{"id":"https://openalex.org/W2038178246","doi":"https://doi.org/10.1145/2628071.2628105","title":"PATS","display_name":"PATS","publication_year":2014,"publication_date":"2014-08-21","ids":{"openalex":"https://openalex.org/W2038178246","doi":"https://doi.org/10.1145/2628071.2628105","mag":"2038178246"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2628105","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","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/A5101023755","display_name":"Qiumin Xu","orcid":"https://orcid.org/0000-0003-1391-3397"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiumin Xu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018033573","display_name":"Murali Annavaram","orcid":"https://orcid.org/0000-0002-4633-6867"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murali Annavaram","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Ming Hsieh Department of Electrical Engineering, University of Southern California, Los Angeles, CA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101023755"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":5.5166,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96150435,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"225","last_page":"236"},"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":0.9994999766349792,"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":0.9986000061035156,"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":0.8509389758110046},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7115113735198975},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.6615496873855591},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6433389186859131},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.628095805644989},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6168763041496277},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.502769947052002},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.47632867097854614},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.47150176763534546},{"id":"https://openalex.org/keywords/electrical-efficiency","display_name":"Electrical efficiency","score":0.44080305099487305},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.43010902404785156},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36010265350341797},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.35723942518234253},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34803682565689087},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23526570200920105},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.06908643245697021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509389758110046},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7115113735198975},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.6615496873855591},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6433389186859131},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.628095805644989},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6168763041496277},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.502769947052002},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.47632867097854614},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.47150176763534546},{"id":"https://openalex.org/C118993495","wikidata":"https://www.wikidata.org/wiki/Q5042828","display_name":"Electrical efficiency","level":3,"score":0.44080305099487305},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.43010902404785156},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36010265350341797},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.35723942518234253},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34803682565689087},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23526570200920105},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.06908643245697021},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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:10.1145/2628071.2628105","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2628105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8500000238418579,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G4580563191","display_name":null,"funder_award_id":"95421","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6051729634","display_name":null,"funder_award_id":"HR0011-12-2-0020","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1971997351","https://openalex.org/W1973538724","https://openalex.org/W1979527452","https://openalex.org/W1980364632","https://openalex.org/W1983235612","https://openalex.org/W1989061323","https://openalex.org/W1996037679","https://openalex.org/W2010840089","https://openalex.org/W2024001079","https://openalex.org/W2026186397","https://openalex.org/W2047060659","https://openalex.org/W2059301531","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2101903894","https://openalex.org/W2110014487","https://openalex.org/W2117357463","https://openalex.org/W2125263803","https://openalex.org/W2131054871","https://openalex.org/W2143999651","https://openalex.org/W2149959321","https://openalex.org/W2155568054","https://openalex.org/W2156831150","https://openalex.org/W2158899676","https://openalex.org/W2161537396","https://openalex.org/W2169880332","https://openalex.org/W2170382128","https://openalex.org/W2399715892","https://openalex.org/W6712805996"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"General":[0],"purpose":[1],"computing":[2],"using":[3],"graphics":[4],"processing":[5],"units":[6],"(GPGPUs)":[7],"is":[8],"an":[9],"attractive":[10],"option":[11],"to":[12,99,121],"achieve":[13],"power":[14,20,140,161,172],"efficient":[15],"throughput":[16],"computing.":[17],"But":[18],"the":[19,29,45,79,86,115,142,147,152,160],"efficiency":[21,174],"of":[22,31,39,49,77,89,156,165,175],"GPGPUs":[23,176],"can":[24],"be":[25],"significantly":[26,170],"curtailed":[27],"in":[28,64,82],"presence":[30],"divergence.":[32],"This":[33],"paper":[34],"evaluates":[35],"two":[36],"important":[37],"facets":[38],"this":[40,90,94],"problem.":[41],"First,":[42],"we":[43,92],"study":[44],"branch":[46,59,71,95],"divergence":[47,60,72,96,103,117],"behavior":[48],"various":[50],"GPGPU":[51],"workloads.":[52,66,84],"We":[53,150],"show":[54],"that":[55],"only":[56,69],"a":[57,101],"few":[58],"patterns":[61,73],"are":[62,135],"dominant":[63],"most":[65],"In":[67,85],"fact":[68],"five":[70],"account":[74],"for":[75,126,138],"60%":[76],"all":[78],"divergent":[80],"instructions":[81],"our":[83],"second":[87],"part":[88],"work":[91],"exploit":[93],"pattern":[97,104,118],"bias":[98],"propose":[100],"new":[102],"aware":[105],"warp":[106],"scheduler,":[107],"called":[108],"PATS.":[109,166],"PATS":[110,157],"prioritizes":[111],"scheduling":[112],"warps":[113],"with":[114,177],"same":[116],"so":[119],"as":[120],"create":[122],"long":[123,132],"idleness":[124,133],"windows":[125,134],"any":[127],"given":[128],"execution":[129],"lane.":[130],"The":[131],"then":[136],"exploited":[137],"efficiently":[139],"gating":[141,148,173],"unused":[143],"lanes":[144],"while":[145],"amortizing":[146],"overhead.":[149,180],"describe":[151],"architectural":[153],"implementation":[154],"details":[155],"and":[158,162],"evaluate":[159],"performance":[163,179],"impact":[164],"Our":[167],"proposed":[168],"design":[169],"improves":[171],"minimal":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}