{"id":"https://openalex.org/W4311119077","doi":"https://doi.org/10.1145/3570305","title":"YaConv: Convolution with Low Cache Footprint","display_name":"YaConv: Convolution with Low Cache Footprint","publication_year":2022,"publication_date":"2022-12-02","ids":{"openalex":"https://openalex.org/W4311119077","doi":"https://doi.org/10.1145/3570305"},"language":"en","primary_location":{"id":"doi:10.1145/3570305","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570305","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570305","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/10.1145/3570305","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009484614","display_name":"Ivan Korostelev","orcid":"https://orcid.org/0000-0002-3451-1920"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ivan Korostelev","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3451-1920","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090480187","display_name":"Jo\u00e3o P. L. de Carvalho","orcid":"https://orcid.org/0000-0002-3476-184X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o P. L. De Carvalho","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3476-184X","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055326969","display_name":"Jos\u00e9 E. Moreira","orcid":"https://orcid.org/0000-0001-7029-6327"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Moreira","raw_affiliation_strings":["IBM Research, Yorktown Heights, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-7029-6327","affiliations":[{"raw_affiliation_string":"IBM Research, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048554669","display_name":"Jos\u00e9 Nelson Amaral","orcid":"https://orcid.org/0000-0002-9943-1809"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Nelson Amaral","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":"https://orcid.org/0000-0002-9943-1809","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009484614"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.0148,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77458134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9973999857902527,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"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":0.8785752654075623},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7510755062103271},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6894485950469971},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6870487332344055},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6730179190635681},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.53862464427948},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.5045143365859985},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5015444755554199},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.49603208899497986},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4687390923500061},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36287063360214233},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35062482953071594},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3287760615348816},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18440935015678406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1399204134941101}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8785752654075623},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7510755062103271},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6894485950469971},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6870487332344055},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6730179190635681},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.53862464427948},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.5045143365859985},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5015444755554199},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.49603208899497986},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4687390923500061},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36287063360214233},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35062482953071594},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3287760615348816},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18440935015678406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1399204134941101},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3570305","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570305","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570305","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:10.1145/3570305","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3570305","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3570305","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/W4311119077.pdf","grobid_xml":"https://content.openalex.org/works/W4311119077.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1983157164","https://openalex.org/W2043275593","https://openalex.org/W2073061372","https://openalex.org/W2172654076","https://openalex.org/W2516525699","https://openalex.org/W2578027111","https://openalex.org/W2790601347","https://openalex.org/W2951894856","https://openalex.org/W3042343931","https://openalex.org/W3046538393","https://openalex.org/W3093756531","https://openalex.org/W3093772369","https://openalex.org/W3096395190","https://openalex.org/W3119880013","https://openalex.org/W3122286897","https://openalex.org/W3123054690","https://openalex.org/W3156745629","https://openalex.org/W4212774754","https://openalex.org/W4224612674","https://openalex.org/W4256261874"],"related_works":["https://openalex.org/W4221139464","https://openalex.org/W4289827464","https://openalex.org/W2350686196","https://openalex.org/W2061075966","https://openalex.org/W3147501184","https://openalex.org/W4230093848","https://openalex.org/W2147122795","https://openalex.org/W4236020707","https://openalex.org/W2167303720","https://openalex.org/W1593732971"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"YaConv":[3,63],",":[4],"a":[5,15,32,121,139,154],"new":[6,105],"algorithm":[7],"to":[8,53,92,108,113],"compute":[9],"convolution":[10],"using":[11],"GEMM":[12,50,89],"microkernels":[13],"from":[14,135],"Basic":[16],"Linear":[17],"Algebra":[18],"Subprograms":[19],"library":[20],"that":[21],"is":[22,82],"efficient":[23,123],"for":[24,38,48],"multiple":[25],"CPU":[26],"architectures.":[27],"Previous":[28],"approaches":[29],"either":[30],"create":[31],"copy":[33],"of":[34,56,76,87,103,125,156],"each":[35,39,49,65],"image":[36,58,66,81],"element":[37,41,67],"filter":[40],"or":[42],"reload":[43],"these":[44,77],"elements":[45,59],"into":[46,69],"cache":[47,71,161],"call,":[51],"leading":[52],"redundant":[54],"instances":[55],"the":[57,70,74,88,93,97,114,126],"in":[60,96,111,159],"cache.":[61],"Instead,":[62],"loads":[64],"once":[68],"and":[72,163],"maximizes":[73],"reuse":[75],"elements.":[78],"The":[79,100,129],"output":[80,98],"computed":[83],"by":[84],"scattering":[85],"results":[86],"microkernel":[90],"calls":[91],"correct":[94],"locations":[95],"image.":[99],"main":[101],"advantage":[102],"this":[104],"algorithm\u2014which":[106],"leads":[107],"better":[109],"performance":[110,151],"comparison":[112],"existing":[115],"im2col":[116,148],"approach":[117],"on":[118,132],"several":[119],"architectures\u2014is":[120],"more":[122],"use":[124],"memory":[127],"hierarchy.":[128],"experimental":[130],"evaluation":[131],"convolutional":[133],"layers":[134],"PyTorch,":[136],"along":[137],"with":[138],"parameterized":[140],"study,":[141],"indicates":[142],"an":[143],"average":[144],"24%":[145],"speedup":[146],"over":[147],"convolution.":[149],"Increased":[150],"comes":[152],"as":[153],"result":[155],"3\u00d7":[157],"reduction":[158],"L3":[160],"accesses":[162],"2\u00d7":[164],"fewer":[165],"branch":[166],"instructions.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}