{"id":"https://openalex.org/W3018661492","doi":"https://doi.org/10.1145/3342195.3387549","title":"Accelerating winograd convolutions using symbolic computation and meta-programming","display_name":"Accelerating winograd convolutions using symbolic computation and meta-programming","publication_year":2020,"publication_date":"2020-04-15","ids":{"openalex":"https://openalex.org/W3018661492","doi":"https://doi.org/10.1145/3342195.3387549","mag":"3018661492"},"language":"en","primary_location":{"id":"doi:10.1145/3342195.3387549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342195.3387549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth European Conference on Computer Systems","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/A5028887858","display_name":"Arya Mazaheri","orcid":"https://orcid.org/0000-0002-5671-4710"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Arya Mazaheri","raw_affiliation_strings":["Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065711020","display_name":"Tim Beringer","orcid":"https://orcid.org/0000-0002-5567-8738"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Beringer","raw_affiliation_strings":["Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076613173","display_name":"Matthew W. Moskewicz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109380","display_name":"Tesla (United States)","ror":"https://ror.org/02kpcqm42","country_code":"US","type":"company","lineage":["https://openalex.org/I4210109380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Moskewicz","raw_affiliation_strings":["Tesla Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tesla Inc","institution_ids":["https://openalex.org/I4210109380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085070208","display_name":"Felix Wolf","orcid":"https://orcid.org/0000-0002-0926-9212"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Wolf","raw_affiliation_strings":["Technical University of Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079359777","display_name":"Ali Jannesari","orcid":"https://orcid.org/0000-0001-8672-5317"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Jannesari","raw_affiliation_strings":["Iowa State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4787,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6428791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9876000285148621,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8256906270980835},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.7906426191329956},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6636595726013184},{"id":"https://openalex.org/keywords/metaprogramming","display_name":"Metaprogramming","score":0.5848230719566345},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5100505948066711},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4583439826965332},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4257959723472595},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4137762486934662},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3152974843978882},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20822909474372864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18590664863586426},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11511239409446716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256906270980835},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.7906426191329956},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6636595726013184},{"id":"https://openalex.org/C35390924","wikidata":"https://www.wikidata.org/wiki/Q661075","display_name":"Metaprogramming","level":2,"score":0.5848230719566345},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5100505948066711},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4583439826965332},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4257959723472595},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4137762486934662},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3152974843978882},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20822909474372864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18590664863586426},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11511239409446716},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3342195.3387549","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342195.3387549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth European Conference on Computer Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:143194","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/143194/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W1487564550","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1825672851","https://openalex.org/W1843951383","https://openalex.org/W1903029394","https://openalex.org/W1922123711","https://openalex.org/W1960289438","https://openalex.org/W2001121794","https://openalex.org/W2016053056","https://openalex.org/W2172654076","https://openalex.org/W2530879419","https://openalex.org/W2549301733","https://openalex.org/W2592875630","https://openalex.org/W2615663338","https://openalex.org/W2785856116","https://openalex.org/W2786374423","https://openalex.org/W2798341898","https://openalex.org/W2799985340","https://openalex.org/W2804032941","https://openalex.org/W2809426916","https://openalex.org/W2890887549","https://openalex.org/W2904795057","https://openalex.org/W2949117887","https://openalex.org/W2950649068","https://openalex.org/W2952713184","https://openalex.org/W2963374099","https://openalex.org/W2967496526","https://openalex.org/W3011121930","https://openalex.org/W3102753670","https://openalex.org/W4251637954"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W1872724644","https://openalex.org/W4367156293","https://openalex.org/W2750549761","https://openalex.org/W28826848","https://openalex.org/W2122272819","https://openalex.org/W2994151208","https://openalex.org/W2964954556"],"abstract_inverted_index":{"Convolution":[0],"operations":[1,120],"are":[2,42],"essential":[3],"constituents":[4],"of":[5,33,39,52,91,118,150,158],"convolutional":[6],"neural":[7],"networks.":[8],"Their":[9],"efficient":[10,92,138],"and":[11,18,58,80,93],"performance-portable":[12],"implementation":[13],"demands":[14],"tremendous":[15],"programming":[16,151],"effort":[17],"fine-tuning.":[19],"Winograd's":[20],"minimal":[21],"filtering":[22],"algorithm":[23,41],"is":[24],"a":[25,49,66,85,148],"well-known":[26],"method":[27,68],"to":[28,47,69,87,114,123,143],"reduce":[29,115],"the":[30,89,116,155],"computational":[31],"complexity":[32],"convolution":[34,96],"operations.":[35],"Unfortunately,":[36],"existing":[37],"implementations":[38],"this":[40,62],"either":[43],"vendor-specific":[44],"or":[45],"hard-coded":[46],"support":[48],"small":[50],"subset":[51],"convolutions,":[53],"thus":[54],"limiting":[55],"their":[56],"versatility":[57],"performance":[59,156],"portability.":[60],"In":[61],"paper,":[63],"we":[64,82,130,135],"propose":[65],"novel":[67],"optimize":[70],"Winograd":[71,95],"convolutions":[72],"based":[73],"on":[74],"symbolic":[75],"computation.":[76],"Taking":[77],"advantage":[78],"meta-programming":[79],"auto-tuning,":[81],"further":[83],"introduce":[84],"system":[86],"automate":[88],"generation":[90],"portable":[94],"code":[97],"for":[98],"various":[99],"GPUs.":[100],"We":[101],"show":[102],"that":[103,134],"our":[104,159],"optimization":[105],"technique":[106],"can":[107,136],"effectively":[108],"exploit":[109],"repetitive":[110],"patterns,":[111],"enabling":[112],"us":[113],"number":[117],"arithmetic":[119],"by":[121],"up":[122],"62%":[124],"without":[125],"compromising":[126],"numerical":[127],"stability.":[128],"Moreover,":[129],"demonstrate":[131],"in":[132],"experiments":[133],"generate":[137],"kernels":[139],"with":[140],"runtimes":[141],"close":[142],"deep-learning":[144],"libraries,":[145],"requiring":[146],"only":[147],"minimum":[149],"effort,":[152],"which":[153],"confirms":[154],"portability":[157],"approach.":[160]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}