{"id":"https://openalex.org/W3126707779","doi":"https://doi.org/10.1145/3394885.3431534","title":"Accelerate Non-unit Stride Convolutions with Winograd Algorithms","display_name":"Accelerate Non-unit Stride Convolutions with Winograd Algorithms","publication_year":2021,"publication_date":"2021-01-18","ids":{"openalex":"https://openalex.org/W3126707779","doi":"https://doi.org/10.1145/3394885.3431534","mag":"3126707779"},"language":"en","primary_location":{"id":"doi:10.1145/3394885.3431534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394885.3431534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","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/A5062919352","display_name":"Junhao Pan","orcid":"https://orcid.org/0000-0001-7156-6077"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junhao Pan","raw_affiliation_strings":["University of Illinois at Urbana Champaign, Urbana, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056321228","display_name":"Deming Chen","orcid":"https://orcid.org/0000-0002-3016-0270"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deming Chen","raw_affiliation_strings":["University of Illinois at Urbana Champaign, Urbana, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign, Urbana, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062919352"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.1528,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.79826797,"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":"358","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9937000274658203,"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":0.9937000274658203,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9807999730110168,"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/stride","display_name":"STRIDE","score":0.7918434143066406},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.675773561000824},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6706019639968872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6666786074638367},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6244185566902161},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6208075284957886},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.519901692867279},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5028313994407654},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48317041993141174},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.439158171415329},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4387635886669159},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2863231897354126},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.16969162225723267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16660624742507935},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15514922142028809},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.1043727695941925}],"concepts":[{"id":"https://openalex.org/C18007350","wikidata":"https://www.wikidata.org/wiki/Q7394815","display_name":"STRIDE","level":2,"score":0.7918434143066406},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.675773561000824},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6706019639968872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6666786074638367},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6244185566902161},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6208075284957886},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.519901692867279},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5028313994407654},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48317041993141174},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.439158171415329},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4387635886669159},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2863231897354126},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.16969162225723267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16660624742507935},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15514922142028809},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.1043727695941925},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394885.3431534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394885.3431534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1991706428","display_name":null,"funder_award_id":"2803.001","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"}],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W118713324","https://openalex.org/W1487564550","https://openalex.org/W1686810756","https://openalex.org/W1903029394","https://openalex.org/W1922123711","https://openalex.org/W1970032753","https://openalex.org/W2021944457","https://openalex.org/W2052867683","https://openalex.org/W2061171222","https://openalex.org/W2063922433","https://openalex.org/W2104451751","https://openalex.org/W2108019747","https://openalex.org/W2137966900","https://openalex.org/W2141597697","https://openalex.org/W2149239312","https://openalex.org/W2172654076","https://openalex.org/W2183341477","https://openalex.org/W2574797063","https://openalex.org/W2618530766","https://openalex.org/W2630837129","https://openalex.org/W2741455831","https://openalex.org/W2773042115","https://openalex.org/W2890071283","https://openalex.org/W2904795057","https://openalex.org/W2949650786","https://openalex.org/W2951460453","https://openalex.org/W2962856739","https://openalex.org/W2964010167","https://openalex.org/W2997109118","https://openalex.org/W3000160544","https://openalex.org/W3018618942","https://openalex.org/W3033033241","https://openalex.org/W3082569543","https://openalex.org/W4235465459","https://openalex.org/W4236601256","https://openalex.org/W4240188816","https://openalex.org/W4300096023","https://openalex.org/W4301336690","https://openalex.org/W6600263792","https://openalex.org/W6604409029","https://openalex.org/W6805632839","https://openalex.org/W6819060087"],"related_works":["https://openalex.org/W2963993660","https://openalex.org/W2989991345","https://openalex.org/W3127017759","https://openalex.org/W3045877795","https://openalex.org/W2024134184","https://openalex.org/W4297776043","https://openalex.org/W3006437870","https://openalex.org/W2971742398","https://openalex.org/W4283326721","https://openalex.org/W2799985340"],"abstract_inverted_index":{"While":[0],"computer":[1],"vision":[2],"tasks":[3],"target":[4],"increasingly":[5],"challenging":[6],"scenarios,":[7],"the":[8,45,50,67,80,99,109,121,132,140,149,155,158,166,169,196,200],"need":[9],"for":[10,85,148],"real-time":[11],"processing":[12],"of":[13,52,123,134,143,157,165,195],"images":[14],"rises":[15],"as":[16],"well,":[17],"requiring":[18],"more":[19],"efficient":[20],"methods":[21,34],"to":[22,38,65,78,101,113,130,176],"accelerate":[23,66],"convolutional":[24,105],"neural":[25],"networks.":[26],"For":[27,54],"unit":[28],"stride":[29,56,82,88,116,151],"convolutions,":[30,41,57],"we":[31,58,72,96,138,187],"use":[32],"FFT-based":[33],"and":[35,89,107,126,145,153],"Winograd":[36,93,110,160,197],"algorithms":[37,64,84,111,198],"compute":[39,114],"matrix":[40],"which":[42],"effectively":[43],"lower":[44],"computing":[46],"complexity":[47],"by":[48,128],"reducing":[49],"number":[51,142],"multiplications.":[53,179],"non-unit":[55,81,115,150],"usually":[59],"cannot":[60],"directly":[61],"apply":[62,108],"those":[63],"computations.":[68],"In":[69,180],"this":[70,124,135],"work,":[71],"propose":[73],"a":[74],"novel":[75],"universal":[76],"approach":[77,171],"construct":[79],"convolution":[83,202],"any":[86],"given":[87],"filter":[90],"sizes":[91],"from":[92,174],"algorithms.":[94,161],"Specifically,":[95],"first":[97],"demonstrate":[98],"steps":[100],"decompose":[102],"an":[103],"arbitrary":[104],"kernel":[106],"separately":[112],"convolutions.":[117],"We":[118],"then":[119],"present":[120],"derivation":[122],"method":[125],"proof":[127],"construction":[129],"confirm":[131],"validity":[133],"approach.":[136],"Finally,":[137],"discuss":[139],"minimum":[141],"multiplications":[144],"additions":[146],"necessary":[147],"convolutions":[152],"evaluate":[154],"performance":[156],"decomposed":[159],"From":[162],"our":[163,181],"analysis":[164],"computational":[167],"complexity,":[168],"new":[170],"can":[172],"benefit":[173],"1.5x":[175],"3x":[177],"fewer":[178],"experiments":[182],"in":[183,204],"real":[184],"DNN":[185],"layers,":[186],"have":[188],"acquired":[189],"around":[190],"1.3x":[191],"speedup":[192],"(Told":[193],"/Tnew)":[194],"against":[199],"conventional":[201],"algorithm":[203],"various":[205],"experiment":[206],"settings.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}