{"id":"https://openalex.org/W2910114332","doi":"https://doi.org/10.1145/3229631.3229649","title":"Massively parallel computation of linear recurrence equations with graphics processing units","display_name":"Massively parallel computation of linear recurrence equations with graphics processing units","publication_year":2018,"publication_date":"2018-07-15","ids":{"openalex":"https://openalex.org/W2910114332","doi":"https://doi.org/10.1145/3229631.3229649","mag":"2910114332"},"language":"en","primary_location":{"id":"doi:10.1145/3229631.3229649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229631.3229649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation","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/A5113491293","display_name":"Wonyong Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100654316","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-3878-6876"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong-hwan Lee","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057914051","display_name":"Kyuyeon Hwang","orcid":"https://orcid.org/0000-0001-6700-1583"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuyeon Hwang","raw_affiliation_strings":["Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113491293"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18565143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9922999739646912,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9883999824523926,"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/parallel-computing","display_name":"Parallel computing","score":0.8378435373306274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8299872875213623},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7619138956069946},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7274127006530762},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5871358513832092},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5036410689353943},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5023398399353027},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.4940360188484192},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4905206561088562},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4713556170463562},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4594830274581909},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.431417852640152},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.42761683464050293},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4128713309764862},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2760588526725769},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.14132338762283325}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8378435373306274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8299872875213623},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7619138956069946},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7274127006530762},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5871358513832092},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5036410689353943},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5023398399353027},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.4940360188484192},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4905206561088562},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4713556170463562},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4594830274581909},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.431417852640152},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42761683464050293},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4128713309764862},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2760588526725769},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.14132338762283325},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3229631.3229649","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3229631.3229649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation","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":22,"referenced_works":["https://openalex.org/W63016970","https://openalex.org/W1963965124","https://openalex.org/W2015055672","https://openalex.org/W2017086619","https://openalex.org/W2019708326","https://openalex.org/W2049794528","https://openalex.org/W2061681593","https://openalex.org/W2066653153","https://openalex.org/W2087977509","https://openalex.org/W2089366856","https://openalex.org/W2114279700","https://openalex.org/W2119212493","https://openalex.org/W2120373864","https://openalex.org/W2122978030","https://openalex.org/W2138509139","https://openalex.org/W2164552691","https://openalex.org/W2167334577","https://openalex.org/W2952436057","https://openalex.org/W2997701623","https://openalex.org/W3145668479","https://openalex.org/W4243513274","https://openalex.org/W4250981202"],"related_works":["https://openalex.org/W2255048617","https://openalex.org/W2092102951","https://openalex.org/W1512604874","https://openalex.org/W2140636994","https://openalex.org/W2142204081","https://openalex.org/W1968724572","https://openalex.org/W2158982898","https://openalex.org/W1784407820","https://openalex.org/W2883786246","https://openalex.org/W2191246539"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"show":[4,45],"very":[5],"high":[6,46],"performance":[7],"when":[8],"executing":[9],"many":[10],"parallel":[11,34,75,83],"programs;":[12],"however":[13],"their":[14],"use":[15],"in":[16,48],"solving":[17],"linear":[18],"recurrence":[19,119],"equations":[20,120],"is":[21],"considered":[22],"difficult":[23],"because":[24,50],"of":[25,29,51,57,79,92],"the":[26,30,55,93,101,133,138],"sequential":[27],"nature":[28],"problem.":[31],"Previously":[32],"developed":[33,64],"algorithms,":[35],"such":[36],"as":[37,95,97],"recursive":[38],"doubling":[39],"and":[40,104,127,132,142],"multi-block":[41],"processing,":[42],"do":[43],"not":[44],"efficiency":[47,103],"GPUs":[49],"poor":[52],"scalability":[53],"with":[54,137],"number":[56],"threads.":[58],"In":[59],"this":[60],"work,":[61],"we":[62],"have":[63],"a":[65,73,106],"highly":[66],"efficient":[67],"GPU-based":[68],"algorithm":[69],"for":[70,109],"recurrences":[71],"using":[72],"thread-level":[74],"(TLP)":[76],"approach,":[77],"instead":[78],"conventional":[80],"thread-block":[81],"level":[82],"(TBLP)":[84],"methods.":[85],"The":[86],"proposed":[87],"TLP":[88],"method":[89],"executes":[90],"all":[91],"threads":[94],"independently":[96],"possible":[98],"to":[99],"improve":[100],"computational":[102],"employs":[105],"hierarchical":[107],"structure":[108],"inter-thread":[110],"communication.":[111],"Not":[112],"only":[113],"constant":[114],"but":[115],"also":[116],"time-varying":[117],"coefficient":[118],"are":[121,135],"implemented":[122],"on":[123,140],"NVIDIA":[124],"GTX285,":[125],"GTX580":[126],"GTX":[128],"TITAN":[129],"X":[130],"GPUs,":[131],"performances":[134],"compared":[136],"results":[139],"single-core":[141],"multi-core":[143],"SIMD":[144],"CPU-based":[145],"PCs.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}