{"id":"https://openalex.org/W7116516765","doi":"https://doi.org/10.1145/3754598.3754624","title":"Optimizing Incomplete Cholesky Factorization on MIMD Many-core Architecture","display_name":"Optimizing Incomplete Cholesky Factorization on MIMD Many-core Architecture","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116516765","doi":"https://doi.org/10.1145/3754598.3754624"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754624","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 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754624","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yongzhen Shi","orcid":"https://orcid.org/0009-0008-0256-325X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongzhen Shi","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0008-0256-325X","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120929812","display_name":"Qinglin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglin Wang","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-8286-6566","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Liu","orcid":"https://orcid.org/0000-0003-3745-7541"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":["Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-3745-7541","affiliations":[{"raw_affiliation_string":"Laboratory of Digitizing Software for Frontier Equipment, National University of Defense Technology, Changsha, China; National Key Laboratory of Parallel and Distributed Computing, National University of Defense Technology, Changsha, China and College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lian Wang","orcid":"https://orcid.org/0009-0005-4548-6600"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lian Wang","raw_affiliation_strings":["Shanxi Supercomputing Center, Lvliang, China"],"raw_orcid":"https://orcid.org/0009-0005-4548-6600","affiliations":[{"raw_affiliation_string":"Shanxi Supercomputing Center, Lvliang, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120935881","display_name":"Zhiyan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyan Liu","raw_affiliation_strings":["Shanxi Supercomputing Center, Lvliang, China"],"raw_orcid":"https://orcid.org/0009-0008-5870-0145","affiliations":[{"raw_affiliation_string":"Shanxi Supercomputing Center, Lvliang, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048298058","display_name":"Bingwei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingwei Wang","raw_affiliation_strings":["Shanxi Supercomputing Center, Lvliang, China"],"raw_orcid":"https://orcid.org/0009-0004-6434-6235","affiliations":[{"raw_affiliation_string":"Shanxi Supercomputing Center, Lvliang, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Feiming Liu","orcid":"https://orcid.org/0009-0009-8775-4836"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiming Liu","raw_affiliation_strings":["Shanxi Supercomputing Center, Lvliang, China"],"raw_orcid":"https://orcid.org/0009-0009-8775-4836","affiliations":[{"raw_affiliation_string":"Shanxi Supercomputing Center, Lvliang, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057280984","display_name":"Xiangdong Pei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Pei","raw_affiliation_strings":["Shanxi Supercomputing Center, Lvliang, China"],"raw_orcid":"https://orcid.org/0009-0005-5454-9482","affiliations":[{"raw_affiliation_string":"Shanxi Supercomputing Center, Lvliang, China","institution_ids":["https://openalex.org/I4210158984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64791774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4447000026702881,"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":0.4447000026702881,"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":0.3237999975681305,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.054099999368190765,"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/mimd","display_name":"MIMD","score":0.8091999888420105},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.7856000065803528},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.6209999918937683},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.49889999628067017},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.491100013256073},{"id":"https://openalex.org/keywords/minimum-degree-algorithm","display_name":"Minimum degree algorithm","score":0.4772000014781952},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4383000135421753},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.41280001401901245},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.41280001401901245},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4075999855995178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112999796867371},{"id":"https://openalex.org/C21032095","wikidata":"https://www.wikidata.org/wiki/Q1149237","display_name":"MIMD","level":2,"score":0.8091999888420105},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7864999771118164},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.7856000065803528},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.6209999918937683},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.49889999628067017},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C46085209","wikidata":"https://www.wikidata.org/wiki/Q17098969","display_name":"Minimum degree algorithm","level":5,"score":0.4772000014781952},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.41280001401901245},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C192465680","wikidata":"https://www.wikidata.org/wiki/Q1413450","display_name":"Precondition","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.3190999925136566},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C93693863","wikidata":"https://www.wikidata.org/wiki/Q897659","display_name":"Branch and bound","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754624","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 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754624","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 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.7721689343452454}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W376280045","https://openalex.org/W1506342804","https://openalex.org/W1965034778","https://openalex.org/W1974421439","https://openalex.org/W1986822694","https://openalex.org/W1994182141","https://openalex.org/W2002988981","https://openalex.org/W2019527453","https://openalex.org/W2035080386","https://openalex.org/W2067802451","https://openalex.org/W2073555064","https://openalex.org/W2075618555","https://openalex.org/W2095258827","https://openalex.org/W2124200646","https://openalex.org/W2155568054","https://openalex.org/W2182968645","https://openalex.org/W2434281400","https://openalex.org/W2535466884","https://openalex.org/W2584547575","https://openalex.org/W2958885886","https://openalex.org/W3038558128","https://openalex.org/W3135187275","https://openalex.org/W4283157740","https://openalex.org/W4312258136","https://openalex.org/W4367322593","https://openalex.org/W4372359475","https://openalex.org/W4385062345","https://openalex.org/W4392449925"],"related_works":[],"abstract_inverted_index":{"Incomplete":[0],"Cholesky":[1],"(IC)":[2],"factorization":[3,51,69,128],"is":[4,76],"widely":[5],"used":[6],"to":[7,31],"precondition":[8],"large":[9],"sparse":[10],"positive":[11],"definite":[12],"symmetric":[13],"linear":[14],"equations,":[15],"since":[16],"it":[17],"can":[18],"effectively":[19],"reduce":[20],"the":[21,27,32,49,56,71,79,137,167],"number":[22],"of":[23,132],"iterations":[24],"and":[25,81,101,113,134,146,148,153],"enhance":[26],"solution":[28],"efficiency":[29],"compared":[30],"unconditioned":[33],"Conjugate":[34],"Gradient":[35],"(CG)":[36],"iterative":[37],"algorithm.":[38,85],"In":[39],"this":[40],"paper,":[41],"we":[42],"have":[43],"carried":[44],"out":[45],"optimization":[46,96,107,116],"research":[47],"on":[48,55,78,98,109,118,141,156],"IC":[50,68,126],"parallel":[52,65,127],"algorithms":[53],"based":[54,77,97,108,117],"MIMD":[57,72],"many-core":[58],"architecture":[59,169],"PEZY-SC3s":[60],"processor.":[61],"We":[62,86],"propose":[63],"a":[64,157],"algorithm":[66,75,88],"for":[67],"under":[70],"architecture.":[73],"This":[74],"level-scheduling":[80],"graph":[82,119],"coloring":[83],"reordering":[84],"optimize":[87],"performance":[89,177],"using":[90],"various":[91],"measures,":[92],"including":[93],"memory":[94],"access":[95],"vector":[99],"units":[100],"on-chip":[102],"local":[103],"memory,":[104],"load":[105],"balancing":[106],"dynamic":[110],"thread":[111],"scheduling,":[112],"task":[114],"allocation":[115],"partitioning.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"that":[124,166],"our":[125],"achieves":[129,175],"average":[130],"speedups":[131],"17.5x":[133],"8.4x":[135],"over":[136,150],"two":[138],"cuSPARSE":[139],"implementations":[140,155],"an":[142],"NVIDIA":[143],"A30":[144],"GPU,":[145],"230.6x":[147],"83.0x":[149],"Ginkgo\u2019s":[151],"serial":[152],"OpenMP":[154],"dual-socket":[158],"Intel":[159],"Xeon":[160],"4314":[161],"platform.":[162],"Our":[163],"study":[164],"demonstrates":[165],"PEZY":[168],"with":[170],"effective":[171],"algorithmic":[172],"design":[173],"still":[174],"good":[176],"gains":[178],"while":[179],"maintaining":[180],"low":[181],"power":[182],"consumption.":[183]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-21T00:00:00"}