{"id":"https://openalex.org/W4386710522","doi":"https://doi.org/10.1145/3616873","title":"CHIP-KNNv2: A<u>C</u>onfigurable and<u>Hi</u>gh-<u>P</u>erformance<u>K</u>-<u>N</u>earest<u>N</u>eighbors Accelerator on HBM-based FPGAs","display_name":"CHIP-KNNv2: A<u>C</u>onfigurable and<u>Hi</u>gh-<u>P</u>erformance<u>K</u>-<u>N</u>earest<u>N</u>eighbors Accelerator on HBM-based FPGAs","publication_year":2023,"publication_date":"2023-09-13","ids":{"openalex":"https://openalex.org/W4386710522","doi":"https://doi.org/10.1145/3616873"},"language":"en","primary_location":{"id":"doi:10.1145/3616873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3616873","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"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 Reconfigurable Technology and Systems","raw_type":"journal-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/A5004089365","display_name":"Kenneth Liu","orcid":"https://orcid.org/0009-0002-1348-6583"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kenneth Liu","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0009-0002-1348-6583","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067662998","display_name":"Alec Lu","orcid":"https://orcid.org/0000-0002-3315-7368"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Alec Lu","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0000-0002-3315-7368","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032269879","display_name":"Kartik Samtani","orcid":"https://orcid.org/0009-0000-6309-7995"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kartik Samtani","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0009-0000-6309-7995","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065889904","display_name":"Zhenman Fang","orcid":"https://orcid.org/0000-0003-0603-9697"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhenman Fang","raw_affiliation_strings":["School of Engineering Science, Simon Fraser University, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0603-9697","affiliations":[{"raw_affiliation_string":"School of Engineering Science, Simon Fraser University, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032647120","display_name":"Licheng Guo","orcid":"https://orcid.org/0000-0002-0705-9510"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Licheng Guo","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, United States"],"raw_orcid":"https://orcid.org/0000-0002-0705-9510","affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, United States","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8982,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76608164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"16","issue":"4","first_page":"1","last_page":"26"},"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":0.9995999932289124,"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":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.995199978351593,"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":0.8106193542480469},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.639171838760376},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6184426546096802},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4720745086669922},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4718855619430542},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24889326095581055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106193542480469},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.639171838760376},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6184426546096802},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4720745086669922},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4718855619430542},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24889326095581055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3616873","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3616873","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"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 Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6110381416","display_name":"Intelligent Computing Memory Systems for Data-Intensive Applications_x000d_","funder_award_id":"552042-2020","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G832689143","display_name":null,"funder_award_id":"RGPIN-2019","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322551","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320335271","display_name":"British Columbia Knowledge Development Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1518139028","https://openalex.org/W1985258161","https://openalex.org/W2028960610","https://openalex.org/W2047207335","https://openalex.org/W2073137766","https://openalex.org/W2080592089","https://openalex.org/W2087158689","https://openalex.org/W2124592110","https://openalex.org/W2136132422","https://openalex.org/W2142827986","https://openalex.org/W2157234796","https://openalex.org/W2249264440","https://openalex.org/W2427881153","https://openalex.org/W2559192460","https://openalex.org/W2626616508","https://openalex.org/W2807808525","https://openalex.org/W2886589913","https://openalex.org/W2896983500","https://openalex.org/W2913535816","https://openalex.org/W2979602826","https://openalex.org/W2993580201","https://openalex.org/W2998702515","https://openalex.org/W3006389481","https://openalex.org/W3012047118","https://openalex.org/W3101568187","https://openalex.org/W3133395503","https://openalex.org/W3162360055","https://openalex.org/W3179878372","https://openalex.org/W4210859512","https://openalex.org/W4213187929","https://openalex.org/W4280568654","https://openalex.org/W4304140717"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W1980160788","https://openalex.org/W2148915962","https://openalex.org/W2283866686","https://openalex.org/W4287182096","https://openalex.org/W27867058"],"abstract_inverted_index":{"The":[0],"k-nearest":[1],"neighbors":[2,157],"(KNN)":[3],"algorithm":[4,8],"is":[5,121],"an":[6,95,202,230,334],"essential":[7,125],"in":[9,25,128,189],"many":[10],"applications,":[11],"such":[12,112],"as":[13,113],"similarity":[14],"search,":[15],"image":[16],"classification,":[17],"and":[18,29,42,73,92,98,141,152,167,179,200,219,223,256],"database":[19],"query.":[20],"With":[21],"the":[22,26,30,51,56,66,104,114,129,132,135,138,149,153,169,185,211,216,221,239,252,257,262,270,313],"rapid":[23],"growth":[24],"dataset":[27],"size":[28,133],"feature":[31,139],"dimension":[32,140],"of":[33,53,134,145,155,162,238,287,293,338,343],"each":[34,146],"data":[35,142,147],"point,":[36,148],"processing":[37],"KNN":[38,54,100,240],"becomes":[39],"more":[40],"compute":[41],"memory":[43,67,106,224],"hungry.":[44],"Most":[45],"prior":[46],"studies":[47],"focus":[48],"on":[49,60,70,108,261,269,326],"accelerating":[50],"computation":[52,222],"using":[55],"abundant":[57],"parallel":[58],"resource":[59],"FPGAs.":[61],"However,":[62],"they":[63],"often":[64],"overlook":[65],"access":[68,107,225],"optimizations":[69],"FPGA":[71,118,264],"platforms":[72],"only":[74],"achieve":[75],"a":[76,80,235,277,283,290,327],"marginal":[77],"speedup":[78,286,292,305],"over":[79,306],"multi-thread":[81],"CPU":[82,279],"implementation":[83,324],"for":[84,123,251],"large":[85],"datasets.":[86],"In":[87,160],"this":[88],"article,":[89],"we":[90,165,183,227,296],"design":[91,163,173,217,255],"implement":[93,193],"CHIP-KNN:":[94],"HLS-based,":[96],"configurable,":[97],"high-performance":[99],"accelerator.":[101],"CHIP-KNN":[102,120],"optimizes":[103],"off-chip":[105],"modern":[109],"HBM-based":[110,263],"FPGAs":[111],"AMD/Xilinx":[115],"Alveo":[116,271],"U280":[117,272],"board.":[119],"configurable":[122],"all":[124],"parameters":[126],"used":[127],"algorithm,":[130],"including":[131],"search":[136],"dataset,":[137],"type":[143],"representation":[144],"distance":[150],"metric,":[151],"number":[154],"nearest":[156],"-":[158],"K.":[159],"terms":[161],"architecture,":[164],"explore":[166,215],"discuss":[168],"tradeoffs":[170],"between":[171],"two":[172],"versions:":[174],"CHIP-KNNv1":[175,307],"(Ping-Pong":[176],"buffer":[177],"based)":[178],"CHIP-KNNv2":[180,281,299,332],"(streaming-based).":[181],"Moreover,":[182],"investigate":[184],"routing":[186],"congestion":[187],"issue":[188],"our":[190,242],"accelerator":[191,254],"design,":[192],"hierarchical":[194],"structures":[195],"to":[196,209,276,302],"shorten":[197],"critical":[198],"paths,":[199],"integrate":[201],"open-source":[203],"floorplanning":[204],"optimization":[205],"tool":[206,243],"called":[207],"TAPA/AutoBridge":[208],"eliminate":[210],"place-and-route":[212],"issues.":[213],"To":[214],"space":[218],"balance":[220],"performance,":[226],"also":[228],"build":[229],"analytical":[231],"performance":[232,285,304],"model.":[233],"Given":[234],"user":[236],"configuration":[237],"parameters,":[241],"can":[244],"automatically":[245],"generate":[246],"TAPA":[247],"HLS":[248],"C":[249],"code":[250],"optimal":[253],"corresponding":[258],"host":[259],"code,":[260],"platform.":[265],"Our":[266],"experimental":[267],"results":[268],"show":[273,297],"that,":[274],"compared":[275],"48-thread":[278],"implementation,":[280],"achieves":[282,300,333],"geomean":[284],"15\u00d7,":[288],"with":[289,312],"maximum":[291],"45\u00d7.":[294],"Additionally,":[295],"that":[298],"up":[301],"2.1\u00d7":[303],"while":[308,340],"increasing":[309],"configurability.":[310],"Compared":[311],"state-of-the-art":[314],"Facebook":[315],"AI":[316],"Similarity":[317],"Search":[318],"(FAISS)":[319],"[":[320],"23":[321],"]":[322],"GPU":[323,344],"running":[325],"Nvidia":[328],"Tesla":[329],"V100":[330],"GPU,":[331],"average":[335],"latency":[336],"reduction":[337],"30.6\u00d7":[339],"requiring":[341],"34.3%":[342],"power":[345],"consumption.":[346]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}