{"id":"https://openalex.org/W3137858876","doi":"https://doi.org/10.1109/tpds.2021.3066635","title":"YuenyeungSpTRSV: A Thread-Level and Warp-Level Fusion Synchronization-Free Sparse Triangular Solve","display_name":"YuenyeungSpTRSV: A Thread-Level and Warp-Level Fusion Synchronization-Free Sparse Triangular Solve","publication_year":2021,"publication_date":"2021-03-17","ids":{"openalex":"https://openalex.org/W3137858876","doi":"https://doi.org/10.1109/tpds.2021.3066635","mag":"3137858876"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3066635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3066635","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5091139467","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0003-1983-7321"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1983-7321","affiliations":[{"raw_affiliation_string":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025797638","display_name":"Jiya Su","orcid":"https://orcid.org/0000-0002-4952-1486"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiya Su","raw_affiliation_strings":["Computer Science Department, Illinois Institute of Technology, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","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":["Department of Computer Science and Technology, China University of Petroleum, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, China University of Petroleum, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039946576","display_name":"Bingsheng He","orcid":"https://orcid.org/0000-0001-8618-4581"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bingsheng He","raw_affiliation_strings":["School of Computing, National University of Singapore, SingaporeSingapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, SingaporeSingapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076272801","display_name":"Ruofan Wu","orcid":"https://orcid.org/0000-0001-6826-8108"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruofan Wu","raw_affiliation_strings":["Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008721449","display_name":"Xiaoyong Du","orcid":"https://orcid.org/0000-0002-5757-9135"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyong Du","raw_affiliation_strings":["Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073855975","display_name":"Rujia Wang","orcid":"https://orcid.org/0000-0003-4019-5327"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rujia Wang","raw_affiliation_strings":["Computer Science Department, Illinois Institute of Technology, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0003-4019-5327","affiliations":[{"raw_affiliation_string":"Computer Science Department, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0692,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.86288416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"9","first_page":"2321","last_page":"2337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.7701866626739502},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6881850361824036},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6515118479728699},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.6369712352752686},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6359833478927612},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5511415600776672},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.519753634929657},{"id":"https://openalex.org/keywords/row-and-column-spaces","display_name":"Row and column spaces","score":0.43793830275535583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43246781826019287},{"id":"https://openalex.org/keywords/sparse-array","display_name":"Sparse array","score":0.43019527196884155},{"id":"https://openalex.org/keywords/triangular-matrix","display_name":"Triangular matrix","score":0.4205382466316223},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3213919997215271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11929646134376526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1132093071937561}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701866626739502},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6881850361824036},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6515118479728699},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.6369712352752686},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6359833478927612},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5511415600776672},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.519753634929657},{"id":"https://openalex.org/C104140500","wikidata":"https://www.wikidata.org/wiki/Q2088159","display_name":"Row and column spaces","level":3,"score":0.43793830275535583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43246781826019287},{"id":"https://openalex.org/C145177509","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse array","level":2,"score":0.43019527196884155},{"id":"https://openalex.org/C104528550","wikidata":"https://www.wikidata.org/wiki/Q506265","display_name":"Triangular matrix","level":3,"score":0.4205382466316223},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3213919997215271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11929646134376526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1132093071937561},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2021.3066635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3066635","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G992000842","display_name":null,"funder_award_id":"61802412","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W993511226","https://openalex.org/W1506342804","https://openalex.org/W1557692423","https://openalex.org/W1965034778","https://openalex.org/W1982358758","https://openalex.org/W2003840611","https://openalex.org/W2009654791","https://openalex.org/W2035080386","https://openalex.org/W2042879774","https://openalex.org/W2052602889","https://openalex.org/W2072680607","https://openalex.org/W2080090223","https://openalex.org/W2088866486","https://openalex.org/W2091883426","https://openalex.org/W2095249664","https://openalex.org/W2097717378","https://openalex.org/W2098903349","https://openalex.org/W2115052535","https://openalex.org/W2122817518","https://openalex.org/W2128329055","https://openalex.org/W2162283062","https://openalex.org/W2168931017","https://openalex.org/W2181846018","https://openalex.org/W2263374743","https://openalex.org/W2276719940","https://openalex.org/W2406344247","https://openalex.org/W2411480360","https://openalex.org/W2469975815","https://openalex.org/W2524532592","https://openalex.org/W2581090187","https://openalex.org/W2741907101","https://openalex.org/W2789228469","https://openalex.org/W2790789009","https://openalex.org/W2805150752","https://openalex.org/W2984946966","https://openalex.org/W3048232878","https://openalex.org/W3048330007","https://openalex.org/W3125710003","https://openalex.org/W4232836277","https://openalex.org/W4252721932","https://openalex.org/W4302564868","https://openalex.org/W6685981158","https://openalex.org/W6695046875"],"related_works":["https://openalex.org/W2313440505","https://openalex.org/W3123744736","https://openalex.org/W1505848319","https://openalex.org/W2137691148","https://openalex.org/W4281399881","https://openalex.org/W2905020035","https://openalex.org/W3166006430","https://openalex.org/W4281971614","https://openalex.org/W2049180840","https://openalex.org/W2052885993"],"abstract_inverted_index":{"Sparse":[0,241],"triangular":[1],"solves":[2],"(SpTRSVs)":[3],"are":[4,30],"widely":[5],"used":[6],"in":[7,103,273],"linear":[8],"algebra":[9],"domains,":[10],"and":[11,27,71,106,125,222,248,267],"several":[12],"GPU-based":[13],"SpTRSV":[14,35,45,129,265,272],"algorithms":[15,46],"have":[16,110],"been":[17],"developed.":[18],"Synchronization-free":[19],"SpTRSVs,":[20],"due":[21],"to":[22,99,174,228],"their":[23],"short":[24],"preprocessing":[25,172],"time":[26,173],"high":[28,70,180],"performance,":[29],"currently":[31],"the":[32,41,62,72,97,114,133,145,164,197,211,239,262,271],"most":[33,212],"popular":[34,213],"algorithms.":[36],"However,":[37],"we":[38,120],"observe":[39],"that":[40,60,184,251],"performance":[42,181,209],"of":[43,65,75,113,139,151],"those":[44,82],"on":[47,96,182,196,210,244],"different":[48],"matrices":[49,183,237],"can":[50,205],"vary":[51],"greatly":[52],"by":[53],"845":[54],"times.":[55],"Our":[56],"further":[57],"studies":[58],"show":[59,250],"when":[61],"average":[63,73],"number":[64,74,138,150],"components":[66],"per":[67,78],"level":[68],"is":[69,80,90,258],"nonzero":[76,140,152],"elements":[77,141,153],"row":[79,102,219],"low,":[81],"SpTRSVs":[83,186],"exhibit":[84],"extremely":[85],"low":[86,149],"performance.":[87],"The":[88],"reason":[89],"that,":[91],"they":[92],"use":[93],"a":[94,101,123,136,148],"warp":[95],"GPU":[98,246],"process":[100],"sparse":[104,199,214,218],"matrices,":[105],"such":[107],"warp-level":[108,143],"designs":[109],"severe":[111],"underutilization":[112],"GPU.":[115],"To":[116],"solve":[117],"this":[118],"problem,":[119],"propose":[121],"YuenyeungSpTRSV,":[122],"thread-level":[124],"wrap-level":[126],"fusion":[127],"synchronization-free":[128,264],"algorithm,":[130,266],"which":[131,257],"handles":[132],"rows":[134,146],"with":[135,147,235],"large":[137],"at":[142,154],"while":[144],"thread-level.":[155],"Particularly,":[156],"YuenyeungSpTRSV":[157,167,178,234,253],"has":[158],"three":[159],"novel":[160],"features.":[161],"First,":[162],"unlike":[163],"previous":[165,185],"studies,":[166],"does":[168,193],"not":[169,194,226],"need":[170,227],"long":[171],"calculate":[175],"levels.":[176],"Second,":[177],"exhibits":[179,254],"cannot":[187],"handle":[188],"efficiently.":[189],"Third,":[190],"YuenyeungSpTRSV's":[191],"optimization":[192],"rely":[195],"specific":[198],"matrix":[200,215],"storage":[201],"format.":[202],"Instead,":[203],"it":[204],"achieve":[206],"very":[207],"good":[208],"storage,":[216],"compressed":[217],"(CSR)":[220],"format,":[221],"thus":[223],"users":[224],"do":[225],"conduct":[229],"format":[230],"conversion.":[231],"We":[232],"evaluate":[233],"245":[236],"from":[238],"Florida":[240],"Matrix":[242],"Collection":[243],"four":[245],"platforms,":[247],"experiments":[249],"our":[252],"7.14":[255],"GFLOPS/s,":[256],"5.98x":[259],"speedup":[260,269],"over":[261,270],"state-of-the-art":[263],"4.83x":[268],"cuSPARSE.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}