{"id":"https://openalex.org/W2203401041","doi":"https://doi.org/10.1109/iccd.2015.7357119","title":"Effective hardware-level thread synchronization for high performance and power efficiency in application specific multi-threaded embedded processors","display_name":"Effective hardware-level thread synchronization for high performance and power efficiency in application specific multi-threaded embedded processors","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2203401041","doi":"https://doi.org/10.1109/iccd.2015.7357119","mag":"2203401041"},"language":"en","primary_location":{"id":"doi:10.1109/iccd.2015.7357119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2015.7357119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 33rd IEEE International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5022212243","display_name":"Mahanama Wickramasinghe","orcid":"https://orcid.org/0000-0003-0899-2705"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mahanama Wickramasinghe","raw_affiliation_strings":["University of New South Wales, Sydney, NSW, AU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, NSW, AU","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115076813","display_name":"Hui Guo","orcid":"https://orcid.org/0009-0009-4952-4271"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hui Guo","raw_affiliation_strings":["School of Computer Science and Engineering The University of New South Wales, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering The University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.4082,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53985932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"46","issue":null,"first_page":"311","last_page":"318"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9980000257492065,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8727073669433594},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6582990884780884},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.649430513381958},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6158103346824646},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6103985905647278},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5321649312973022},{"id":"https://openalex.org/keywords/simultaneous-multithreading","display_name":"Simultaneous multithreading","score":0.4534478485584259},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41324383020401},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31546592712402344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8727073669433594},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6582990884780884},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.649430513381958},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6158103346824646},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6103985905647278},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5321649312973022},{"id":"https://openalex.org/C85717602","wikidata":"https://www.wikidata.org/wiki/Q82178","display_name":"Simultaneous multithreading","level":4,"score":0.4534478485584259},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41324383020401},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31546592712402344}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccd.2015.7357119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccd.2015.7357119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 33rd IEEE International Conference on Computer Design (ICCD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1003965471","https://openalex.org/W1490068595","https://openalex.org/W1986363052","https://openalex.org/W2029009124","https://openalex.org/W2036648807","https://openalex.org/W2037740397","https://openalex.org/W2043558658","https://openalex.org/W2043815962","https://openalex.org/W2047060659","https://openalex.org/W2054397171","https://openalex.org/W2063389777","https://openalex.org/W2071578467","https://openalex.org/W2086672145","https://openalex.org/W2100799944","https://openalex.org/W2127000736","https://openalex.org/W2134058640","https://openalex.org/W2141138026","https://openalex.org/W2157490181","https://openalex.org/W2160468841","https://openalex.org/W2162138122","https://openalex.org/W2162623750","https://openalex.org/W2293964831","https://openalex.org/W2413835052","https://openalex.org/W3145579537","https://openalex.org/W6668626555","https://openalex.org/W6697052910"],"related_works":["https://openalex.org/W2115561485","https://openalex.org/W1985089255","https://openalex.org/W2153202644","https://openalex.org/W2380961080","https://openalex.org/W2010970156","https://openalex.org/W4235861380","https://openalex.org/W2106625514","https://openalex.org/W2133675875","https://openalex.org/W2726029565","https://openalex.org/W1867214769"],"abstract_inverted_index":{"Multi-threaded":[0],"processors":[1,76],"interleave":[2],"the":[3,23,109,150,173,179],"execution":[4,36,152],"of":[5,22,118],"several":[6],"threads":[7,120],"to":[8,28,49,58,79,91,112,153,157],"reduce":[9,92],"processor":[10,100,135],"stalling":[11,25],"time.":[12],"Instruction":[13],"cache":[14,45,66,94],"misses":[15,46,67,95],"usually":[16],"account":[17],"for":[18,101,136],"a":[19,97,116,126,132,142],"significant":[20],"fraction":[21],"overall":[24],"time":[26,37],"due":[27,57],"frequent":[29],"instruction":[30,65,93],"fetches.":[31],"Apart":[32],"from":[33],"incurring":[34],"extended":[35],"(hence":[38],"its":[39],"direct":[40],"impact":[41],"on":[42,121],"energy":[43,187],"consumption),":[44],"also":[47,177],"lead":[48],"indirect":[50],"power":[51],"overheads":[52],"and":[53,84,107],"increased":[54],"thread":[55,151],"switching":[56],"resulting":[59],"main":[60],"memory":[61,180],"accesses.":[62],"Therefore,":[63],"minimizing":[64],"is":[68],"important":[69],"especially":[70],"in":[71,82,96],"designing":[72],"application":[73],"specific":[74],"embedded":[75],"that":[77,103,167],"tend":[78],"be":[80,113,129,158],"compact":[81],"size":[83],"consume":[85],"low":[86],"power.":[87],"This":[88],"paper":[89],"aims":[90],"single":[98],"pipeline":[99,174],"applications":[102],"offer":[104],"embarrassing":[105],"parallelism":[106],"enable":[108],"same":[110],"code":[111],"executed":[114],"by":[115,161],"number":[117],"independent":[119],"different":[122],"data":[123],"sets.":[124],"Such":[125],"design":[127,169],"can":[128],"used":[130],"as":[131],"building":[133],"block":[134],"large":[137],"multicomputer":[138],"systems.":[139],"We":[140],"propose":[141],"micro-architectural":[143],"level":[144],"multithreading":[145],"control":[146],"design,":[147],"which":[148],"synchronizes":[149],"allow":[154],"cached":[155],"instructions":[156],"maximally":[159],"reused":[160],"all":[162],"threads.":[163],"Our":[164],"experiments":[165],"show":[166],"our":[168],"not":[170],"only":[171],"increases":[172],"performance":[175],"but":[176],"reduces":[178],"access":[181],"frequency,":[182],"hence":[183],"effectively":[184],"achieving":[185],"high":[186],"efficiency.":[188]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}