{"id":"https://openalex.org/W2072912074","doi":"https://doi.org/10.1109/icip.2013.6738436","title":"Communication-minimizing 2D convolution in GPU registers","display_name":"Communication-minimizing 2D convolution in GPU registers","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2072912074","doi":"https://doi.org/10.1109/icip.2013.6738436","mag":"2072912074"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2013.6738436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2013.6738436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5031485831","display_name":"Forrest Iandola","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Forrest N. Iandola","raw_affiliation_strings":["Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063801377","display_name":"David Sheffield","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Sheffield","raw_affiliation_strings":["Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104652429","display_name":"Michael J. Anderson","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Anderson","raw_affiliation_strings":["Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046321852","display_name":"Phitchaya Mangpo Phothilimthana","orcid":"https://orcid.org/0000-0003-3492-3690"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phitchaya Mangpo Phothilimthana","raw_affiliation_strings":["Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047285420","display_name":"Kurt Keutzer","orcid":"https://orcid.org/0000-0003-3868-8501"},"institutions":[{"id":"https://openalex.org/I4210131745","display_name":"Parallel Consulting (United States)","ror":"https://ror.org/03cssbw37","country_code":"US","type":"company","lineage":["https://openalex.org/I4210131745"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kurt Keutzer","raw_affiliation_strings":["Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Parallel Computing Laboratory (ParLab) University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I4210131745"]},{"raw_affiliation_string":"Parallel Comput. Lab. (ParLab), Univ. of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.663,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.88031853,"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":"2116","last_page":"2120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9991000294685364,"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":0.838276743888855},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6833714246749878},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5969254374504089},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.535031259059906},{"id":"https://openalex.org/keywords/very-long-instruction-word","display_name":"Very long instruction word","score":0.5227927565574646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2108215093612671},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10988417267799377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.838276743888855},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6833714246749878},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5969254374504089},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.535031259059906},{"id":"https://openalex.org/C170595534","wikidata":"https://www.wikidata.org/wiki/Q249743","display_name":"Very long instruction word","level":2,"score":0.5227927565574646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2108215093612671},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10988417267799377},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icip.2013.6738436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2013.6738436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.8051","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.8051","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.forrestiandola.com/PREPRINT_convolution_2d_gpu_registers.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.431.5730","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.431.5730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.forrestiandola.com/PREPRINT_convolution_2d_gpu_registers.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.46000000834465027,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W342164080","https://openalex.org/W1988057723","https://openalex.org/W1989988531","https://openalex.org/W2000873501","https://openalex.org/W2063186542","https://openalex.org/W2115148068","https://openalex.org/W2128853364","https://openalex.org/W2129170915","https://openalex.org/W2144085134","https://openalex.org/W2145194992","https://openalex.org/W2151103935","https://openalex.org/W2161969291","https://openalex.org/W3141650078","https://openalex.org/W4246028237","https://openalex.org/W4253426709","https://openalex.org/W6681616147"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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/W2211967836","https://openalex.org/W1991993901"],"abstract_inverted_index":{"2D":[0],"image":[1,6,34,53,66],"convolution":[2,35,62,89,106],"is":[3,18,49],"ubiquitous":[4],"in":[5],"processing":[7],"and":[8,70,99],"computer":[9],"vision":[10],"problems":[11],"such":[12,32,42],"as":[13,33,43],"feature":[14],"extraction.":[15],"Exploiting":[16],"parallelism":[17],"a":[19,88],"common":[20],"strategy":[21],"for":[22],"accelerating":[23,52],"convolution.":[24,54],"Parallel":[25],"processors":[26,41],"keep":[27],"getting":[28],"faster,":[29],"but":[30,111],"algorithms":[31],"remain":[36],"memory":[37,47,57,97],"bounded":[38],"on":[39,105,122,127],"parallel":[40],"GPUs.":[44],"Therefore,":[45],"reducing":[46],"communication":[48],"fundamental":[50],"to":[51,64,68,83,117,134],"To":[55,80],"reduce":[56],"communication,":[58],"we":[59,71,86],"reorganize":[60],"the":[61,93],"algorithm":[63],"prefetch":[65],"regions":[67],"register,":[69],"do":[72],"more":[73],"work":[74],"per":[75],"thread":[76],"with":[77,107],"fewer":[78],"threads.":[79],"enable":[81],"portability":[82],"future":[84],"architectures,":[85],"implement":[87],"autotuner":[90],"that":[91],"sweeps":[92],"design":[94],"space":[95],"of":[96],"layouts":[98],"loop":[100],"unrolling":[101],"configurations.":[102],"We":[103],"focus":[104],"small":[108],"filters":[109],"(2\u00d72-7\u00d77),":[110],"our":[112,125],"techniques":[113],"can":[114],"be":[115],"extended":[116],"larger":[118],"filter":[119,123],"sizes.":[120],"Depending":[121],"size,":[124],"speedups":[126],"two":[128],"NVIDIA":[129],"architectures":[130],"range":[131],"from":[132],"1.2\u00d7":[133],"4.5\u00d7":[135],"over":[136],"state-of-the-art":[137],"GPU":[138],"libraries.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
