{"id":"https://openalex.org/W7167101474","doi":"https://doi.org/10.1145/3797905.3800554","title":"Non-Delayed Cholesky Factorization","display_name":"Non-Delayed Cholesky Factorization","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167101474","doi":"https://doi.org/10.1145/3797905.3800554"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3800554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800554","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3800554","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030675373","display_name":"Yuchen Luo","orcid":"https://orcid.org/0000-0003-0202-3727"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Luo","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-9990-230X","affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080562719","display_name":"H Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Chen","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7693-4558","affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091290657","display_name":"Shaoshuai Zhang","orcid":"https://orcid.org/0000-0002-9525-1659"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoshuai Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-9525-1659","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2150-5759","affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1272","last_page":"1283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6335999965667725,"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":0.6335999965667725,"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":0.07259999960660934,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.05609999969601631,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.8144000172615051},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6215000152587891},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.5674999952316284},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5559999942779541},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.478300005197525},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.39329999685287476}],"concepts":[{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.8144000172615051},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.5674999952316284},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5443000197410583},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4521999955177307},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.3898000121116638},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.31940001249313354},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3800554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800554","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3800554","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800554","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1558296484","https://openalex.org/W1983616264","https://openalex.org/W1986334759","https://openalex.org/W1997033059","https://openalex.org/W2002257715","https://openalex.org/W2057670757","https://openalex.org/W2099021415","https://openalex.org/W2104749334","https://openalex.org/W2124480634","https://openalex.org/W2124661136","https://openalex.org/W2134427337","https://openalex.org/W2277451201","https://openalex.org/W2410272182","https://openalex.org/W2469975815","https://openalex.org/W2493354458","https://openalex.org/W2509368344","https://openalex.org/W2528423095","https://openalex.org/W2563513434","https://openalex.org/W2588282852","https://openalex.org/W2614912021","https://openalex.org/W2731116490","https://openalex.org/W2741907101","https://openalex.org/W2775348209","https://openalex.org/W2903556862","https://openalex.org/W2983126917","https://openalex.org/W2994914294","https://openalex.org/W3048330007","https://openalex.org/W3129397352","https://openalex.org/W3137858876","https://openalex.org/W3193415234","https://openalex.org/W3212893044","https://openalex.org/W3216608520","https://openalex.org/W4230438631","https://openalex.org/W4285503969","https://openalex.org/W4294733340","https://openalex.org/W4380356442","https://openalex.org/W4386764095","https://openalex.org/W4388662066","https://openalex.org/W4405741266","https://openalex.org/W4413429202","https://openalex.org/W4416146776","https://openalex.org/W7125915276"],"related_works":[],"abstract_inverted_index":{"While":[0],"General":[1],"Matrix-Matrix":[2],"Multiplication":[3],"(GEMM)":[4],"often":[5],"nearly":[6],"approaches":[7],"the":[8,31,38],"peak":[9],"performance":[10,27],"of":[11,34],"modern":[12],"GPUs,":[13],"other":[14],"fundamental":[15],"dense":[16],"linear":[17],"algebra":[18],"algorithms,":[19],"such":[20],"as":[21,37],"Cholesky":[22],"factorization,":[23],"exhibit":[24],"a":[25,43],"significant":[26],"gap.":[28],"We":[29],"identify":[30],"root":[32],"cause":[33],"this":[35],"inefficiency":[36],"conventional":[39],"\u2018delayed":[40],"update\u2019":[41],"paradigm,":[42],"multi-kernel":[44],"approach":[45],"that":[46],"relies":[47],"on":[48],"coarse-grained":[49],"synchronization":[50],"and":[51],"incurs":[52],"substantial":[53],"data":[54],"movement":[55],"overhead,":[56],"particularly":[57],"for":[58],"small-to-medium":[59],"matrices.":[60]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-03T00:00:00"}
