{"id":"https://openalex.org/W7164503718","doi":"https://doi.org/10.1145/3770854.3780212","title":"Hitcher:Efficient GPU-based Vector Search via Cluster-Centric Kernel and Hitch-Ride Ordering","display_name":"Hitcher:Efficient GPU-based Vector Search via Cluster-Centric Kernel and Hitch-Ride Ordering","publication_year":2026,"publication_date":"2026-08-01","ids":{"openalex":"https://openalex.org/W7164503718","doi":"https://doi.org/10.1145/3770854.3780212"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://scholars.cityu.edu.hk/en/publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049112067","display_name":"Qihui Zhou","orcid":"https://orcid.org/0000-0003-2474-4197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Qihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085580462","display_name":"Changji Li","orcid":"https://orcid.org/0000-0003-2768-1224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Changji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008188402","display_name":"Guanxian Jiang","orcid":"https://orcid.org/0000-0001-9837-0904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Guanxian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138542205","display_name":"Chenhao Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138529525","display_name":"Xiao Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101217602","display_name":"Yu Mao","orcid":"https://orcid.org/0000-0002-7948-8138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Yu; id_orcid 0000-0001-9803-4927","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102930563","display_name":"Ming-Chang Yang","orcid":"https://orcid.org/0000-0002-4029-757X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ming-Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5113409160","display_name":"James Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, James","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.18289999663829803,"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":0.18289999663829803,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.14740000665187836,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.11029999703168869,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/kernel","display_name":"Kernel (algebra)","score":0.6363000273704529},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.628600001335144},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.5627999901771545},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5435000061988831},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.5123000144958496},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.4715999960899353},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4381999969482422},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4194999933242798},{"id":"https://openalex.org/keywords/vector-processor","display_name":"Vector processor","score":0.4189000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519999980926514},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6363000273704529},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5728999972343445},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.4715999960899353},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4381999969482422},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.4077000021934509},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C2779729312","wikidata":"https://www.wikidata.org/wiki/Q784232","display_name":"Query plan","level":5,"score":0.3763999938964844},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C172722865","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial query","level":5,"score":0.3531000018119812},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:pure.atira.dk:publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/7671bf91-c885-4d55-8c49-76e008f1d8b8","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Similarity-based":[0],"vector":[1,13,17,34,218],"search,":[2,24],"which":[3,160],"retrieves":[4],"the":[5,73,145,157,162,183,215],"most":[6],"similar":[7],"vectors":[8],"to":[9,38,68,72,81,99,112,126,141,173,182,185,201],"a":[10,15,82,97,137],"given":[11],"query":[12,51,110,153,166,205,210,219],"from":[14],"large":[16],"dataset,":[18],"underlies":[19],"many":[20],"applications":[21],"such":[22],"as":[23],"recommendation,":[25],"and":[26,53,79,131,190,207],"Large":[27],"Language":[28],"Models":[29],"(LLMs).":[30],"Some":[31],"systems":[32],"run":[33],"search":[35],"on":[36,144],"GPUs":[37],"enjoy":[39],"GPU's":[40],"high":[41],"parallelism,":[42],"but":[43,104],"we":[44,122],"observe":[45],"that":[46,197],"they":[47],"are":[48],"limited":[49],"in":[50,96],"throughput":[52,211],"latency.":[54],"In":[55],"particular,":[56],"their":[57,88],"query-centric":[58],"GPU":[59,74,84,133,139],"kernel":[60,140],"conducts":[61],"computation":[62,93,143,170,180],"independently":[63],"for":[64,94,114,148,165],"each":[65,109],"query,":[66],"failing":[67],"reuse":[69,127],"data":[70,102,128,147,188],"loaded":[71],"shared":[75],"memory":[76],"across":[77,129,171],"queries":[78,95,130,172],"leading":[80],"low":[83],"compute":[85],"utilization.":[86],"While":[87],"batch-based":[89],"task":[90],"reordering":[91],"rearranges":[92],"batch":[98,142],"reduce":[100,152,186],"CPU-GPU":[101,187],"transfer,":[103],"latency":[105,206],"is":[106],"prolonged":[107],"since":[108],"needs":[111],"wait":[113],"its":[115],"slowest":[116],"task.":[117],"To":[118,151],"tackle":[119],"these":[120],"problems,":[121],"propose":[123],"Hitcher.":[124],"Specifically,":[125],"improve":[132,174],"utilization,":[134],"Hitcher":[135,155,176,198],"implements":[136],"cluster-centric":[138],"same":[146],"multiple":[149,192],"queries.":[150],"latency,":[154],"adopts":[156],"hitch-ride":[158],"ordering,":[159],"preserves":[161],"arrival":[163],"order":[164],"processing":[167,220],"while":[168],"batching":[169],"efficiency.":[175],"can":[177],"also":[178],"offload":[179],"tasks":[181],"CPU":[184],"transfer":[189],"utilize":[191],"GPUs.":[193],"Experimental":[194],"results":[195],"show":[196],"achieves":[199],"up":[200],"22\u00d7":[202],"lower":[203],"P99":[204],"9\u00d7":[208],"higher":[209],"when":[212],"compared":[213],"with":[214],"state-of-the-art":[216],"GPU-based":[217],"systems.":[221],"\u00a9":[222],"2026":[223],"Owner/Author.":[224]},"counts_by_year":[],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2026-06-13T00:00:00"}