{"id":"https://openalex.org/W3161333526","doi":"https://doi.org/10.1007/s11227-021-03853-x","title":"Compiler-directed scratchpad memory data transfer optimization for multithreaded applications on a heterogeneous many-core architecture","display_name":"Compiler-directed scratchpad memory data transfer optimization for multithreaded applications on a heterogeneous many-core architecture","publication_year":2021,"publication_date":"2021-05-15","ids":{"openalex":"https://openalex.org/W3161333526","doi":"https://doi.org/10.1007/s11227-021-03853-x","mag":"3161333526"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-021-03853-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-021-03853-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03853-x.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"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":"The Journal of Supercomputing","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/s11227-021-03853-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009323865","display_name":"Xiaohan Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohan Tao","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049750136","display_name":"Jianmin Pang","orcid":"https://orcid.org/0000-0003-1835-5419"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jianmin Pang","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1835-5419","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101431784","display_name":"Jinlong Xu","orcid":"https://orcid.org/0000-0002-6261-8186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinlong Xu","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028753892","display_name":"Yu Zhu","orcid":"https://orcid.org/0000-0001-8836-7939"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhu","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5049750136"],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.9194,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73412112,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"77","issue":"12","first_page":"14502","last_page":"14524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.900248646736145},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7628113031387329},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6664806604385376},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5866454243659973},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.5053477883338928},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.45831507444381714},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4162517488002777},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2591051161289215},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17943137884140015}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.900248646736145},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7628113031387329},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6664806604385376},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5866454243659973},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.5053477883338928},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.45831507444381714},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4162517488002777},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2591051161289215},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17943137884140015}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-021-03853-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-021-03853-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03853-x.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"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":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11227-021-03853-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-021-03853-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-021-03853-x.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"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":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G6833750381","display_name":null,"funder_award_id":"2014AA01A301","funder_id":"https://openalex.org/F4320335773","funder_display_name":"National High-tech Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320335773","display_name":"National High-tech Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161333526.pdf","grobid_xml":"https://content.openalex.org/works/W3161333526.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1551757538","https://openalex.org/W1751458545","https://openalex.org/W1848142254","https://openalex.org/W1973479450","https://openalex.org/W1990383399","https://openalex.org/W2020322423","https://openalex.org/W2024666804","https://openalex.org/W2035720033","https://openalex.org/W2036853599","https://openalex.org/W2063656563","https://openalex.org/W2076848169","https://openalex.org/W2086807722","https://openalex.org/W2088943630","https://openalex.org/W2091545779","https://openalex.org/W2091729601","https://openalex.org/W2098511965","https://openalex.org/W2104009155","https://openalex.org/W2112121929","https://openalex.org/W2118486730","https://openalex.org/W2128938762","https://openalex.org/W2134572726","https://openalex.org/W2149590159","https://openalex.org/W2165366735","https://openalex.org/W2168412050","https://openalex.org/W2475126267","https://openalex.org/W2561081978","https://openalex.org/W2730450744","https://openalex.org/W2893613126","https://openalex.org/W2911579567","https://openalex.org/W2915780780","https://openalex.org/W2973031157","https://openalex.org/W3004326334","https://openalex.org/W3009601136","https://openalex.org/W3034163943","https://openalex.org/W3098602506","https://openalex.org/W4240791849"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W2046172023","https://openalex.org/W4256502920","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2999756192","https://openalex.org/W2389738237"],"abstract_inverted_index":{"Abstract":[0],"The":[1,160],"heterogeneous":[2,90],"many-core":[3,91],"architecture":[4],"plays":[5],"an":[6,182],"important":[7],"role":[8],"in":[9,88],"the":[10,83,105,114,121,129,137,141,165,169],"fields":[11],"of":[12,38,85,107,124,185],"high-performance":[13],"computing":[14,158],"and":[15,28,56,103,127,144,156,180],"scientific":[16,157],"computing.":[17],"It":[18],"uses":[19],"accelerator":[20],"cores":[21],"with":[22,42,47,150],"on-chip":[23,40],"memories":[24],"to":[25,81,97,119],"improve":[26],"performance":[27,117],"reduce":[29],"energy":[30,44,183],"consumption.":[31],"Scratchpad":[32],"memory":[33,41,58],"(SPM)":[34],"is":[35],"a":[36,48,64,73,89],"kind":[37],"fast":[39],"lower":[43],"consumption":[45],"compared":[46],"hardware":[49],"cache.":[50],"However,":[51],"data":[52,77,86,99,108,115,125,132],"transfer":[53,78,87,109,116,126,133],"between":[54],"SPM":[55,76],"off-chip":[57],"can":[59],"be":[60],"managed":[61],"only":[62],"by":[63,173],"programmer":[65],"or":[66],"compiler.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"propose":[72],"compiler-directed":[74],"multithreaded":[75],"model":[79,118],"(MSDTM)":[80],"optimize":[82],"process":[84],"architecture.":[92],"We":[93,111,135],"use":[94],"compile-time":[95],"analysis":[96],"classify":[98],"accesses,":[100],"check":[101],"dependences":[102],"determine":[104],"allocation":[106],"operations.":[110],"further":[112],"present":[113],"derive":[120],"optimal":[122],"granularity":[123],"select":[128],"most":[130],"profitable":[131],"strategy.":[134],"implement":[136],"proposed":[138,166],"MSDTM":[139,167],"on":[140,147,192],"GCC":[142],"complier":[143],"evaluate":[145],"it":[146],"Sunway":[148],"TaihuLight":[149],"selected":[151],"test":[152],"cases":[153],"from":[154],"benchmarks":[155],"applications.":[159],"experimental":[161],"result":[162],"shows":[163],"that":[164],"improves":[168],"application":[170],"execution":[171],"time":[172],"5.49":[174],"$$\\times$$":[175,187],"<mml:math":[176,188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[177,189],"<mml:mo>\u00d7</mml:mo>":[178,190],"</mml:math>":[179,191],"achieves":[181],"saving":[184],"5.16":[186],"average.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
