{"id":"https://openalex.org/W1595723543","doi":"https://doi.org/10.5075/epfl-thesis-6552","title":"Efficient Communication and Synchronization on Manycore Processors","display_name":"Efficient Communication and Synchronization on Manycore Processors","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1595723543","doi":"https://doi.org/10.5075/epfl-thesis-6552","mag":"1595723543"},"language":"en","primary_location":{"id":"pmh:oai:infoscience.tind.io:206245","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/112264","pdf_url":"http://infoscience.epfl.ch/record/206245","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/206245","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046020902","display_name":"Darko Petrovi\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Petrovi\u0107, Darko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5046020902"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9995999932289124,"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":0.8705152869224548},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.7604870796203613},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6686655879020691},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6261420249938965},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.6229040622711182},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5853578448295593},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5350929498672485},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5092450380325317},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5044177770614624},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5022428035736084},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.45182177424430847},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.4344113767147064},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.41403836011886597},{"id":"https://openalex.org/keywords/mesif-protocol","display_name":"MESIF protocol","score":0.41224682331085205},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4100120961666107},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3424321413040161},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.33142122626304626},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.27696508169174194},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19694381952285767},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1390663981437683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8705152869224548},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.7604870796203613},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6686655879020691},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6261420249938965},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.6229040622711182},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5853578448295593},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5350929498672485},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5092450380325317},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5044177770614624},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5022428035736084},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.45182177424430847},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.4344113767147064},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.41403836011886597},{"id":"https://openalex.org/C199979278","wikidata":"https://www.wikidata.org/wiki/Q263221","display_name":"MESIF protocol","level":5,"score":0.41224682331085205},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4100120961666107},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3424321413040161},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.33142122626304626},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.27696508169174194},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19694381952285767},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1390663981437683},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:infoscience.tind.io:206245","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/112264","pdf_url":"http://infoscience.epfl.ch/record/206245","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},{"id":"pmh:doi:10.5075/epfl-thesis-6552","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:infoscience.epfl.ch:206245","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/206245","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.5075/epfl-thesis-6552","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-6552","pdf_url":null,"source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"mag:1595723543","is_oa":false,"landing_page_url":"https://infoscience.epfl.ch/record/206245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:206245","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/112264","pdf_url":"http://infoscience.epfl.ch/record/206245","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doctoral thesis"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7799999713897705,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1595723543.pdf","grobid_xml":"https://content.openalex.org/works/W1595723543.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W57462620","https://openalex.org/W246536198","https://openalex.org/W647867498","https://openalex.org/W1512616543","https://openalex.org/W1525350307","https://openalex.org/W1560897251","https://openalex.org/W1591363587","https://openalex.org/W1825216778","https://openalex.org/W1963921067","https://openalex.org/W1974420955","https://openalex.org/W1979566015","https://openalex.org/W1979885075","https://openalex.org/W1981393723","https://openalex.org/W1983572666","https://openalex.org/W1985131796","https://openalex.org/W1992679913","https://openalex.org/W1996931099","https://openalex.org/W2014345013","https://openalex.org/W2019629740","https://openalex.org/W2032401773","https://openalex.org/W2039765803","https://openalex.org/W2060204338","https://openalex.org/W2065742943","https://openalex.org/W2085407655","https://openalex.org/W2088143111","https://openalex.org/W2100817684","https://openalex.org/W2102061396","https://openalex.org/W2103772475","https://openalex.org/W2111470409","https://openalex.org/W2113552056","https://openalex.org/W2113751407","https://openalex.org/W2114052846","https://openalex.org/W2114688360","https://openalex.org/W2119887431","https://openalex.org/W2131136524","https://openalex.org/W2131613942","https://openalex.org/W2132220514","https://openalex.org/W2133557963","https://openalex.org/W2134058640","https://openalex.org/W2135052239","https://openalex.org/W2138404963","https://openalex.org/W2141168287","https://openalex.org/W2142729958","https://openalex.org/W2148032086","https://openalex.org/W2148564531","https://openalex.org/W2151194859","https://openalex.org/W2152455393","https://openalex.org/W2154717928","https://openalex.org/W2158551169","https://openalex.org/W2160054705","https://openalex.org/W2168075869","https://openalex.org/W2170293694","https://openalex.org/W2170653240","https://openalex.org/W2225140656","https://openalex.org/W2398665257","https://openalex.org/W2404301698"],"related_works":["https://openalex.org/W2141168287","https://openalex.org/W626390526","https://openalex.org/W2118980029","https://openalex.org/W2042880462","https://openalex.org/W165724657","https://openalex.org/W1556995085","https://openalex.org/W2127368689","https://openalex.org/W2399849424","https://openalex.org/W2766883563","https://openalex.org/W2733525365","https://openalex.org/W2072099290","https://openalex.org/W2613318832","https://openalex.org/W1987596260","https://openalex.org/W2050120016","https://openalex.org/W2245133856","https://openalex.org/W1999489580","https://openalex.org/W2099030945","https://openalex.org/W2121736689","https://openalex.org/W2047967421","https://openalex.org/W1983518954"],"abstract_inverted_index":{"The":[0,258,289,323],"increased":[1],"number":[2,13,249],"of":[3,14,20,86,103,118,163,230,242,250,261,274,325,346,355,364,406],"cores":[4],"integrated":[5],"on":[6,74,83,128,201,254,265,282,317,339,379],"a":[7,12,40,129,157,318],"chip":[8],"has":[9,49],"brought":[10],"about":[11,17],"challenges.":[15],"Concerns":[16],"the":[18,100,115,119,139,178,222,226,240,248,255,262,272,331,344,347,362,404],"scalability":[19],"cache":[21,36,348],"coherence":[22,37,349],"protocols":[23],"have":[24],"urged":[25],"both":[26,281],"researchers":[27],"and":[28,71,105,123,183,193,204,228,286,295,315,394],"practitioners":[29],"to":[30,55,209,299,310,373],"explore":[31],"alternative":[32,54],"programming":[33],"models,":[34],"where":[35],"is":[38,99],"not":[39],"given.":[41],"Message":[42,179],"passing,":[43,341],"traditionally":[44],"used":[45,59,309],"in":[46,60,92,174,190],"distributed":[47,191],"systems,":[48],"surfaced":[50],"as":[51,358,412,414],"an":[52,81,142,217],"appealing":[53],"shared":[56,112,284,356,359],"memory,":[57,357],"commonly":[58],"multiprocessor":[61],"systems.":[62],"In":[63,114],"this":[64,91,235],"thesis,":[65,120],"we":[66,121,134,215,237,292,352,371,396],"study":[67,125],"how":[68],"basic":[69],"communication":[70,104,127,203,219],"synchronization":[72],"primitives":[73],"manycore":[75,131,144],"processors":[76,380,391],"can":[77],"be":[78],"improved,":[79],"with":[80,109,399],"accent":[82],"taking":[84],"advantage":[85,241,324,354],"message":[87,97,287,340,385],"passing.":[88,288,386],"We":[89,268],"do":[90],"two":[93,388],"different":[94,231],"contexts:":[95],"(i)":[96],"passing":[98],"only":[101],"means":[102],"(ii)":[106],"it":[107],"coexists":[108],"traditional":[110],"cache-coherent":[111,283],"memory.":[113],"first":[116],"part":[117,260],"analytically":[122],"experimentally":[124],"collective":[126],"message-passing":[130],"processor.":[132,322],"First,":[133],"devise":[135],"broadcast":[136,159,232],"algorithms":[137,192,233,291,328],"for":[138,168,172,185,188,221,384],"Intel":[140,393],"SCC,":[141],"experimental":[143],"platform":[145],"without":[146,381],"coherent":[147],"caches.":[148],"Our":[149],"ideas":[150],"are":[151,165,199,297],"captured":[152],"by":[153,270,411],"OC-Bcast":[154,164,197,243],"(on-chip":[155],"broadcast),":[156],"tree-based":[158],"algorithm.":[160],"Two":[161],"versions":[162],"presented:":[166],"One":[167],"synchronous":[169],"communication,":[170,187],"suitable":[171],"use":[173,189],"high-performance":[175],"libraries":[176],"implementing":[177],"Passing":[180],"Interface":[181],"(MPI),":[182],"another":[184],"asynchronous":[186],"general-purpose":[194],"software.":[195],"Both":[196],"flavors":[198],"based":[200],"one-sided":[202],"significantly":[205,300],"outperform":[206,301],"(by":[207,302],"up":[208,398],"3x)":[210],"state-of-the-art":[211],"two-sided":[212],"algorithms.":[213],"Next,":[214,370],"conceive":[216],"analytical":[218],"model":[220],"SCC.":[223],"By":[224],"expressing":[225],"latency":[227],"throughput":[229],"through":[234],"model,":[236],"reveal":[238],"that":[239,333,402],"comes":[244,329],"from":[245,330,375,392],"greatly":[246],"reducing":[247],"off-chip":[251],"memory":[252,285],"accesses":[253],"critical":[256,336,409],"path.":[257],"second":[259],"thesis":[263],"focuses":[264],"lock-based":[266],"synchronization.":[267],"start":[269],"introducing":[271],"concept":[273],"hybrid":[275,290,319,327],"mutual":[276],"exclusion":[277],"algorithms,":[278],"which":[279],"rely":[280,338],"present,":[293],"HybLock":[294],"HybComb,":[296],"shown":[298],"even":[303,378],"4x)":[304],"their":[305,334],"shared-memory-only":[306],"counterparts,":[307],"when":[308],"implement":[311],"concurrent":[312],"counters,":[313],"stacks":[314],"queues":[316],"Tilera":[320],"TILE-Gx":[321],"our":[326],"fact":[332],"most":[335],"parts":[337],"thereby":[342],"avoiding":[343],"overhead":[345],"protocol.":[350],"Still,":[351],"take":[353],"state":[360],"makes":[361],"implementation":[363],"certain":[365],"mechanisms":[366],"much":[367,413],"more":[368],"straightforward.":[369],"try":[372],"profit":[374],"these":[376],"insights":[377],"hardware":[382],"support":[383],"Taking":[387],"classic":[389],"x86":[390],"AMD,":[395],"come":[397],"cache-aware":[400],"optimizations":[401],"improve":[403],"performance":[405],"executing":[407],"contended":[408],"sections":[410],"6x.":[415]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}