{"id":"https://openalex.org/W2913778848","doi":"https://doi.org/10.1145/3300208","title":"Accelerating Synchronization Using Moving Compute to Data Model at 1,000-core Multicore Scale","display_name":"Accelerating Synchronization Using Moving Compute to Data Model at 1,000-core Multicore Scale","publication_year":2019,"publication_date":"2019-02-13","ids":{"openalex":"https://openalex.org/W2913778848","doi":"https://doi.org/10.1145/3300208","mag":"2913778848"},"language":"en","primary_location":{"id":"doi:10.1145/3300208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3300208","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3300208","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3300208","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036729752","display_name":"Halit Dogan","orcid":null},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Halit Dogan","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, USA"],"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023088436","display_name":"Masab Ahmad","orcid":"https://orcid.org/0000-0001-7786-3558"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masab Ahmad","raw_affiliation_strings":["University of Connecticut, Storrs, Connecticut, USA"],"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087708802","display_name":"Brian Kahne","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kahne","raw_affiliation_strings":["NXP Semiconductors, Austin, TX"],"affiliations":[{"raw_affiliation_string":"NXP Semiconductors, Austin, TX","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048129220","display_name":"Omer Khan","orcid":"https://orcid.org/0000-0001-6293-7403"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omer Khan","raw_affiliation_strings":["University of Connecticut, Connecticut, USA"],"affiliations":[{"raw_affiliation_string":"University of Connecticut, Connecticut, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036729752"],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":2.2218,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87128212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"1","last_page":"27"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8439176082611084},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7260044813156128},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7174356579780579},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.7013723850250244},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5773887634277344},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4901333749294281},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.48523473739624023},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.46053552627563477},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.43399739265441895},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.41639775037765503},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35041099786758423},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.2404116690158844},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.166826069355011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8439176082611084},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7260044813156128},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7174356579780579},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.7013723850250244},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5773887634277344},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4901333749294281},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.48523473739624023},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.46053552627563477},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.43399739265441895},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.41639775037765503},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35041099786758423},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.2404116690158844},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.166826069355011},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3300208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3300208","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3300208","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3300208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3300208","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3300208","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","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/G3593490706","display_name":null,"funder_award_id":"CNS-1718481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G490593687","display_name":null,"funder_award_id":"Intel","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G7005708999","display_name":"CSR: Small: Efficient Many-core Execution Models for Cognitive Computing","funder_award_id":"1718481","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2913778848.pdf","grobid_xml":"https://content.openalex.org/works/W2913778848.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W220440441","https://openalex.org/W1501077214","https://openalex.org/W1670978437","https://openalex.org/W1863196152","https://openalex.org/W1955235267","https://openalex.org/W1981943579","https://openalex.org/W1985818188","https://openalex.org/W2000137365","https://openalex.org/W2070747130","https://openalex.org/W2083868341","https://openalex.org/W2105876415","https://openalex.org/W2108598243","https://openalex.org/W2126603706","https://openalex.org/W2132231716","https://openalex.org/W2137299962","https://openalex.org/W2138815064","https://openalex.org/W2146591355","https://openalex.org/W2155066383","https://openalex.org/W2161522487","https://openalex.org/W2162422574","https://openalex.org/W2170382128","https://openalex.org/W2279098554","https://openalex.org/W2469279958","https://openalex.org/W2516627871","https://openalex.org/W2533063182","https://openalex.org/W2616512162","https://openalex.org/W2618530766","https://openalex.org/W2731857860","https://openalex.org/W2909218611","https://openalex.org/W2995394804","https://openalex.org/W3004291881","https://openalex.org/W4205196060","https://openalex.org/W4245607618","https://openalex.org/W4251382119"],"related_works":["https://openalex.org/W2337418885","https://openalex.org/W1979099492","https://openalex.org/W2145592252","https://openalex.org/W4207012101","https://openalex.org/W2407815036","https://openalex.org/W4255008187","https://openalex.org/W4205439893","https://openalex.org/W4250205214","https://openalex.org/W2036306661","https://openalex.org/W2143087414"],"abstract_inverted_index":{"Thread":[0],"synchronization":[1,140],"using":[2,130],"shared":[3,49],"memory":[4],"hardware":[5],"cache":[6,24,86],"coherence":[7,87],"paradigm":[8],"is":[9,93,112],"prevalent":[10],"in":[11,65,158,163],"multicore":[12,98,110],"processors.":[13],"However,":[14],"as":[15],"the":[16,85,117,122,147,151],"number":[17],"of":[18,121],"cores":[19,64],"increase":[20],"on":[21,95],"a":[22,66],"chip,":[23],"line":[25],"ping-pong":[26],"prevents":[27],"performance":[28,118],"scaling":[29,119],"for":[30],"algorithms":[31],"that":[32,47,136],"deploy":[33],"fine-grain":[34],"synchronization.":[35],"This":[36],"article":[37],"proposes":[38],"an":[39],"in-hardware":[40,90],"moving":[41],"computation":[42],"to":[43,69,100,103,114,143],"data":[44,50,71],"model":[45,92,124,149],"(MC)":[46],"pins":[48],"at":[51,62,125,150],"dedicated":[52],"cores.":[53],"The":[54,89,128],"critical":[55],"code":[56],"sections":[57],"are":[58],"serialized":[59],"and":[60,78,132,146,161],"executed":[61],"these":[63],"spatial":[67],"setting":[68],"enable":[70,76],"locality":[72],"optimizations.":[73],"In-hardware":[74],"messages":[75],"non-blocking":[77],"blocking":[79],"communication":[80],"between":[81],"cores,":[82,145],"without":[83],"involving":[84],"protocol.":[88],"MC":[91,123,148],"implemented":[94],"Tilera":[96],"Tile-Gx72":[97],"platform":[99],"evaluate":[101,116],"8-":[102],"64-core":[104],"count":[105,154],"scale.":[106,127],"A":[107],"simulated":[108],"RISC-V":[109],"environment":[111],"built":[113],"further":[115],"advantages":[120],"1,024-cores":[126],"evaluation":[129],"graph":[131],"machine-learning":[133],"benchmarks":[134],"illustrates":[135],"atomic":[137],"instructions":[138],"based":[139],"scales":[141],"up":[142],"512":[144],"same":[152],"core":[153],"outperforms":[155],"by":[156],"27%":[157],"completion":[159],"time":[160],"39%":[162],"dynamic":[164],"energy":[165],"consumption.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}