{"id":"https://openalex.org/W2774005267","doi":"https://doi.org/10.1109/iiswc.2017.8167781","title":"HeteroSync: A benchmark suite for fine-grained synchronization on tightly coupled GPUs","display_name":"HeteroSync: A benchmark suite for fine-grained synchronization on tightly coupled GPUs","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2774005267","doi":"https://doi.org/10.1109/iiswc.2017.8167781","mag":"2774005267"},"language":"en","primary_location":{"id":"doi:10.1109/iiswc.2017.8167781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2017.8167781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"},"type":"article","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/A5047054160","display_name":"Matthew D. Sinclair","orcid":"https://orcid.org/0000-0003-0189-7895"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew D. Sinclair","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075312447","display_name":"Johnathan Alsop","orcid":"https://orcid.org/0000-0001-5272-2396"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johnathan Alsop","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086111967","display_name":"Sarita V. Adve","orcid":"https://orcid.org/0000-0002-3403-5119"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarita V. Adve","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047054160"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.7694,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.92288007,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"239","last_page":"249"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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":0.891162633895874},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7013773918151855},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6509116291999817},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.6450255513191223},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6449593901634216},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5886078476905823},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5323182940483093},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5111809372901917},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.44757795333862305},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.4377906322479248},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42879998683929443},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2362382411956787},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13158679008483887},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.11915412545204163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.891162633895874},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7013773918151855},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6509116291999817},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.6450255513191223},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6449593901634216},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5886078476905823},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5323182940483093},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5111809372901917},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.44757795333862305},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.4377906322479248},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2362382411956787},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13158679008483887},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.11915412545204163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iiswc.2017.8167781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iiswc.2017.8167781","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Symposium on Workload Characterization (IISWC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1825921030","https://openalex.org/W1897254069","https://openalex.org/W1945229733","https://openalex.org/W1978155891","https://openalex.org/W1979527452","https://openalex.org/W1988877888","https://openalex.org/W1991397056","https://openalex.org/W1997162567","https://openalex.org/W1997352364","https://openalex.org/W2021211271","https://openalex.org/W2041356909","https://openalex.org/W2053776346","https://openalex.org/W2083780331","https://openalex.org/W2086167999","https://openalex.org/W2099912705","https://openalex.org/W2101209730","https://openalex.org/W2122901568","https://openalex.org/W2128870271","https://openalex.org/W2138218143","https://openalex.org/W2150618958","https://openalex.org/W2152885346","https://openalex.org/W2153636750","https://openalex.org/W2157225945","https://openalex.org/W2160963348","https://openalex.org/W2164264749","https://openalex.org/W2236227338","https://openalex.org/W2301631282","https://openalex.org/W2319071579","https://openalex.org/W2415865954","https://openalex.org/W2528784626","https://openalex.org/W2562836034","https://openalex.org/W2605442520","https://openalex.org/W2626811727","https://openalex.org/W2797554255","https://openalex.org/W4250422783","https://openalex.org/W6639801777","https://openalex.org/W7075319370"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W3017188964","https://openalex.org/W2128546436","https://openalex.org/W2929727597","https://openalex.org/W2972717823","https://openalex.org/W4254940814","https://openalex.org/W55660756","https://openalex.org/W4256119818"],"abstract_inverted_index":{"Traditionally":[0],"GPUs":[1,26,41],"focused":[2],"on":[3,117],"streaming,":[4],"data-parallel":[5],"applications,":[6],"with":[7,30],"little":[8],"data":[9,92],"reuse":[10],"or":[11],"sharing":[12,33,93],"and":[13,35,48,101,114,123,130],"coarse-grained":[14],"synchronization.":[15],"However,":[16],"the":[17,58,98,106],"rise":[18],"of":[19,60,70,78,97,108],"general-purpose":[20],"GPU":[21],"(GPGPU)":[22],"computing":[23],"has":[24,53],"made":[25],"desirable":[27],"for":[28,39,110],"applications":[29],"more":[31],"general":[32],"patterns":[34],"fine-grained":[36],"synchronization,":[37],"especially":[38],"recent":[40],"that":[42,125],"have":[43],"a":[44,83],"unified":[45],"address":[46],"space":[47],"coherent":[49],"caches.":[50],"Prior":[51],"work":[52],"introduced":[54],"microbenchmarks":[55],"to":[56],"measure":[57],"impact":[59],"these":[61,79],"changes,":[62],"but":[63],"each":[64],"paper":[65],"uses":[66],"its":[67],"own":[68],"set":[69],"microbenchmarks.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"combine":[76],"several":[77,89],"sets":[80],"together":[81],"in":[82],"single":[84],"suite,":[85],"HeteroSync.":[86],"HeteroSync":[87,109],"includes":[88],"synchronization":[90],"primitives,":[91],"at":[94],"different":[95,111],"levels":[96],"memory":[99],"hierarchy,":[100],"relaxed":[102],"atomics.":[103],"We":[104],"characterize":[105],"scalability":[107],"coherence":[112,128],"protocols":[113],"consistency":[115,131],"models":[116,132],"modern,":[118],"tightly":[119],"coupled":[120],"CPU-GPU":[121],"systems":[122],"show":[124],"certain":[126],"algorithms,":[127],"protocols,":[129],"scale":[133],"better":[134],"than":[135],"others.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}