{"id":"https://openalex.org/W2235785597","doi":"https://doi.org/10.1145/2830772.2830822","title":"SAWS","display_name":"SAWS","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2235785597","doi":"https://doi.org/10.1145/2830772.2830822","mag":"2235785597"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","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/A5101826859","display_name":"Jiwei Liu","orcid":"https://orcid.org/0000-0001-6211-8491"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiwei Liu","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101605460","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0001-8372-6541"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038997010","display_name":"Rami Melhem","orcid":"https://orcid.org/0000-0001-6403-5446"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rami Melhem","raw_affiliation_strings":["University of Pittsburgh, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":3.624,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93073668,"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":"383","last_page":"394"},"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/T11181","display_name":"Advanced Data Storage Technologies","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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9991000294685364,"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":0.8869616985321045},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6854890584945679},{"id":"https://openalex.org/keywords/synchronizing","display_name":"Synchronizing","score":0.568821907043457},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5287551283836365},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5270393490791321},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5040168166160583},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.48601871728897095},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.47198158502578735},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.438510924577713},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41078445315361023},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.3982140123844147},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.3394774794578552},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24364212155342102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08076760172843933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8869616985321045},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6854890584945679},{"id":"https://openalex.org/C162932704","wikidata":"https://www.wikidata.org/wiki/Q1058791","display_name":"Synchronizing","level":3,"score":0.568821907043457},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5287551283836365},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5270393490791321},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5040168166160583},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.48601871728897095},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.47198158502578735},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.438510924577713},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41078445315361023},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.3982140123844147},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.3394774794578552},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24364212155342102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08076760172843933},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830772.2830822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1762731526","https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W1984222112","https://openalex.org/W1989061323","https://openalex.org/W2027806965","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2049875313","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2098505406","https://openalex.org/W2111669132","https://openalex.org/W2142444503","https://openalex.org/W2166263440","https://openalex.org/W2169880332","https://openalex.org/W2273440736"],"related_works":["https://openalex.org/W272107128","https://openalex.org/W2149156503","https://openalex.org/W2125768521","https://openalex.org/W1579918296","https://openalex.org/W2160206528","https://openalex.org/W2115925816","https://openalex.org/W2008492897","https://openalex.org/W66392291","https://openalex.org/W2928470165","https://openalex.org/W2187267005"],"abstract_inverted_index":{"General-purpose":[0],"computing":[1],"on":[2,126,171],"Graphics":[3],"Processing":[4],"Units":[5],"(GPGPUs)":[6],"became":[7],"increasingly":[8],"popular":[9],"for":[10,66,129],"a":[11,84,127,150],"wide":[12],"range":[13],"of":[14,75,140,166],"applications":[15,25],"beyond":[16],"traditional":[17],"graphic":[18],"rendering":[19],"workloads.":[20],"GPGPU":[21],"exploits":[22],"parallelism":[23],"in":[24,108,147],"via":[26],"multithreading":[27],"to":[28,45,104,120,175],"hide":[29],"memory":[30,47],"latencies,":[31],"and":[32],"handles":[33],"control":[34],"complexity":[35],"by":[36,169],"barrier":[37,128,151],"synchronizations.":[38],"Warp":[39],"scheduling":[40,86],"algorithms":[41],"have":[42],"been":[43],"optimized":[44],"increase":[46],"latency":[48],"hiding":[49],"capability,":[50],"improve":[51,163],"cache":[52],"behavior,":[53],"or":[54],"alleviate":[55],"branch":[56],"divergence.":[57],"To":[58],"date,":[59],"there":[60],"is":[61,89,95,152],"no":[62],"scheduler":[63],"that":[64,88,96,114,143,157],"accounts":[65],"the":[67,73,137,164,176],"synchronization":[68,90],"behavior":[69],"among":[70],"warps":[71,106,122,141],"under":[72],"presence":[74],"multiple":[76],"warp":[77,85,110],"schedulers.":[78,111,179],"In":[79],"this":[80],"paper,":[81],"we":[82],"develop":[83],"algorithm":[87],"aware.":[91],"The":[92],"key":[93],"observation":[94],"excessive":[97],"stall":[98],"cycles":[99],"may":[100],"be":[101],"introduced":[102],"due":[103],"synchronizing":[105],"residing":[107],"different":[109],"We":[112],"propose":[113],"schedulers":[115,161],"coordinate":[116],"with":[117],"each":[118],"other":[119],"avoid":[121],"from":[123],"being":[124],"blocked":[125],"overly":[130],"long.":[131],"Such":[132],"coordination":[133],"will":[134],"dynamically":[135],"reorder":[136],"execution":[138],"sequence":[139],"so":[142],"they":[144],"are":[145],"issued":[146],"proximity":[148],"when":[149,173],"encountered.":[153],"Performance":[154],"evaluations":[155],"demonstrate":[156],"our":[158],"proposed":[159],"coordinated":[160],"can":[162],"performance":[165],"synchronization-rich":[167],"benchmarks":[168],"10%":[170],"average":[172],"compared":[174],"state-of-the-art":[177],"non-coordinating":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2016-06-24T00:00:00"}
