{"id":"https://openalex.org/W4318328349","doi":"https://doi.org/10.1145/3559009.3569678","title":"Improving Convolution via Cache Hierarchy Tiling and Reduced Packing","display_name":"Improving Convolution via Cache Hierarchy Tiling and Reduced Packing","publication_year":2022,"publication_date":"2022-10-08","ids":{"openalex":"https://openalex.org/W4318328349","doi":"https://doi.org/10.1145/3559009.3569678"},"language":"en","primary_location":{"id":"doi:10.1145/3559009.3569678","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3559009.3569678","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569678","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569678","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010935709","display_name":"Victor Ferrari","orcid":"https://orcid.org/0000-0002-2051-2877"},"institutions":[{"id":"https://openalex.org/I4210148978","display_name":"Hospital de Cl\u00ednicas da Unicamp","ror":"https://ror.org/05g89bp20","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210148978"]},{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Victor Ferrari","raw_affiliation_strings":["UNICAMP, Campinas, Brazil"],"affiliations":[{"raw_affiliation_string":"UNICAMP, Campinas, Brazil","institution_ids":["https://openalex.org/I4210148978","https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056962045","display_name":"Rafael T. de Sousa","orcid":"https://orcid.org/0000-0003-1101-3029"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]},{"id":"https://openalex.org/I4210148978","display_name":"Hospital de Cl\u00ednicas da Unicamp","ror":"https://ror.org/05g89bp20","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210148978"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Sousa","raw_affiliation_strings":["UNICAMP, Campinas, Brazil"],"affiliations":[{"raw_affiliation_string":"UNICAMP, Campinas, Brazil","institution_ids":["https://openalex.org/I4210148978","https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104103748","display_name":"M\u00e1rcio Pereira","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148978","display_name":"Hospital de Cl\u00ednicas da Unicamp","ror":"https://ror.org/05g89bp20","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210148978"]},{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcio Pereira","raw_affiliation_strings":["UNICAMP, Campinas, Brazil"],"affiliations":[{"raw_affiliation_string":"UNICAMP, Campinas, Brazil","institution_ids":["https://openalex.org/I4210148978","https://openalex.org/I181391015"]}]},{"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, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","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, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067675731","display_name":"Guido Ara\u00fajo","orcid":"https://orcid.org/0000-0003-4869-5190"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]},{"id":"https://openalex.org/I4210148978","display_name":"Hospital de Cl\u00ednicas da Unicamp","ror":"https://ror.org/05g89bp20","country_code":"BR","type":"healthcare","lineage":["https://openalex.org/I4210148978"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guido Araujo","raw_affiliation_strings":["UNICAMP, Campinas, Brazil"],"affiliations":[{"raw_affiliation_string":"UNICAMP, Campinas, Brazil","institution_ids":["https://openalex.org/I4210148978","https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010935709"],"corresponding_institution_ids":["https://openalex.org/I181391015","https://openalex.org/I4210148978"],"apc_list":null,"apc_paid":null,"fwci":0.4084,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61421422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5785","issue":null,"first_page":"538","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9940000176429749,"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":0.7907121181488037},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6824437379837036},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6567889451980591},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6563330888748169},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6439723968505859},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.5413662195205688},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.49271467328071594},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.45271551609039307},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.40050914883613586},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38254931569099426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1662265956401825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1409693956375122},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.11213460564613342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907121181488037},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6824437379837036},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6567889451980591},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6563330888748169},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6439723968505859},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.5413662195205688},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.49271467328071594},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.45271551609039307},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.40050914883613586},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38254931569099426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1662265956401825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1409693956375122},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.11213460564613342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3559009.3569678","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3559009.3569678","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569678","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3559009.3569678","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1145/3559009.3569678","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3559009.3569678","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318328349.pdf","grobid_xml":"https://content.openalex.org/works/W4318328349.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2073061372","https://openalex.org/W4200342808","https://openalex.org/W4285060868"],"related_works":["https://openalex.org/W2274935188","https://openalex.org/W2538519144","https://openalex.org/W2546991807","https://openalex.org/W2730690135","https://openalex.org/W2109265242","https://openalex.org/W4311655071","https://openalex.org/W2147122795","https://openalex.org/W2167303720","https://openalex.org/W2144941482","https://openalex.org/W4239937081"],"abstract_inverted_index":{"Convolution":[0],"is":[1],"one":[2],"of":[3],"the":[4,15,49,61,82,89],"most":[5],"computationally":[6],"intensive":[7],"machine":[8,100],"learning":[9,101],"model":[10,102],"operations,":[11],"usually":[12],"solved":[13],"by":[14,33,63,104],"known":[16],"Im2Col":[17,30],"+":[18,31],"BLAS":[19,32],"method.":[20],"This":[21],"work":[22],"proposes":[23],"a":[24,37,54,67],"novel":[25],"convolution-algorithm":[26],"to":[27,59,72,87,106],"improve":[28],"upon":[29],"introducing":[34],"(a)":[35],"CSA:":[36],"convolution":[38,62],"specific":[39],"3D":[40],"cache-blocking":[41],"analysis":[42],"that":[43,56,70],"focuses":[44],"on":[45],"tile":[46],"reuse":[47],"over":[48],"cache":[50],"hierarchy,":[51],"(b)":[52],"CSO:":[53],"macro-kernel":[55],"follows":[57],"CSA":[58],"compute":[60],"tiling":[64,92],"it,":[65],"(c)":[66],"specialized":[68],"microkernel":[69],"seeks":[71],"achieve":[73],"peak":[74],"hardware":[75],"performance,":[76],"and":[77,85,93,108,112],"(d)":[78],"packing":[79],"routines":[80],"for":[81,110],"input":[83],"tensor":[84],"filters":[86],"bridge":[88],"gap":[90],"between":[91],"micro-kernel.":[94],"Our":[95],"approach":[96],"speeds":[97],"up":[98,105],"end-to-end":[99],"inference":[103],"26%":[107],"21%":[109],"x86":[111],"POWER10":[113],"architectures,":[114],"respectively.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
