{"id":"https://openalex.org/W2887282140","doi":"https://doi.org/10.1145/3225058.3225071","title":"A Fast Sparse Triangular Solver for Structured-grid Problems on Sunway Many-core Processor SW26010","display_name":"A Fast Sparse Triangular Solver for Structured-grid Problems on Sunway Many-core Processor SW26010","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2887282140","doi":"https://doi.org/10.1145/3225058.3225071","mag":"2887282140"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-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/A5106943856","display_name":"Xinliang Wang","orcid":"https://orcid.org/0000-0003-0719-7187"},"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinliang Wang","raw_affiliation_strings":["Tsinghua University, National Supercomputing Center in Wuxi"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111514666","display_name":"Ping Xu","orcid":"https://orcid.org/0009-0000-3550-5955"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Ping Xu","raw_affiliation_strings":["Tsinghua University, National Supercomputing Center in Wuxi"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091437474","display_name":"Wei Xue","orcid":"https://orcid.org/0000-0001-9740-6581"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Wei Xue","raw_affiliation_strings":["Tsinghua University, National Supercomputing Center in Wuxi"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001005409","display_name":"Yulong Ao","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulong Ao","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031545295","display_name":"Haohuan Fu","orcid":"https://orcid.org/0000-0002-6982-2235"},"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohuan Fu","raw_affiliation_strings":["Tsinghua University, National Supercomputing Center in Wuxi"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038750675","display_name":"Lin Gan","orcid":"https://orcid.org/0000-0003-1297-4462"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Lin Gan","raw_affiliation_strings":["Tsinghua University, National Supercomputing Center in Wuxi"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"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":"Guangwen Yang","raw_affiliation_strings":["Tsinghua University, National Supercomputing Center in Wuxi"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, National Supercomputing Center in Wuxi","institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108050911","display_name":"Weimin Zheng","orcid":"https://orcid.org/0000-0002-4450-5428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weimin Zheng","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5106943856"],"corresponding_institution_ids":["https://openalex.org/I4210158984","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8077,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75182017,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9994000196456909,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/xeon","display_name":"Xeon","score":0.8884494304656982},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8501024842262268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8475172519683838},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7610414028167725},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6490029096603394},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.6133602857589722},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6099739074707031},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5876768827438354},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5873015522956848},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5675373077392578},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5569547414779663},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3819446563720703},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0835566520690918}],"concepts":[{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.8884494304656982},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8501024842262268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475172519683838},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7610414028167725},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6490029096603394},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6133602857589722},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6099739074707031},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5876768827438354},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5873015522956848},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5675373077392578},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5569547414779663},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3819446563720703},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0835566520690918},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W993511226","https://openalex.org/W1490374280","https://openalex.org/W1506342804","https://openalex.org/W1577852788","https://openalex.org/W1965034778","https://openalex.org/W1969849430","https://openalex.org/W1982358758","https://openalex.org/W1987145120","https://openalex.org/W1990577937","https://openalex.org/W2009654791","https://openalex.org/W2017239768","https://openalex.org/W2042879774","https://openalex.org/W2045618500","https://openalex.org/W2048955810","https://openalex.org/W2059825112","https://openalex.org/W2062424467","https://openalex.org/W2080090223","https://openalex.org/W2095258827","https://openalex.org/W2115052535","https://openalex.org/W2135181239","https://openalex.org/W2168931017","https://openalex.org/W2181846018","https://openalex.org/W2276719940","https://openalex.org/W2295944314","https://openalex.org/W2406344247","https://openalex.org/W2411480360","https://openalex.org/W2469975815","https://openalex.org/W2473076915","https://openalex.org/W2475126267","https://openalex.org/W2562913534","https://openalex.org/W2582745347","https://openalex.org/W2620106252","https://openalex.org/W2741907101","https://openalex.org/W2768065515","https://openalex.org/W2789228469","https://openalex.org/W2818841450","https://openalex.org/W3125710003","https://openalex.org/W4206109200"],"related_works":["https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2022666014","https://openalex.org/W2030340070","https://openalex.org/W4239672454","https://openalex.org/W4388580994","https://openalex.org/W2951241120","https://openalex.org/W2963673899","https://openalex.org/W1510302770","https://openalex.org/W3021853727"],"abstract_inverted_index":{"The":[0],"sparse":[1,66,206],"triangular":[2,69,165],"solver":[3],"(SpTRSV)":[4],"is":[5,26,44,119,145],"one":[6],"of":[7,33,42,116,124,129,154,158,182,194],"the":[8,20,50,58,125,135,155,186,220],"most":[9],"essential":[10],"kernels":[11],"in":[12,57],"many":[13],"scientific":[14],"and":[15,35,103,127,226],"engineering":[16],"applications.":[17],"Efficiently":[18],"parallelizing":[19],"SpTRSV":[21,43,106,118,144,174,213],"on":[22,87,99,110,161,199],"modern":[23],"many-core":[24,54,88,131],"architectures":[25],"considerably":[27],"difficult":[28],"due":[29],"to":[30,64,84,101,134,185,191],"inherent":[31],"dependency":[32],"computation":[34],"discontinuous":[36],"memory":[37],"accesses.":[38],"Achieving":[39],"high":[40],"performance":[41,218],"even":[45],"more":[46],"challenging":[47],"for":[48,107,121],"SW26010,":[49],"new-generation":[51],"customized":[52],"heterogeneous":[53],"processor":[55],"equipped":[56],"top-rank":[59],"Sunway":[60],"TaihuLight":[61],"supercomputer.":[62],"Owing":[63],"regular":[65],"pattern,":[67],"structured-grid":[68,108,143,164],"problems":[70,109,166,208],"show":[71,209],"much":[72],"different":[73,168],"computing":[74,156],"characteristics":[75],"with":[76,167,203],"general":[77],"ones":[78],"as":[79,81],"well":[80],"new":[82],"opportunities":[83],"algorithm":[85,114],"design":[86,102],"architectures,":[89],"which":[90,189],"ever":[91],"lacks":[92],"attention.":[93],"In":[94],"this":[95],"work,":[96],"we":[97],"focus":[98],"how":[100],"implement":[104],"fast":[105],"SW26010.":[111,159,200],"A":[112],"generalized":[113],"framework":[115],"parallel":[117,142],"proposed":[120,212],"best":[122],"utilization":[123,181],"features":[126],"flexibilities":[128],"SW26010":[130],"architecture":[132],"according":[133,184],"fine-grained":[136],"Producer-Consumer":[137],"model.":[138],"Moreover,":[139],"a":[140,192],"novel":[141],"presented":[146],"by":[147],"using":[148],"direct":[149],"data":[150],"transfers":[151],"across":[152],"registers":[153],"elements":[157],"Experiments":[160],"four":[162],"typical":[163],"problem":[169],"sizes":[170],"demonstrate":[171],"that":[172,210],"our":[173,211],"can":[175,214],"achieve":[176,215],"an":[177],"average":[178],"momory":[179],"bandwidth":[180],"79.7%":[183],"stream":[187],"benchmark,":[188],"leads":[190],"speedup":[193],"17.7":[195],"over":[196,219,232],"serial":[197],"version":[198],"Furthermore,":[201],"experiments":[202],"real":[204],"world":[205],"linear":[207],"superior":[216],"preconditioning":[217],"Intel":[221,227],"Xeon":[222,228],"E5-2670":[223],"v3":[224],"CPU":[225],"Phi":[229],"7210":[230],"KNL":[231],"DDR4":[233],"memory.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}