{"id":"https://openalex.org/W7125520671","doi":"https://doi.org/10.1007/s42514-025-00269-4","title":"Optimization of the ParILUT-GPU algorithm","display_name":"Optimization of the ParILUT-GPU algorithm","publication_year":2026,"publication_date":"2026-01-23","ids":{"openalex":"https://openalex.org/W7125520671","doi":"https://doi.org/10.1007/s42514-025-00269-4"},"language":"en","primary_location":{"id":"doi:10.1007/s42514-025-00269-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42514-025-00269-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42514-025-00269-4.pdf","source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s42514-025-00269-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101539233","display_name":"S. L. Yang","orcid":"https://orcid.org/0009-0002-1083-7894"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaofeng Yang","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1083-7894","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123640121","display_name":"Zhi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Li","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001140939","display_name":"Y. Wang","orcid":"https://orcid.org/0009-0004-9153-0732"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunting Wang","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123640169","display_name":"Xin He","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123656735","display_name":"Guangming Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","University of Chinese Academy of Sciences, Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101539233"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2790},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10241714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"2","first_page":"196","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6216999888420105,"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":0.6216999888420105,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.09719999879598618,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.05550000071525574,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speedup","display_name":"Speedup","score":0.896399974822998},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5963000059127808},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5188999772071838},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5182999968528748},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.383899986743927},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3610000014305115}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.896399974822998},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200000286102295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6592000126838684},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5963000059127808},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C207024777","wikidata":"https://www.wikidata.org/wiki/Q621673","display_name":"Search tree","level":3,"score":0.3499999940395355},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.26179999113082886},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2775973920","wikidata":"https://www.wikidata.org/wiki/Q3252726","display_name":"Selection algorithm","level":3,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s42514-025-00269-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42514-025-00269-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42514-025-00269-4.pdf","source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s42514-025-00269-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42514-025-00269-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42514-025-00269-4.pdf","source":{"id":"https://openalex.org/S4210190911","display_name":"CCF Transactions on High Performance Computing","issn_l":"2524-4922","issn":["2524-4922","2524-4930"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"CCF Transactions on High Performance Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G401163042","display_name":null,"funder_award_id":"62172389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125520671.pdf","grobid_xml":"https://content.openalex.org/works/W7125520671.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1974336758","https://openalex.org/W1974421439","https://openalex.org/W1998366068","https://openalex.org/W2015806545","https://openalex.org/W2060803192","https://openalex.org/W2087283353","https://openalex.org/W2095258827","https://openalex.org/W2098862161","https://openalex.org/W2099093654","https://openalex.org/W2106618443","https://openalex.org/W2164374667","https://openalex.org/W2252346314","https://openalex.org/W2883011321","https://openalex.org/W2908198074","https://openalex.org/W2972050710","https://openalex.org/W4248478717"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"We":[1],"have":[2],"optimized":[3,156,163],"the":[4,43,48,56,68,97,102,108,120,125,135,141,147,152,155,162,171,175,179],"parallel":[5],"threshold":[6,30,121],"ILU":[7,22,38],"algorithm":[8,45,51,65,71],"(ParILUT)":[9],"for":[10,15],"GPUs.":[11],"The":[12,158],"optimizations":[13],"are":[14],"three":[16],"building":[17],"blocks:":[18],"candidate":[19,35],"search":[20,36,64],"and":[21,26,29,37,46,88,90,146,174],"residual":[23,39],"computation,":[24],"adding":[25],"removing":[27],"elements,":[28],"selection.":[31],"Firstly,":[32],"we":[33,59,77,113],"fuse":[34],"computation":[40],"by":[41],"modifying":[42],"ParILUT":[44,164],"extending":[47],"register-aware":[49,69],"SpGEMM":[50,70],"to":[52,66,82,85,106,123],"calculate":[53],"it.":[54],"At":[55],"same":[57,136],"time,":[58],"developed":[60],"a":[61,79,115,129],"GPU":[62,104],"bin":[63],"make":[67],"perform":[72],"better":[73],"in":[74,119],"ParILUT.":[75,149,157],"Secondly,":[76],"adopt":[78],"warp-row-parallel":[80],"approach":[81],"add":[83],"elements":[84,92,133],"new":[86],"L":[87],"U":[89],"remove":[91],"from":[93],"candidates":[94],"instead":[95],"of":[96,110,132,143,154,181],"thread-row-parallel":[98],"approach.":[99],"And":[100,150],"used":[101],"efficient":[103],"instructions":[105],"locate":[107],"positions":[109],"elements.":[111],"Thirdly,":[112],"proposed":[114],"balanced":[116],"classification":[117],"tree":[118],"selection":[122],"balance":[124],"buckets\u2019":[126],"data,":[127],"when":[128],"large":[130],"number":[131],"with":[134,140,178],"value.":[137],"Finally,we":[138],"experimented":[139],"performance":[142],"each":[144],"optimization":[145],"whole":[148],"verified":[151],"correctness":[153],"result":[159],"indicates":[160],"that":[161],"average":[165],"speedup":[166,176],"is":[167],"4.03":[168],"times":[169],"over":[170],"original":[172],"version,":[173],"increases":[177],"amount":[180],"fill-in.":[182]},"counts_by_year":[],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2026-01-24T00:00:00"}