2016","raw_type":"info:eu-repo/semantics/report"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01316783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074132178","display_name":"Emmanuel Agullo","orcid":"https://orcid.org/0000-0003-0655-6934","observed_orcids":["https://orcid.org/0000-0003-0655-6934"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agullo, Emmanuel","raw_affiliation_strings":["High-End Parallel Algorithms for Challenging Numerical Simulations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High-End Parallel Algorithms for Challenging Numerical Simulations","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060047917","display_name":"Luc Giraud","orcid":"https://orcid.org/0000-0002-7062-7672","observed_orcids":["https://orcid.org/0000-0002-7062-7672"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giraud, Luc","raw_affiliation_strings":["High-End Parallel Algorithms for Challenging Numerical Simulations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High-End Parallel Algorithms for Challenging Numerical Simulations","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089256591","display_name":"Stojce Nakov","orcid":"https://orcid.org/0000-0002-8657-6750","observed_orcids":["https://orcid.org/0000-0002-8657-6750"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nakov, Stojce","raw_affiliation_strings":["High-End Parallel Algorithms for Challenging Numerical Simulations"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High-End Parallel Algorithms for Challenging Numerical Simulations","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7803000211715698,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7803000211715698,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.20739999413490295,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.003800000064074993,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task-parallelism","display_name":"task parallelism","score":0.7390000224113464},{"id":"https://openalex.org/keywords/sparse-direct-solvers","display_name":"sparse direct solvers","score":0.800000011920929},{"id":"https://openalex.org/keywords/domain-decomposition","display_name":"domain decomposition","score":0.8669999837875366},{"id":"https://openalex.org/keywords/multi-core-processors","display_name":"multi-core processors","score":0.8450000286102295},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.8899999856948853},{"id":"https://openalex.org/keywords/chameleons","display_name":"chameleons","score":0.7839999794960022},{"id":"https://openalex.org/keywords/runtime-systems","display_name":"runtime systems","score":0.5640000104904175},{"id":"https://openalex.org/keywords/numerical-stability","display_name":"numerical stability","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6882683038711548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6713582277297974},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6555134654045105},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6289917826652527},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42145347595214844},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3424416184425354},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1434684693813324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07962629199028015},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-01316783v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01316783","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-8913, Inria Bordeaux Sud-Ouest. 2016","raw_type":"info:eu-repo/semantics/report"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01316783v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01316783","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"[Research Report] RR-8913, Inria Bordeaux Sud-Ouest. 2016","raw_type":"info:eu-repo/semantics/report"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2602060087","https://openalex.org/W2604152328","https://openalex.org/W3199141021","https://openalex.org/W2282448441","https://openalex.org/W2170802276","https://openalex.org/W1502414128","https://openalex.org/W2280361371","https://openalex.org/W2144997873","https://openalex.org/W2089270187","https://openalex.org/W4297549403"],"abstract_inverted_index":{"Heterogeneity":[0],"is":[1,205],"emerging":[2],"as":[3,121],"one":[4,57,60],"of":[5,10,129,172,178,186,216],"the":[6,47,77,80,130,142,149,170,175,179,184,195],"most":[7],"challenging":[8],"characteristics":[9],"today\u2019s":[11],"parallel":[12],"environments.":[13],"However,":[14,63],"not":[15],"many":[16],"fully-featured":[17],"advanced":[18],"numerical,":[19],"scientific":[20],"libraries":[21],"have":[22],"been":[23,190],"ported":[24],"on":[25,85,116,148,214],"such":[26],"architectures.":[27,222],"In":[28],"this":[29,98,160,198],"paper,":[30],"we":[31,50],"propose":[32],"to":[33,91,209,219],"extend":[34],"a":[35,52,72,110,122,127],"sparse":[36,144,155],"hybrid":[37,145,181],"solver":[38,82,146],"for":[39,103,168],"handling":[40],"distributed":[41,105],"memory":[42,106],"heterogeneous":[43,107,187,221],"platforms.":[44],"As":[45],"in":[46,76],"original":[48,78],"solver,":[49,79],"perform":[51],"domain":[53],"decomposition":[54],"and":[55,151,154],"associate":[56],"subdomain":[58,66,111],"with":[59,135,141],"MPI":[61],"process.":[62],"while":[64],"each":[65],"was":[67],"processed":[68,115],"sequentially":[69],"(binded":[70],"onto":[71],"single":[73],"CPU":[74,118],"core)":[75],"new":[81],"instead":[83],"relies":[84],"task-based":[86],"local":[87],"solvers,":[88],"delegating":[89],"tasks":[90],"available":[92,131],"computing":[93,188],"units.":[94],"We":[95,137],"show":[96],"that":[97,203],"\u201cMPI+task\u201d":[99],"design":[100,163],"conveniently":[101],"allows":[102],"exploiting":[104],"machines.":[108],"Indeed,":[109],"can":[112],"now":[113,206],"be":[114],"multiple":[117],"cores":[119],"(such":[120],"whole":[123],"multicore":[124],"processor":[125],"or":[126],"subset":[128],"cores)":[132],"possibly":[133],"enhanced":[134],"GPUs.":[136],"illustrate":[138],"our":[139],"discussion":[140],"MaPHyS":[143],"relying":[147],"PaStiX":[150],"Chameleon":[152],"dense":[153],"direct":[156],"libraries,":[157],"respectively.":[158],"Interestingly,":[159],"two-level":[161],"MPI+task":[162],"furthermore":[164],"provides":[165],"extra":[166],"flexibility":[167],"controlling":[169],"number":[171],"subdomains,":[173],"enhancing":[174],"numerical":[176],"stability":[177],"considered":[180],"method.":[182],"While":[183],"rise":[185],"has":[189],"strongly":[191],"carried":[192],"out":[193],"by":[194],"theoretical":[196],"community,":[197],"study":[199],"aims":[200],"at":[201],"showing":[202],"it":[204],"also":[207],"possible":[208],"build":[210],"complex":[211],"software":[212],"layers":[213],"top":[215],"runtime":[217],"systems":[218],"exploit":[220]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2022-10-01T00:00:00"}