{"id":"https://openalex.org/W4403670414","doi":"https://doi.org/10.1177/10943420241241491","title":"NUMA-aware parallel sparse LU factorization for SPICE-based circuit simulators on ARM multi-core processors","display_name":"NUMA-aware parallel sparse LU factorization for SPICE-based circuit simulators on ARM multi-core processors","publication_year":2024,"publication_date":"2024-10-23","ids":{"openalex":"https://openalex.org/W4403670414","doi":"https://doi.org/10.1177/10943420241241491"},"language":"en","primary_location":{"id":"doi:10.1177/10943420241241491","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420241241491","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","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/A5110837133","display_name":"Junsheng Zhou","orcid":"https://orcid.org/0000-0001-8346-1811"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsheng Zhou","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-8346-1811","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016247312","display_name":"Wangdong Yang","orcid":"https://orcid.org/0000-0003-2681-7898"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangdong Yang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101216578","display_name":"Fengkun Dong","orcid":"https://orcid.org/0000-0002-6508-3121"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengkun Dong","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085878424","display_name":"Shengle Lin","orcid":"https://orcid.org/0000-0003-3329-0924"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengle Lin","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102922586","display_name":"Qinyun Cai","orcid":"https://orcid.org/0000-0001-7642-457X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinyun Cai","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5016247312"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14930362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"3","first_page":"405","last_page":"423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9984999895095825,"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/spice","display_name":"Spice","score":0.8327244520187378},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7518042325973511},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7473680973052979},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5449806451797485},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5313466191291809},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.4784379303455353},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41590142250061035},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3867238759994507},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3393694758415222},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2129208743572235},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.1312248706817627},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07882478833198547},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06473171710968018}],"concepts":[{"id":"https://openalex.org/C2780077345","wikidata":"https://www.wikidata.org/wiki/Q16891888","display_name":"Spice","level":2,"score":0.8327244520187378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7518042325973511},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7473680973052979},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5449806451797485},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5313466191291809},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.4784379303455353},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41590142250061035},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3867238759994507},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3393694758415222},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2129208743572235},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.1312248706817627},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07882478833198547},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06473171710968018}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420241241491","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420241241491","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"0890-2720","issn":["0890-2720","1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1431077282","display_name":null,"funder_award_id":"2021JJ50158","funder_id":"https://openalex.org/F4320322866","funder_display_name":"Natural Science Foundation of Hainan Province"},{"id":"https://openalex.org/G4190216169","display_name":"\u9762\u5411\u9ad8\u7ef4\u6570\u636e\u7a7a\u95f4\u7684\u5f20\u91cf\u5f02\u6784\u5e76\u884c\u8ba1\u7b97\u65b9\u6cd5\u7814\u7a76\u4e0e\u63a2\u7d22","funder_award_id":"61872127","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6353171209","display_name":null,"funder_award_id":"2021YFB0300800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322866","display_name":"Natural Science Foundation of Hainan Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1963584319","https://openalex.org/W1970009422","https://openalex.org/W1988425770","https://openalex.org/W2020561008","https://openalex.org/W2041999884","https://openalex.org/W2045886945","https://openalex.org/W2051917325","https://openalex.org/W2053999255","https://openalex.org/W2055094346","https://openalex.org/W2118076222","https://openalex.org/W2132450860","https://openalex.org/W2355089277","https://openalex.org/W2397636522","https://openalex.org/W2586400059","https://openalex.org/W2887698420","https://openalex.org/W3007849603","https://openalex.org/W3009653888","https://openalex.org/W3117932782","https://openalex.org/W3209203812","https://openalex.org/W4240517907","https://openalex.org/W4280529869","https://openalex.org/W6607735624"],"related_works":["https://openalex.org/W4255057712","https://openalex.org/W3017642087","https://openalex.org/W4251458280","https://openalex.org/W2512412909","https://openalex.org/W1547865754","https://openalex.org/W2126398188","https://openalex.org/W2116570023","https://openalex.org/W4210605172","https://openalex.org/W4245707462","https://openalex.org/W4248999141"],"abstract_inverted_index":{"In":[0,96,227],"circuit":[1,66],"simulators":[2],"that":[3,239],"resemble":[4],"the":[5,15,20,57,81,110,113,117,125,138,173,216,223,233],"Simulation":[6],"Program":[7],"with":[8,88,229],"Integrated":[9],"Circuit":[10],"Emphasis":[11],"(SPICE),":[12],"one":[13],"of":[14,22,59,76,83,112,119,128,215,244],"most":[16],"crucial":[17],"steps":[18],"is":[19],"solution":[21],"numerous":[23],"sparse":[24,37,62,103,217],"linear":[25],"equations":[26],"generated":[27],"by":[28,222],"frequency":[29],"domain":[30,34],"analysis":[31,237],"or":[32],"time":[33],"analysis.":[35],"The":[36,211],"direct":[38,63,104],"solvers":[39,64],"based":[40,92,148,188],"on":[41,93,149,189,252],"lower-upper":[42],"(LU)":[43],"factorization":[44],"are":[45,220],"extremely":[46],"time-consuming,":[47],"so":[48],"their":[49],"performance":[50,77,111],"has":[51],"become":[52],"a":[53,101,144,242,253],"significant":[54],"bottleneck.":[55],"Despite":[56],"existence":[58],"some":[60],"parallel":[61,86,102,114],"for":[65,164],"simulation":[67],"problems,":[68],"they":[69],"remain":[70],"challenging":[71],"to":[72,161,193,202,246],"adapt":[73],"in":[74,80,121,153,172],"terms":[75],"and":[78,124,135,167,198,213,231,236,248],"scalability":[79],"face":[82],"rapidly":[84],"evolving":[85],"computers":[87],"multiple":[89],"NUMA":[90,181,190],"hardware":[91],"ARM":[94],"architecture.":[95],"this":[97],"paper,":[98],"we":[99],"introduce":[100],"solver":[105,218],"named":[106],"HLU,":[107],"which":[108,156],"re-examines":[109],"algorithm":[115],"from":[116],"viewpoint":[118],"parallelism":[120,134],"pipeline":[122,154],"mode":[123],"computing":[126],"efficiency":[127],"each":[129],"task.":[130],"To":[131],"maximize":[132],"task-level":[133],"further":[136],"minimize":[137],"thread":[139,185],"waiting":[140],"time,":[141],"HLU":[142,177,219,240],"devises":[143],"fine-grained":[145],"scheduling":[146],"method":[147],"an":[150],"elimination":[151],"tree":[152],"mode,":[155],"employs":[157],"depth-first":[158],"search":[159,163],"(DFS-like)":[160],"iteratively":[162],"parent":[165],"tasks":[166,171],"then":[168],"place":[169],"dependent":[170],"same":[174],"task":[175],"queue.":[176],"also":[178],"suggests":[179],"two":[180],"node":[182],"affinity":[183,186,200],"strategies:":[184],"optimization":[187,201],"nodes":[191],"topology":[192],"guarantee":[194],"computational":[195],"load":[196],"balancing":[197],"data":[199],"enable":[203],"effective":[204],"memory":[205],"placement":[206],"when":[207],"threads":[208],"access":[209],"data.":[210],"rationality":[212],"effectiveness":[214],"validated":[221],"SuiteSparse":[224],"Matrix":[225],"Collection.":[226],"comparison":[228],"KLU":[230],"NICSLU,":[232],"experimental":[234],"results":[235],"show":[238],"attains":[241],"speedup":[243],"up":[245],"9.14\u00d7":[247],"1.26x":[249],"(geometric":[250],"mean)":[251],"Huawei":[254],"Kunpeng":[255],"920":[256],"Server,":[257],"respectively.":[258]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
