{"id":"https://openalex.org/W4289656102","doi":"https://doi.org/10.1109/tpds.2022.3196192","title":"Improving Cache Utilization of Nested Parallel Programs by Almost Deterministic Work Stealing","display_name":"Improving Cache Utilization of Nested Parallel Programs by Almost Deterministic Work Stealing","publication_year":2022,"publication_date":"2022-08-03","ids":{"openalex":"https://openalex.org/W4289656102","doi":"https://doi.org/10.1109/tpds.2022.3196192"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3196192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3196192","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09848990.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09848990.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015135400","display_name":"Shumpei Shiina","orcid":"https://orcid.org/0000-0002-9129-3448"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shumpei Shiina","raw_affiliation_strings":["Department of Information and Communication Engineering, Graduate School of Information Science and Technology, University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9129-3448","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Graduate School of Information Science and Technology, University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009359355","display_name":"Kenjiro Taura","orcid":"https://orcid.org/0000-0001-5224-382X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenjiro Taura","raw_affiliation_strings":["Department of Information and Communication Engineering, Graduate School of Information Science and Technology, University of Tokyo, Bunkyo-ku, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5224-382X","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Graduate School of Information Science and Technology, University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.4351,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57153891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"33","issue":"12","first_page":"4530","last_page":"4546"},"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":0.9987000226974487,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9011029005050659},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7975700497627258},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7458781003952026},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5756672024726868},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5074006915092468},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5014946460723877},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.45904794335365295},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.4325827658176422},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4276903569698334},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4214613735675812},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.34822380542755127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9011029005050659},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7975700497627258},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7458781003952026},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5756672024726868},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5074006915092468},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5014946460723877},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.45904794335365295},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.4325827658176422},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4276903569698334},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4214613735675812},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.34822380542755127},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3196192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3196192","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09848990.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1109/tpds.2022.3196192","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3196192","pdf_url":"https://ieeexplore.ieee.org/ielx7/71/9790018/09848990.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3661865649","display_name":null,"funder_award_id":"JPNP16007","funder_id":"https://openalex.org/F4320321680","funder_display_name":"New Energy and Industrial Technology Development Organization"},{"id":"https://openalex.org/G4828951881","display_name":null,"funder_award_id":"PRIMERGY CX400M1/CX2550M5","funder_id":"https://openalex.org/F4320322832","funder_display_name":"University of Tokyo"},{"id":"https://openalex.org/G602837018","display_name":null,"funder_award_id":"CX400M1/CX2550M5","funder_id":"https://openalex.org/F4320322832","funder_display_name":"University of Tokyo"},{"id":"https://openalex.org/G8840736634","display_name":"Dynamic task scheduling strategies for deep memory hierarchies in the future","funder_award_id":"22KJ0677","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321680","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"},{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289656102.pdf","grobid_xml":"https://content.openalex.org/works/W4289656102.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1489069776","https://openalex.org/W1542798451","https://openalex.org/W1545054551","https://openalex.org/W1562463424","https://openalex.org/W1594031697","https://openalex.org/W1968020161","https://openalex.org/W1972200437","https://openalex.org/W1978278938","https://openalex.org/W1986864222","https://openalex.org/W2002209075","https://openalex.org/W2006450678","https://openalex.org/W2009964586","https://openalex.org/W2016559894","https://openalex.org/W2026842524","https://openalex.org/W2028637981","https://openalex.org/W2032401773","https://openalex.org/W2038141711","https://openalex.org/W2043013658","https://openalex.org/W2046356862","https://openalex.org/W2052196304","https://openalex.org/W2060847221","https://openalex.org/W2061211558","https://openalex.org/W2068306188","https://openalex.org/W2072725684","https://openalex.org/W2087610851","https://openalex.org/W2089064856","https://openalex.org/W2091782827","https://openalex.org/W2093357625","https://openalex.org/W2095875205","https://openalex.org/W2096898433","https://openalex.org/W2104861744","https://openalex.org/W2119860027","https://openalex.org/W2125621954","https://openalex.org/W2131264486","https://openalex.org/W2131296084","https://openalex.org/W2135063076","https://openalex.org/W2144404616","https://openalex.org/W2146700739","https://openalex.org/W2159031085","https://openalex.org/W2159184943","https://openalex.org/W2159952265","https://openalex.org/W2172139828","https://openalex.org/W2202621926","https://openalex.org/W2237102931","https://openalex.org/W2467057949","https://openalex.org/W2508028078","https://openalex.org/W2577529361","https://openalex.org/W2768348081","https://openalex.org/W2787188540","https://openalex.org/W2949888609","https://openalex.org/W2986763848","https://openalex.org/W3102453088","https://openalex.org/W3105788098","https://openalex.org/W3120740533","https://openalex.org/W3130341238","https://openalex.org/W3159768617","https://openalex.org/W6632419363","https://openalex.org/W6656899617","https://openalex.org/W6662079299","https://openalex.org/W6679289121","https://openalex.org/W6683813759","https://openalex.org/W6745609711"],"related_works":["https://openalex.org/W2140282198","https://openalex.org/W3141593011","https://openalex.org/W2026842524","https://openalex.org/W2379400621","https://openalex.org/W1968013322","https://openalex.org/W1991739900","https://openalex.org/W2809015808","https://openalex.org/W2143013049","https://openalex.org/W2088401441","https://openalex.org/W3194406605"],"abstract_inverted_index":{"Nested":[0],"(fork-join)":[1],"parallelism":[2,11,32],"eases":[3],"parallel":[4,17,162],"programming":[5],"by":[6,74,145,179],"enabling":[7],"high-level":[8],"expression":[9],"of":[10,30,49,56,96,111,127,161,176],"and":[12,19,181],"leaving":[13],"the":[14,22,45,112,148,171,189],"mapping":[15],"between":[16],"tasks":[18],"hardware":[20],"to":[21,35,86,102,137],"runtime":[23],"scheduler.":[24],"A":[25],"challenge":[26],"in":[27,44],"dynamic":[28,88],"scheduling":[29,84],"nested":[31],"is":[33,114,123,134,143],"how":[34],"exploit":[36],"data":[37,72],"locality,":[38],"which":[39,69],"has":[40],"become":[41],"more":[42],"demanding":[43],"deep":[46],"cache":[47,106,142,149],"hierarchies":[48],"modern":[50],"processors":[51],"with":[52],"a":[53,77,82,128,140,159,184],"large":[54],"number":[55],"cores.":[57],"This":[58],"paper":[59],"introduces":[60],"<italic":[61,116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[62,117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">almost":[63],"deterministic":[64],"work":[65,99,174],"stealing":[66,175],"(ADWS)</i>":[67],",":[68],"efficiently":[70],"exploits":[71],"locality":[73],"deterministically":[75],"planning":[76],"cache-hierarchy-aware":[78],"schedule,":[79],"while":[80],"allowing":[81],"little":[83],"variety":[85],"facilitate":[87],"load":[89],"balancing.":[90],"Furthermore,":[91],"we":[92],"propose":[93],"an":[94],"extension":[95],"our":[97],"prior":[98],"on":[100,158],"ADWS":[101,146,169,191],"achieve":[103],"better":[104],"shared":[105,141],"utilization.":[107],"The":[108,121],"improved":[109],"version":[110],"scheduler":[113],"called":[115],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">multi-level":[118],"ADWS</i>":[119],".":[120],"idea":[122],"that":[124,167],"only":[125],"part":[126],"computation":[129],"whose":[130],"working":[131],"set":[132],"size":[133],"small":[135],"enough":[136],"fit":[138],"into":[139],"scheduled":[144],"within":[147],"recursively,":[150],"thus":[151],"avoiding":[152],"excessive":[153],"capacity":[154],"misses.":[155],"Our":[156],"evaluation":[157],"benchmark":[160],"decision":[163],"tree":[164],"construction":[165],"demonstrated":[166],"multi-level":[168],"outperformed":[170],"conventional":[172],"random":[173],"Cilk":[177],"Plus":[178],"61%":[180],"it":[182],"showed":[183],"40%":[185],"performance":[186],"improvement":[187],"over":[188],"previous":[190],"design.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}