{"id":"https://openalex.org/W3204958249","doi":"https://doi.org/10.1145/3472456.3473520","title":"Exploring HW/SW Co-Optimizations for Accelerating Large-scale Texture Identification on Distributed GPUs","display_name":"Exploring HW/SW Co-Optimizations for Accelerating Large-scale Texture Identification on Distributed GPUs","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3204958249","doi":"https://doi.org/10.1145/3472456.3473520","mag":"3204958249"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3473520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3473520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","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/A5066266521","display_name":"Junsong Wang","orcid":"https://orcid.org/0000-0002-8935-4969"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Junsong Wang","raw_affiliation_strings":["V-Origin, China"],"affiliations":[{"raw_affiliation_string":"V-Origin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330729","display_name":"Xiaofan Zhang","orcid":"https://orcid.org/0000-0001-5081-3972"},"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":"Xiaofan Zhang","raw_affiliation_strings":["Unviversity of Illinois at Urbana-Champaign, United States of America"],"affiliations":[{"raw_affiliation_string":"Unviversity of Illinois at Urbana-Champaign, United States of America","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100690995","display_name":"Yubo Li","orcid":"https://orcid.org/0000-0003-0455-0969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yubo Li","raw_affiliation_strings":["V-Origin, China"],"affiliations":[{"raw_affiliation_string":"V-Origin, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000419795","display_name":"Yonghua Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghua Lin","raw_affiliation_strings":["V-Origin, China"],"affiliations":[{"raw_affiliation_string":"V-Origin, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066266521"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.49714052,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9970999956130981,"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":0.9937999844551086,"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":0.8475006818771362},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6787151098251343},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6365737318992615},{"id":"https://openalex.org/keywords/texture-memory","display_name":"Texture memory","score":0.5666460394859314},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.49790024757385254},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4769552946090698},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.45060136914253235},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4216330051422119},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.41741621494293213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.283853143453598},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15142405033111572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475006818771362},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6787151098251343},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6365737318992615},{"id":"https://openalex.org/C18766215","wikidata":"https://www.wikidata.org/wiki/Q7708532","display_name":"Texture memory","level":5,"score":0.5666460394859314},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.49790024757385254},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4769552946090698},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.45060136914253235},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4216330051422119},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.41741621494293213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.283853143453598},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15142405033111572},{"id":"https://openalex.org/C109772839","wikidata":"https://www.wikidata.org/wiki/Q2297645","display_name":"Software rendering","level":4,"score":0.0},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C66629338","wikidata":"https://www.wikidata.org/wiki/Q189177","display_name":"3D computer graphics","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472456.3473520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3473520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1588043677","https://openalex.org/W2006516328","https://openalex.org/W2028960610","https://openalex.org/W2087475904","https://openalex.org/W2122621634","https://openalex.org/W2124386111","https://openalex.org/W2124509324","https://openalex.org/W2128237624","https://openalex.org/W2151103935","https://openalex.org/W2161597143","https://openalex.org/W2899915146","https://openalex.org/W2964157791","https://openalex.org/W2974412363","https://openalex.org/W2998702515","https://openalex.org/W3023742835","https://openalex.org/W3037844041","https://openalex.org/W3047057232","https://openalex.org/W3173798785","https://openalex.org/W3177525997","https://openalex.org/W4245551996","https://openalex.org/W6678775411"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W4389157309","https://openalex.org/W3204958249"],"abstract_inverted_index":{"Texture":[0],"identification":[1,86,115,216,259],"has":[2,25],"been":[3],"developed":[4],"recently":[5],"to":[6,29,54,106,138,164,186,211,243],"support":[7,17,55],"one-to-one":[8],"verification":[9],"and":[10,79,82,104,111,176,226,235],"one-to-many":[11],"search,":[12],"which":[13,147,267],"provides":[14],"much":[15],"broader":[16],"than":[18],"texture":[19,37,58,69,85,114,197,215,258,271],"classification":[20],"in":[21,274],"real-life":[22],"applications.":[23],"It":[24],"demonstrated":[26],"great":[27],"potentials":[28],"enable":[30],"product":[31],"traceability":[32],"by":[33,171,254],"identifying":[34],"the":[35,40,43,62,66,157,167,188,200,208,221],"unique":[36],"information":[38],"on":[39,217],"surface":[41],"of":[42,68,195,202],"targeted":[44,158],"objects.":[45],"However,":[46],"existing":[47],"hardware":[48,103,225],"acceleration":[49,110],"schemes":[50],"are":[51],"not":[52],"enough":[53],"a":[56,94,123,134,149,161,244,256],"large-scale":[57,113,214],"identification,":[59],"especially":[60],"for":[61,127,142,191],"search":[63,234],"task,":[64],"where":[65],"number":[67],"images":[70],"being":[71],"searched":[72],"can":[73,229,268],"reach":[74],"millions,":[75],"creating":[76],"enormous":[77],"compute":[78,174],"memory":[80,141,153,177,189],"demands":[81],"making":[83],"real-time":[84,117,213],"infeasible.":[87],"To":[88,199],"address":[89],"these":[90],"problems,":[91],"we":[92,228],"propose":[93],"comprehensive":[95],"toolset":[96],"with":[97,116,261],"jointly":[98],"optimization":[99],"strategies":[100],"from":[101,223],"both":[102,224],"software":[105],"deliver":[107,230],"optimized":[108],"GPU":[109],"leverage":[112],"responses.":[118],"Novel":[119],"technologies":[120],"include:":[121],"1)":[122],"highly-optimized":[124],"cuBLAS":[125],"implementation":[126,210],"efficiently":[128],"running":[129,156],"2-nearest":[130],"neighbors":[131],"algorithm;":[132],"2)":[133],"hybrid":[135],"cache":[136,240],"design":[137],"incorporate":[139],"host":[140],"streaming":[143],"data":[144,168],"toward":[145],"GPUs,":[146],"delivers":[148],"5":[150],"\u00d7":[151,232,237],"larger":[152,238],"capacity":[154,241],"while":[155],"workloads;":[159],"3)":[160],"batch":[162],"process":[163],"fully":[165],"exploit":[166],"reuse":[169],"opportunities":[170],"considering":[172],"available":[173],"resources":[175],"bandwidth":[178],"constraints.":[179],"4)":[180],"an":[181],"asymmetric":[182],"local":[183],"feature":[184,193,239],"extraction":[185],"reduce":[187],"footprint":[190],"keeping":[192],"matrices":[194],"reference":[196],"images.":[198],"best":[201],"our":[203,251],"knowledge,":[204],"this":[205],"work":[206],"is":[207],"first":[209],"provide":[212],"GPUs.":[218],"By":[219],"exploring":[220],"co-optimizations":[222],"software,":[227],"31":[231],"faster":[233],"20":[236],"compared":[242],"conventional":[245],"CUDA":[246],"implementation.":[247],"We":[248],"also":[249],"demonstrate":[250],"proposed":[252],"designs":[253],"proposing":[255],"distributed":[257],"system":[260],"14":[262],"Nvidia":[263],"Tesla":[264],"P100":[265],"GPUs":[266],"complete":[269],"872,984":[270],"similarity":[272],"comparisons":[273],"just":[275],"one":[276],"second.":[277]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}