{"id":"https://openalex.org/W3175296859","doi":"https://doi.org/10.1145/3453688.3461525","title":"Predictive Warp Scheduling for Efficient Execution in GPGPU","display_name":"Predictive Warp Scheduling for Efficient Execution in GPGPU","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3175296859","doi":"https://doi.org/10.1145/3453688.3461525","mag":"3175296859"},"language":"en","primary_location":{"id":"doi:10.1145/3453688.3461525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453688.3461525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Great Lakes Symposium on VLSI","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/A5034589530","display_name":"Abhinish Anand","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Abhinish Anand","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011782290","display_name":"Winnie Thomas","orcid":"https://orcid.org/0000-0001-8341-2403"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Winnie Thomas","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019947309","display_name":"Suryakant Toraskar","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakant Toraskar","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073587430","display_name":"Virendra Singh","orcid":"https://orcid.org/0000-0002-7035-7844"},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Virendra Singh","raw_affiliation_strings":["Indian Institute of Technology Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034589530"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.2303,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47033765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"300"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987000226974487,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980999827384949,"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":0.8606942892074585},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5992087125778198},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5820767283439636},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5420632362365723},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5248335003852844},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5191744565963745},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4762670695781708},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.4530413746833801},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36830317974090576},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23430004715919495},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.12080356478691101},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.0899118185043335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8606942892074585},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5992087125778198},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5820767283439636},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5420632362365723},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5248335003852844},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5191744565963745},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4762670695781708},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.4530413746833801},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36830317974090576},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23430004715919495},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.12080356478691101},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0899118185043335},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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":1,"locations":[{"id":"doi:10.1145/3453688.3461525","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453688.3461525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Great Lakes Symposium on VLSI","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1977987009","https://openalex.org/W1979527452","https://openalex.org/W1984993578","https://openalex.org/W2035872164","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2078994750","https://openalex.org/W2098505406","https://openalex.org/W2138351227","https://openalex.org/W2517837804","https://openalex.org/W2571571258","https://openalex.org/W2883073617","https://openalex.org/W2884590322","https://openalex.org/W2886858179","https://openalex.org/W3005321997","https://openalex.org/W3133282456","https://openalex.org/W3157304207","https://openalex.org/W4239291609","https://openalex.org/W4249082578"],"related_works":["https://openalex.org/W3120961607","https://openalex.org/W4401568740","https://openalex.org/W2098207691","https://openalex.org/W3148568549","https://openalex.org/W1648516568","https://openalex.org/W361036515","https://openalex.org/W2269474412","https://openalex.org/W4386903460","https://openalex.org/W1596579276","https://openalex.org/W2159099865"],"abstract_inverted_index":{"Today's":[0],"general-purpose":[1],"graphics":[2],"processing":[3],"units":[4],"(GPGPUs)":[5],"offer":[6],"phenomenal":[7],"performance":[8,28,142],"to":[9,50,79,102,121,139,148],"applications":[10,34,160],"from":[11,112],"a":[12,37,62,94,156,162],"variety":[13],"of":[14,31,69,99,118,126,144,159],"fields.":[15],"Despite":[16],"its":[17],"memory-latency":[18],"tolerant":[19],"parallel":[20],"architecture,":[21],"GPGPU":[22],"cores":[23,135],"do":[24],"not":[25,48,106],"attain":[26],"optimal":[27],"with":[29,161],"most":[30],"the":[32,67,81,100,107,113,116,124,134,151],"memory-intensive":[33],"which":[35,73],"add":[36],"significant":[38],"load":[39],"on":[40],"memory-resources.":[41],"The":[42,90],"existing":[43],"thread":[44],"scheduling":[45,153],"mechanism":[46],"is":[47],"optimized":[49],"address":[51],"this":[52,58],"challenge":[53],"for":[54],"latency-sensitive":[55],"applications.":[56],"In":[57],"paper,":[59],"we":[60],"propose":[61],"warp-scheduling":[63],"policy":[64,92],"that":[65,128],"defers":[66],"execution":[68],"all":[70],"those":[71],"warps":[72,127],"will":[74],"potentially":[75],"cause":[76],"long-latency":[77],"memory-stalls,":[78],"prevent":[80],"resulting":[82],"congestion":[83,120],"in":[84,96,165],"interconnect":[85],"network":[86],"and":[87,132,146],"DRAM":[88],"bandwidth.":[89],"proposed":[91],"uses":[93],"predictor":[95],"each":[97],"core":[98],"GPU":[101],"predict":[103],"whether":[104],"or":[105],"data":[108],"can":[109,129],"be":[110,130],"retrieved":[111],"L1-cache":[114],"at":[115],"time":[117],"increased":[119],"effectively":[122],"reduce":[123],"number":[125],"paused":[131],"keep":[133],"active.":[136],"This":[137],"translates":[138],"an":[140],"average":[141,166],"improvement":[143],"11.6%":[145],"up":[147],"41.2%":[149],"over":[150],"state-of-the-art":[152],"policies":[154],"across":[155],"diverse":[157],"selection":[158],"4.2%":[163],"increase":[164],"power":[167],"consumption.":[168]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}