{"id":"https://openalex.org/W3175080065","doi":"https://doi.org/10.1145/3431379.3460642","title":"Cache-aware Sparse Patterns for the Factorized Sparse Approximate Inverse Preconditioner","display_name":"Cache-aware Sparse Patterns for the Factorized Sparse Approximate Inverse Preconditioner","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W3175080065","doi":"https://doi.org/10.1145/3431379.3460642","mag":"3175080065"},"language":"en","primary_location":{"id":"doi:10.1145/3431379.3460642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431379.3460642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/382085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071405524","display_name":"Sergi Laut","orcid":"https://orcid.org/0000-0002-8727-0518"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sergi Laut","raw_affiliation_strings":["Barcelona Supercomputing Center &amp; Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center &amp; Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008546385","display_name":"R. Borrell","orcid":"https://orcid.org/0000-0003-3747-7104"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ricard Borrell","raw_affiliation_strings":["Barcelona Supercomputing Center, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044183257","display_name":"Marc Casas","orcid":"https://orcid.org/0000-0003-4564-2093"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marc Casas","raw_affiliation_strings":["Barcelona Supercomputing Center &amp; Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center &amp; Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"93"},"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":0.996399998664856,"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":0.9955999851226807,"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/preconditioner","display_name":"Preconditioner","score":0.9579286575317383},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.7587723731994629},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6512838006019592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6135626435279846},{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.5911300778388977},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5544720888137817},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49571382999420166},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.47192978858947754},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4608333706855774},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.40374889969825745},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.39881473779678345},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.35571545362472534},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33776795864105225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33068037033081055},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.12242019176483154}],"concepts":[{"id":"https://openalex.org/C167431342","wikidata":"https://www.wikidata.org/wiki/Q1754327","display_name":"Preconditioner","level":3,"score":0.9579286575317383},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.7587723731994629},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6512838006019592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135626435279846},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.5911300778388977},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5544720888137817},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49571382999420166},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.47192978858947754},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4608333706855774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40374889969825745},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.39881473779678345},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.35571545362472534},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33776795864105225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33068037033081055},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.12242019176483154},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3431379.3460642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3431379.3460642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/382085","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/382085","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/382085","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/382085","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference report"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W174510205","https://openalex.org/W1506342804","https://openalex.org/W1926678177","https://openalex.org/W1966756606","https://openalex.org/W1969138095","https://openalex.org/W1971079846","https://openalex.org/W1985006751","https://openalex.org/W1988420772","https://openalex.org/W1994805693","https://openalex.org/W2003505798","https://openalex.org/W2026502086","https://openalex.org/W2026977080","https://openalex.org/W2035080386","https://openalex.org/W2038516134","https://openalex.org/W2040639345","https://openalex.org/W2057980100","https://openalex.org/W2058273413","https://openalex.org/W2062233541","https://openalex.org/W2078311192","https://openalex.org/W2085789510","https://openalex.org/W2088200553","https://openalex.org/W2089099677","https://openalex.org/W2182233292","https://openalex.org/W2271597431","https://openalex.org/W2280292853","https://openalex.org/W2290916141","https://openalex.org/W2566696892","https://openalex.org/W2887161653","https://openalex.org/W2944108582","https://openalex.org/W2962947578","https://openalex.org/W2993109347","https://openalex.org/W3005380678","https://openalex.org/W4230055019","https://openalex.org/W4252552527","https://openalex.org/W6959456255"],"related_works":["https://openalex.org/W1513364355","https://openalex.org/W2159515580","https://openalex.org/W2081820376","https://openalex.org/W2318469121","https://openalex.org/W2091325992","https://openalex.org/W2059625160","https://openalex.org/W2006453807","https://openalex.org/W2600459900","https://openalex.org/W2740546554","https://openalex.org/W1964759953"],"abstract_inverted_index":{"Conjugate":[0],"Gradient":[1],"is":[2,55,72],"a":[3,28,42,52,126,156],"widely":[4],"used":[5],"iterative":[6],"method":[7],"to":[8,86],"solve":[9],"linear":[10],"systems":[11],"Ax=b":[12],"with":[13],"matrix":[14],"A":[15],"being":[16],"symmetric":[17],"and":[18,44,142,152],"positive":[19],"definite.":[20],"Part":[21],"of":[22,51,58,66,91,135,158],"its":[23,33,59],"effectiveness":[24,90],"relies":[25],"on":[26,75,144],"finding":[27],"suitable":[29],"preconditioner":[30,54,93],"that":[31,107],"accelerates":[32],"convergence.":[34],"Factorized":[35],"Sparse":[36,121],"Approximate":[37],"Inverse":[38],"(FSAI)":[39],"preconditioners":[40],"are":[41],"prominent":[43],"easily":[45],"parallelizable":[46],"option.":[47],"An":[48],"essential":[49],"element":[50],"FSAI":[53],"the":[56,64,67,88,92,119],"definition":[57,71],"sparse":[60],"pattern,":[61],"which":[62],"constraints":[63],"approximation":[65],"inverse":[68],"A-1.":[69],"This":[70],"generally":[73],"based":[74],"numerical":[76,89],"criteria.":[77],"In":[78,100],"this":[79],"paper":[80],"we":[81,102,128],"introduce":[82],"complementary":[83],"architecture-aware":[84],"criteria":[85],"increase":[87],"without":[94],"incurring":[95],"in":[96,118,133],"significant":[97,131],"performance":[98],"costs.":[99],"particular,":[101],"define":[103],"cache-aware":[104],"pattern":[105],"extensions":[106],"do":[108],"not":[109],"trigger":[110],"additional":[111],"cache":[112],"misses":[113],"when":[114],"accessing":[115],"vector":[116],"x":[117],"y=Ax":[120],"Matrix-Vector":[122],"(SpMV)":[123],"kernel.":[124],"As":[125],"result,":[127],"obtain":[129],"very":[130],"reductions":[132],"terms":[134],"average":[136],"solution":[137],"time":[138],"ranging":[139],"between":[140],"12.94%":[141],"22.85%":[143],"three":[145],"different":[146],"architectures":[147],"-":[148,154],"Intel":[149],"Skylake,":[150],"POWER9":[151],"A64FX":[153],"over":[155],"set":[157],"72":[159],"test":[160],"matrices.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-07-05T00:00:00"}
