{"id":"https://openalex.org/W4409917327","doi":"https://doi.org/10.1109/pdp66500.2025.00037","title":"A synchronization-free incomplete LU factorization for GPUs with level-set analysis","display_name":"A synchronization-free incomplete LU factorization for GPUs with level-set analysis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4409917327","doi":"https://doi.org/10.1109/pdp66500.2025.00037"},"language":"en","primary_location":{"id":"doi:10.1109/pdp66500.2025.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdp66500.2025.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102888118","display_name":"Manuel Freire","orcid":"https://orcid.org/0000-0002-4887-8918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manuel Freire","raw_affiliation_strings":["Instituto de Computaci&#x00F3;n Facultad de Ingenier&#x00ED;a - UDELAR,Montevideo,Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Computaci&#x00F3;n Facultad de Ingenier&#x00ED;a - UDELAR,Montevideo,Uruguay","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020768637","display_name":"Ernesto Dufrechou","orcid":"https://orcid.org/0000-0003-4971-340X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ernesto Dufrechou","raw_affiliation_strings":["Instituto de Computaci&#x00F3;n Facultad de Ingenier&#x00ED;a - UDELAR,Montevideo,Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Computaci&#x00F3;n Facultad de Ingenier&#x00ED;a - UDELAR,Montevideo,Uruguay","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039665879","display_name":"Pablo Ezzatti","orcid":"https://orcid.org/0000-0002-2368-8907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Ezzatti","raw_affiliation_strings":["Instituto de Computaci&#x00F3;n Facultad de Ingenier&#x00ED;a - UDELAR,Montevideo,Uruguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto de Computaci&#x00F3;n Facultad de Ingenier&#x00ED;a - UDELAR,Montevideo,Uruguay","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":"217","last_page":"225"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9783999919891357,"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":0.9783999919891357,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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":0.9717000126838684,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6823298335075378},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.6618699431419373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6540769338607788},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6298101544380188},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5904136896133423},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3470602035522461},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3052580952644348},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07442739605903625}],"concepts":[{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6823298335075378},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.6618699431419373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6540769338607788},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6298101544380188},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5904136896133423},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3470602035522461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3052580952644348},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07442739605903625},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pdp66500.2025.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pdp66500.2025.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 33rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1506342804","https://openalex.org/W2035080386","https://openalex.org/W2088501249","https://openalex.org/W2095258827","https://openalex.org/W2099093654","https://openalex.org/W2106618443","https://openalex.org/W2252346314","https://openalex.org/W2469975815","https://openalex.org/W2741907101","https://openalex.org/W2805150752","https://openalex.org/W2886168566","https://openalex.org/W2971260052","https://openalex.org/W3137858876","https://openalex.org/W3212893044","https://openalex.org/W4365455597","https://openalex.org/W6685981158","https://openalex.org/W6686029512","https://openalex.org/W6687335039","https://openalex.org/W6712590890"],"related_works":["https://openalex.org/W2794559785","https://openalex.org/W1754499339","https://openalex.org/W2013873776","https://openalex.org/W2950281908","https://openalex.org/W2963117165","https://openalex.org/W2084977674","https://openalex.org/W2583828359","https://openalex.org/W3102011585","https://openalex.org/W2037667647","https://openalex.org/W2954309532"],"abstract_inverted_index":{"Incomplete":[0],"factorization":[1,56,67],"methods":[2,20,38],"are":[3,29,57,107],"powerful":[4],"algebraic":[5],"preconditioners":[6],"widely":[7],"used":[8],"to":[9,65,75,125],"accelerate":[10],"the":[11,41,50,60,73,76,80,91,127],"convergence":[12],"of":[13,18,62,90],"linear":[14,48],"solvers.":[15],"The":[16],"parallelization":[17],"ILU":[19,55,66],"has":[21,68],"been":[22,70],"extensively":[23],"studied,":[24],"particularly":[25],"for":[26,44],"GPUs,":[27],"which":[28],"ubiquitous":[30],"parallel":[31],"computing":[32],"devices.":[33],"In":[34,83],"recent":[35],"years,":[36],"synchronization-free":[37,63,88],"have":[39],"become":[40],"mainstream":[42],"approach":[43,118],"solving":[45],"sparse":[46,51],"triangular":[47,52,81],"systems.Although":[49],"solver":[53],"and":[54],"closely":[58],"related,":[59],"application":[61],"strategies":[64],"not":[69],"explored":[71],"in":[72,103],"literature":[74],"same":[77],"extent":[78],"as":[79,113,115],"solver.":[82],"this":[84],"work,":[85],"we":[86,97],"present":[87],"implementations":[89,100],"ILU-0":[92],"preconditioner":[93],"on":[94],"GPUs.":[95],"Specifically,":[96],"propose":[98],"three":[99],"that":[101,119],"vary":[102],"how":[104],"row":[105],"updates":[106],"handled":[108],"after":[109],"each":[110],"coefficient":[111],"elimination,":[112],"well":[114],"an":[116],"additional":[117],"leverages":[120],"a":[121],"prior":[122],"level-set":[123],"analysis":[124],"optimize":[126],"execution":[128],"schedule.":[129]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
