{"id":"https://openalex.org/W3119880013","doi":"https://doi.org/10.1145/3433103","title":"PolyDL","display_name":"PolyDL","publication_year":2021,"publication_date":"2021-01-07","ids":{"openalex":"https://openalex.org/W3119880013","doi":"https://doi.org/10.1145/3433103","mag":"3119880013"},"language":"en","primary_location":{"id":"doi:10.1145/3433103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3433103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3433103","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3433103","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082088223","display_name":"Sanket Tavarageri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sanket Tavarageri","raw_affiliation_strings":["Intel Labs, Bengaluru, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024066643","display_name":"Alexander Heinecke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Alexander Heinecke","raw_affiliation_strings":["Intel Labs, Bengaluru, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110786116","display_name":"Sasikanth Avancha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sasikanth Avancha","raw_affiliation_strings":["Intel Labs, Bengaluru, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083700279","display_name":"Bharat Kaul","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bharat Kaul","raw_affiliation_strings":["Intel Labs, Bengaluru, Karnataka, India"],"affiliations":[{"raw_affiliation_string":"Intel Labs, Bengaluru, Karnataka, India","institution_ids":["https://openalex.org/I4210146682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047984097","display_name":"Gagandeep Goyal","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gagandeep Goyal","raw_affiliation_strings":["IIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075524478","display_name":"Ramakrishna Upadrasta","orcid":"https://orcid.org/0000-0002-5290-3266"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramakrishna Upadrasta","raw_affiliation_strings":["IIT Hyderabad"],"affiliations":[{"raw_affiliation_string":"IIT Hyderabad","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082088223"],"corresponding_institution_ids":["https://openalex.org/I4210146682"],"apc_list":null,"apc_paid":null,"fwci":3.6845,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":{"value":0.93152414,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"1","last_page":"27"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9041202068328857},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6746894121170044},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4680801331996918},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42443087697029114},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.42373090982437134},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41938576102256775},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.41566166281700134},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39540135860443115},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3859216868877411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3762553334236145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9041202068328857},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6746894121170044},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4680801331996918},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42443087697029114},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.42373090982437134},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41938576102256775},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.41566166281700134},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39540135860443115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3859216868877411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3762553334236145},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3433103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3433103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3433103","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3433103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3433103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3433103","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3119880013.pdf","grobid_xml":"https://content.openalex.org/works/W3119880013.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1504751168","https://openalex.org/W1536680647","https://openalex.org/W1558370006","https://openalex.org/W1969392714","https://openalex.org/W1989988531","https://openalex.org/W2051305716","https://openalex.org/W2063774307","https://openalex.org/W2064823029","https://openalex.org/W2073061372","https://openalex.org/W2112391112","https://openalex.org/W2142252451","https://openalex.org/W2151300055","https://openalex.org/W2158626113","https://openalex.org/W2158958889","https://openalex.org/W2162404488","https://openalex.org/W2172191698","https://openalex.org/W2194775991","https://openalex.org/W2314944927","https://openalex.org/W2412152731","https://openalex.org/W2506054026","https://openalex.org/W2606722458","https://openalex.org/W2779253217","https://openalex.org/W2786320458","https://openalex.org/W2804032941","https://openalex.org/W2806891462","https://openalex.org/W2896457183","https://openalex.org/W2905135312","https://openalex.org/W2949967139","https://openalex.org/W2954478959","https://openalex.org/W2955053021","https://openalex.org/W2961619211","https://openalex.org/W2963137752","https://openalex.org/W2963964033","https://openalex.org/W2966258469","https://openalex.org/W3009106325","https://openalex.org/W3016542674","https://openalex.org/W3042343931","https://openalex.org/W3100704941","https://openalex.org/W4212774754","https://openalex.org/W4244254628","https://openalex.org/W4246263814","https://openalex.org/W6682076890"],"related_works":["https://openalex.org/W2128640905","https://openalex.org/W2011460173","https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4246454774","https://openalex.org/W2162051035"],"abstract_inverted_index":{"Deep":[0,79],"Neural":[1,241],"Networks":[2],"(DNNs)":[3],"have":[4],"revolutionized":[5],"many":[6],"aspects":[7],"of":[8,13,36,78,101,133,141,171,191,196,199,235,266,269,287],"our":[9,252,281],"lives.":[10],"The":[11,34],"use":[12,49,168],"DNNs":[14],"is":[15,40,46,56,93,109,113,184],"becoming":[16],"ubiquitous,":[17],"including":[18],"in":[19,50,121,188,194,215],"software":[20],"for":[21,67,84],"image":[22],"recognition,":[23,25],"speech":[24,26],"synthesis,":[27],"language":[28],"translation,":[29],"to":[30,64,128,156,186,222,293,299],"name":[31],"a":[32,179,197,206,210,285,295],"few.":[33],"training":[35],"DNN":[37,103,258],"architectures,":[38,104],"however,":[39],"computationally":[41,57],"expensive.":[42],"Once":[43],"the":[44,51,61,76,94,98,139,153,192,200,232,236,264,278],"model":[45,155],"created,":[47],"its":[48],"intended":[52],"application\u2014the":[53],"inference":[54,62],"task,":[55],"heavy":[58],"too":[59],"and":[60,112,245],"needs":[63],"be":[65],"fast":[66],"real":[68],"time":[69,288],"use.":[70],"For":[71],"obtaining":[72],"high":[73,256,274],"performance":[74,140,262,265],"today,":[75],"code":[77,108],"Learning":[80],"(DL)":[81],"primitives":[82,135,167],"optimized":[83,107,143,301],"specific":[85],"architectures":[86],"by":[87],"expert":[88],"programmers":[89],"exposed":[90],"via":[91],"libraries":[92],"norm.":[95],"However,":[96],"given":[97],"constant":[99],"emergence":[100],"new":[102],"creating":[105],"hand":[106,142],"expensive,":[110],"slow":[111],"not":[114],"scalable.":[115],"To":[116],"address":[117],"this":[118,122],"performance-productivity":[119],"challenge,":[120],"article":[123],"we":[124,177,249],"present":[125],"compiler":[126,208,220],"algorithms":[127,151,221],"automatically":[129,254],"generate":[130],"high-performance":[131],"implementations":[132,190],"DL":[134,166],"that":[136,204,227,251],"closely":[137],"match":[138],"libraries.":[144],"We":[145,202,218],"develop":[146,178,219],"novel":[147],"data":[148,229],"reuse":[149],"analysis":[150],"using":[152],"polyhedral":[154],"derive":[157],"efficient":[158],"execution":[159],"schedules":[160],"automatically.":[161],"In":[162],"addition,":[163],"because":[164],"most":[165],"some":[169],"variant":[170],"matrix":[172,246],"multiplication":[173,247],"at":[174],"their":[175],"core,":[176],"flexible":[180],"framework":[181],"where":[182],"it":[183],"possible":[185],"plug":[187],"library":[189,272],"same":[193,279],"lieu":[195],"subset":[198],"loops.":[201],"show":[203],"such":[205],"hybrid":[207],"plus":[209],"minimal":[211],"library-use":[212],"approach":[213,253],"results":[214],"state-of-the-art":[216],"performance.":[217],"also":[223],"perform":[224],"operator":[225],"fusions":[226],"reduce":[228],"movement":[230],"through":[231],"memory":[233],"hierarchy":[234],"computer":[237],"system.":[238],"Using":[239],"Convolution":[240],"Network":[242],"(CNN)":[243],"models":[244],"operations,":[248],"demonstrate":[250],"creates":[255],"performing":[257],"building":[259],"blocks":[260],"whose":[261],"matches":[263],"hand-crafted":[267],"kernels":[268],"Intel\u2019s":[270],"oneDNN":[271],"on":[273],"end":[275],"CPUs.":[276],"At":[277],"time,":[280],"techniques":[282],"take":[283],"only":[284],"fraction":[286],"(1/20":[289],"or":[290],"less)":[291],"compared":[292],"AutoTVM,":[294],"deep":[296],"learning":[297],"auto-tuner":[298],"create":[300],"implementations.":[302]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-01-18T00:00:00"}