{"id":"https://openalex.org/W4221031300","doi":"https://doi.org/10.1109/cgo53902.2022.9741260","title":"Optimizing GPU Deep Learning Operators with Polyhedral Scheduling Constraint Injection","display_name":"Optimizing GPU Deep Learning Operators with Polyhedral Scheduling Constraint Injection","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W4221031300","doi":"https://doi.org/10.1109/cgo53902.2022.9741260"},"language":"en","primary_location":{"id":"doi:10.1109/cgo53902.2022.9741260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo53902.2022.9741260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024483254","display_name":"C\u00e9dric Bastoul","orcid":"https://orcid.org/0000-0002-7164-8213"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cedric Bastoul","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390198","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0003-2805-4396"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zhen Zhang","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025770235","display_name":"Harenome Razanajato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Harenome Razanajato","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073302324","display_name":"Nelson Lossing","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nelson Lossing","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089671590","display_name":"Adilla Susungi","orcid":"https://orcid.org/0000-0003-4104-8409"},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Adilla Susungi","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107479358","display_name":"Javier de Juan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Javier de Juan","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061411904","display_name":"Etienne Filhol","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Etienne Filhol","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060484040","display_name":"Baptiste Jarry","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Baptiste Jarry","raw_affiliation_strings":["Huawei Technologies France,Paris,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076993668","display_name":"Gianpietro Consolaro","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115519","display_name":"Centre de Recherche en Informatique","ror":"https://ror.org/020cdve92","country_code":"FR","type":"facility","lineage":["https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4210091621","https://openalex.org/I4210115519","https://openalex.org/I70768539"]},{"id":"https://openalex.org/I4210123571","display_name":"Huawei Technologies (France)","ror":"https://ror.org/02rbzf697","country_code":"FR","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210123571"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gianpietro Consolaro","raw_affiliation_strings":["Huawei Technologies France,Paris,France","Centre de Recherche en Informatique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies France,Paris,France","institution_ids":["https://openalex.org/I4210123571"]},{"raw_affiliation_string":"Centre de Recherche en Informatique","institution_ids":["https://openalex.org/I4210115519"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101772672","display_name":"Renwei Zhang","orcid":"https://orcid.org/0000-0002-9744-5676"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renwei Zhang","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Beijing,China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6236,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81388479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"313","last_page":"324"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization 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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9943000078201294,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9940000176429749,"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":0.8521685004234314},{"id":"https://openalex.org/keywords/polytope-model","display_name":"Polytope model","score":0.6183969974517822},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5535839796066284},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5527820587158203},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5179535150527954},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4116747975349426},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.28886348009109497},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25482919812202454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521685004234314},{"id":"https://openalex.org/C113391598","wikidata":"https://www.wikidata.org/wiki/Q1681391","display_name":"Polytope model","level":3,"score":0.6183969974517822},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5535839796066284},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5527820587158203},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5179535150527954},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4116747975349426},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28886348009109497},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25482919812202454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C145691206","wikidata":"https://www.wikidata.org/wiki/Q747980","display_name":"Polytope","level":2,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cgo53902.2022.9741260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo53902.2022.9741260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03663917v1","is_oa":false,"landing_page_url":"https://minesparis-psl.hal.science/hal-03663917","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2022 IEEE/ACM International Symposium on Code Generation and Optimization (CGO), Apr 2022, Seoul, South Korea. pp.313-324, ⟨10.1109/CGO53902.2022.9741260⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1191262899","https://openalex.org/W1533186609","https://openalex.org/W1558370006","https://openalex.org/W1591453641","https://openalex.org/W1686810756","https://openalex.org/W1922926746","https://openalex.org/W1970141743","https://openalex.org/W1985161391","https://openalex.org/W1991009705","https://openalex.org/W2034761517","https://openalex.org/W2038543880","https://openalex.org/W2055312318","https://openalex.org/W2068562880","https://openalex.org/W2077143534","https://openalex.org/W2108598243","https://openalex.org/W2113459411","https://openalex.org/W2157273783","https://openalex.org/W2168412050","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2290988208","https://openalex.org/W2291192259","https://openalex.org/W2318529993","https://openalex.org/W2332864379","https://openalex.org/W2398692629","https://openalex.org/W2549139847","https://openalex.org/W2583110315","https://openalex.org/W2788464413","https://openalex.org/W2804032941","https://openalex.org/W2806891462","https://openalex.org/W2896457183","https://openalex.org/W2905135312","https://openalex.org/W2925102126","https://openalex.org/W2955053021","https://openalex.org/W2963163009","https://openalex.org/W2964054286","https://openalex.org/W2979365412","https://openalex.org/W2983923412","https://openalex.org/W3081231451","https://openalex.org/W3086093316","https://openalex.org/W3118608800","https://openalex.org/W3119880013","https://openalex.org/W3177452048","https://openalex.org/W3193287414","https://openalex.org/W3203568064","https://openalex.org/W4231316372","https://openalex.org/W4233558979","https://openalex.org/W4244917406","https://openalex.org/W6637373629","https://openalex.org/W6676984168","https://openalex.org/W6712880563","https://openalex.org/W6740283659","https://openalex.org/W6751349269","https://openalex.org/W6755207826","https://openalex.org/W6757717574","https://openalex.org/W6760952751","https://openalex.org/W6781902310","https://openalex.org/W6787972765","https://openalex.org/W7018618753","https://openalex.org/W7062088831"],"related_works":["https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2020341030","https://openalex.org/W586214199","https://openalex.org/W2269131302","https://openalex.org/W2184722600","https://openalex.org/W2101285930"],"abstract_inverted_index":{"Automatic":[0],"parallel":[1],"code":[2],"generation":[3],"from":[4,132],"high-level":[5],"abstractions":[6],"such":[7,133],"as":[8],"those":[9],"manipulated":[10],"by":[11,112],"artificial":[12],"intelligence":[13],"and":[14,27,46,63,99,116,168,178],"deep":[15],"learning":[16],"(AI/DL)":[17],"frameworks":[18],"heavily":[19],"rely":[20,32],"on":[21,33,84,165,189],"compiler":[22],"techniques":[23],"for":[24,37,80,140,160,206],"automatic":[25],"parallelization":[26],"optimization.":[28],"Many":[29],"recent":[30],"advances":[31],"the":[34,57,60,71,94,104,119,143,154,195],"polyhedral":[35,95,120,155,204],"framework":[36,82,96],"this":[38,88,198],"task":[39],"because":[40],"of":[41,52,59,64,78,145,197],"its":[42],"ability":[43],"to":[44,47,68,92,118,123,130,136,152,202],"model":[45],"apply":[48],"a":[49,81,113,134,184],"wide":[50],"range":[51],"loop":[53],"transformations.":[54],"However,":[55],"modeling":[56],"complexity":[58],"target":[61],"architecture":[62],"efficient":[65,138,158],"cost":[66],"models":[67],"decide":[69],"about":[70],"best":[72],"transformation":[73],"is":[74],"in":[75,142],"general":[76],"out":[77],"reach":[79],"based":[83],"linear/affine":[85],"constraints.":[86],"In":[87],"work,":[89],"we":[90],"propose":[91],"decouple":[93],"into":[97],"linear":[98],"non-linear":[100,114],"components.":[101],"We":[102,127,171],"introduce":[103],"constraint":[105,149,176,180],"tree":[106],"abstraction":[107],"which":[108],"may":[109],"be":[110],"generated":[111],"optimizer":[115],"injected":[117],"optimization":[121],"process":[122],"build":[124],"better":[125],"solutions.":[126],"present":[128],"how":[129],"benefit":[131],"mechanism":[135],"generate":[137],"codes":[139],"GPU":[141],"context":[144],"AI/DL":[146,186],"operators.":[147],"Our":[148],"injection":[150,177],"allows":[151],"drive":[153],"scheduler":[156,174],"towards":[157],"solutions":[159],"load/store":[161],"vectorization":[162],"relying":[163],"both":[164],"memory":[166],"coalescing":[167],"vector":[169],"types.":[170],"implemented":[172],"our":[173,179],"supporting":[175],"construction":[181],"system":[182],"within":[183],"production":[185],"framework.":[187],"Experiments":[188],"well":[190],"known":[191],"neural":[192],"networks":[193],"show":[194],"efficiency":[196],"approach":[199],"with":[200],"respect":[201],"state-of-the-art":[203],"scheduling":[205],"GPU.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}