{"id":"https://openalex.org/W4381198747","doi":"https://doi.org/10.1109/tpds.2023.3287238","title":"A Multi-GPU Aggregation-Based AMG Preconditioner for Iterative Linear Solvers","display_name":"A Multi-GPU Aggregation-Based AMG Preconditioner for Iterative Linear Solvers","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4381198747","doi":"https://doi.org/10.1109/tpds.2023.3287238"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2023.3287238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3287238","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ieeexplore.ieee.org/abstract/document/10155151","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006496977","display_name":"Massimo Bernaschi","orcid":"https://orcid.org/0000-0003-3661-9836"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Massimo Bernaschi","raw_affiliation_strings":["Institute for Applied Computing (IAC) - CNR, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3661-9836","affiliations":[{"raw_affiliation_string":"Institute for Applied Computing (IAC) - CNR, Rome, Italy","institution_ids":["https://openalex.org/I3005160176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005168115","display_name":"Alessandro Celestini","orcid":"https://orcid.org/0000-0002-8493-4550"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Celestini","raw_affiliation_strings":["Institute for Applied Computing (IAC) - CNR, Rome, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8493-4550","affiliations":[{"raw_affiliation_string":"Institute for Applied Computing (IAC) - CNR, Rome, Italy","institution_ids":["https://openalex.org/I3005160176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011440366","display_name":"Flavio Vella","orcid":"https://orcid.org/0000-0002-5676-9228"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Flavio Vella","raw_affiliation_strings":["University of Trento, Trento, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5676-9228","affiliations":[{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077824645","display_name":"Pasqua D\u2019Ambra","orcid":"https://orcid.org/0000-0003-2047-4986"},"institutions":[{"id":"https://openalex.org/I3005160176","display_name":"Institute for High Performance Computing and Networking","ror":"https://ror.org/04r5fge26","country_code":"IT","type":"facility","lineage":["https://openalex.org/I3005160176","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pasqua D'Ambra","raw_affiliation_strings":["Institute for Applied Computing (IAC) - CNR, Naples, Italy"],"raw_orcid":"https://orcid.org/0000-0003-2047-4986","affiliations":[{"raw_affiliation_string":"Institute for Applied Computing (IAC) - CNR, Naples, Italy","institution_ids":["https://openalex.org/I3005160176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1407,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8011583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"34","issue":"8","first_page":"2365","last_page":"2376"},"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":0.9994000196456909,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8755868673324585},{"id":"https://openalex.org/keywords/preconditioner","display_name":"Preconditioner","score":0.8152303099632263},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7794466018676758},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7457361221313477},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.6888366937637329},{"id":"https://openalex.org/keywords/multigrid-method","display_name":"Multigrid method","score":0.6019987463951111},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6004011631011963},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5940320491790771},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.5492057204246521},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5346965193748474},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5217660069465637},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5119841694831848},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4681532680988312},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3952985405921936},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.28794318437576294},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1816810965538025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8755868673324585},{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.8152303099632263},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7794466018676758},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7457361221313477},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6888366937637329},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.6019987463951111},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6004011631011963},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5940320491790771},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.5492057204246521},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5346965193748474},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5217660069465637},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5119841694831848},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4681532680988312},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3952985405921936},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.28794318437576294},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1816810965538025},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"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/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpds.2023.3287238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2023.3287238","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:iris.unitn.it:11572/401010","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/abstract/document/10155151","pdf_url":null,"source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:it.cnr:prodotti:483479","is_oa":false,"landing_page_url":"http://www.cnr.it/prodotto/i/483479","pdf_url":null,"source":{"id":"https://openalex.org/S7407055101","display_name":"CNR ExploRA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"info:cnr-pdr/source/autori:M. Bernaschi, A. Celestini, F. Vella, P. D'Ambra/titolo:A multi-GPU aggregation-based AMG preconditioner for iterative linear solvers/doi:10.1109%2FTPDS.2023.3287238/rivista:IEEE transactions on parallel and distributed systems (Online)/anno:2023/pagina_da:2365/pagina_a:2376/intervallo_pagine:2365\u20132376/volume:34","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:iris.unitn.it:11572/401010","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/abstract/document/10155151","pdf_url":null,"source":{"id":"https://openalex.org/S4377196320","display_name":"Iris (University of Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"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":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1252105715","https://openalex.org/W1506342804","https://openalex.org/W1569680480","https://openalex.org/W1790422192","https://openalex.org/W1845641575","https://openalex.org/W2022916138","https://openalex.org/W2025501795","https://openalex.org/W2065973083","https://openalex.org/W2114138609","https://openalex.org/W2123458460","https://openalex.org/W2127610428","https://openalex.org/W2148802605","https://openalex.org/W2164904521","https://openalex.org/W2273593125","https://openalex.org/W2570841452","https://openalex.org/W2751658790","https://openalex.org/W2808718522","https://openalex.org/W2922443778","https://openalex.org/W2950905676","https://openalex.org/W2963889991","https://openalex.org/W2981048485","https://openalex.org/W2995489632","https://openalex.org/W2999537838","https://openalex.org/W3000323728","https://openalex.org/W3047681903","https://openalex.org/W3091170309","https://openalex.org/W3107374472","https://openalex.org/W3134229947","https://openalex.org/W3199141021","https://openalex.org/W3203922106","https://openalex.org/W4247826031","https://openalex.org/W4249613779"],"related_works":["https://openalex.org/W4389317411","https://openalex.org/W1492522302","https://openalex.org/W2120298265","https://openalex.org/W2096454229","https://openalex.org/W2042199958","https://openalex.org/W2103149966","https://openalex.org/W2177482563","https://openalex.org/W2016008514","https://openalex.org/W2464766188","https://openalex.org/W1963859303"],"abstract_inverted_index":{"We":[0],"present":[1],"and":[2,32,69,129],"release":[3],"in":[4,61,95,156],"open":[5],"source":[6],"format":[7],"a":[8,65,81,154],"sparse":[9,33],"linear":[10,34,83],"solver":[11,19,84],"which":[12],"efficiently":[13],"exploits":[14],"heterogeneous":[15],"parallel":[16,38],"computers.":[17],"The":[18,51],"can":[20],"be":[21],"easily":[22],"integrated":[23],"into":[24],"scientific":[25],"applications":[26],"that":[27],"need":[28],"to":[29,161],"solve":[30,158],"large":[31],"systems":[35],"on":[36,74,86,140],"modern":[37],"computers":[39],"made":[40],"of":[41,56,58,64,80,124,133,137],"hybrid":[42,76,101],"nodes":[43],"hosting":[44],"Nvidia":[45,150],"Graphics":[46],"Processing":[47],"Unit":[48],"(GPU)":[49],"accelerators.":[50],"work":[52],"extends":[53],"previous":[54],"efforts":[55],"some":[57],"the":[59,62,75,100,107,122,125,134,138,149,157],"authors":[60],"exploitation":[63],"single":[66],"GPU":[67,126],"accelerator":[68],"proposes":[70],"an":[71,87],"implementation,":[72],"based":[73],"MPI-CUDA":[77],"software":[78],"environment,":[79],"Krylov-type":[82],"relying":[85],"efficient":[88],"Algebraic":[89],"MultiGrid":[90],"(AMG)":[91],"preconditioner":[92],"already":[93],"available":[94],"theBootCMatchGlibrary.":[96],"Our":[97],"design":[98],"for":[99,110],"implementation":[102],"has":[103],"been":[104],"driven":[105],"by":[106],"best":[108],"practices":[109],"minimizing":[111],"data":[112],"communication":[113],"overhead":[114],"when":[115],"multiple":[116],"GPUs":[117],"are":[118,145],"employed,":[119],"yet":[120],"preserving":[121],"efficiency":[123],"kernels.":[127],"Strong":[128],"weak":[130],"scalability":[131],"results":[132],"new":[135],"version":[136],"library":[139],"well-known":[141],"benchmark":[142],"test":[143],"cases":[144],"discussed.":[146],"Comparisons":[147],"with":[148],"AmgX":[151],"solution":[152],"show":[153],"speedup,":[155],"phase,":[159],"up":[160],"2.0x.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}