{"id":"https://openalex.org/W4413109814","doi":"https://doi.org/10.1109/lca.2025.3596970","title":"CABANA : Cluster-Aware Query Batching for Accelerating Billion-Scale ANNS With Intel AMX","display_name":"CABANA : Cluster-Aware Query Batching for Accelerating Billion-Scale ANNS With Intel AMX","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4413109814","doi":"https://doi.org/10.1109/lca.2025.3596970"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2025.3596970","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lca.2025.3596970","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/lca.2025.3596970","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002657848","display_name":"Minho Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minho Kim","raw_affiliation_strings":["Daegu Gyeongbuk Institute of Science &#x0026; Technology, Daegu, South Korea","DGIST, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0006-3604-3901","affiliations":[{"raw_affiliation_string":"Daegu Gyeongbuk Institute of Science &#x0026; Technology, Daegu, South Korea","institution_ids":["https://openalex.org/I193352282"]},{"raw_affiliation_string":"DGIST, Republic of Korea","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059787309","display_name":"Houxiang Ji","orcid":"https://orcid.org/0009-0008-8402-0127"},"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":"Houxiang Ji","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, IL, USA","University of Illinois Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0009-0008-8402-0127","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230358","display_name":"Jaeyoung Kang","orcid":null},"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":"Jaeyoung Kang","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, IL, USA","University of Illinois Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0009-0006-0023-743X","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035850620","display_name":"Hwanjun Lee","orcid":"https://orcid.org/0009-0001-0513-2112"},"institutions":[{"id":"https://openalex.org/I193352282","display_name":"Daegu Gyeongbuk Institute of Science and Technology","ror":"https://ror.org/03frjya69","country_code":"KR","type":"education","lineage":["https://openalex.org/I193352282"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwanjun Lee","raw_affiliation_strings":["Daegu Gyeongbuk Institute of Science &#x0026; Technology, Daegu, South Korea","DGIST, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-0513-2112","affiliations":[{"raw_affiliation_string":"Daegu Gyeongbuk Institute of Science &#x0026; Technology, Daegu, South Korea","institution_ids":["https://openalex.org/I193352282"]},{"raw_affiliation_string":"DGIST, Republic of Korea","institution_ids":["https://openalex.org/I193352282"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101885459","display_name":"Daehoon Kim","orcid":"https://orcid.org/0000-0003-0837-0877"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daehoon Kim","raw_affiliation_strings":["Yonsei University, Seoul, South Korea","Yonsei University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0837-0877","affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"Yonsei University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"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":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, IL, USA","University of Illinois Urbana-Champaign, USA"],"raw_orcid":"https://orcid.org/0000-0002-0442-5634","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7006,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73917433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"24","issue":"2","first_page":"289","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.8258000016212463,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.8258000016212463,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.7666000127792358,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.7271000146865845,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7925189733505249},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6122322082519531},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5848999619483948},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5135272145271301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925189733505249},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6122322082519531},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5848999619483948},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5135272145271301},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2025.3596970","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lca.2025.3596970","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/lca.2025.3596970","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lca.2025.3596970","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Computer Architecture Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2963265099","https://openalex.org/W4404931429","https://openalex.org/W4407197060","https://openalex.org/W4411486062"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"systems":[3],"increasingly":[4],"rely":[5],"on":[6,98],"Approximate":[7],"Nearest":[8],"Neighbor":[9],"Search":[10],"(ANNS)":[11],"to":[12,36,110],"efficiently":[13],"retrieve":[14],"relevant":[15],"context":[16],"from":[17],"billion-scale":[18,99],"vector":[19],"databases.":[20],"While":[21],"IVF-based":[22],"ANNS":[23],"frameworks":[24],"scale":[25],"well":[26],"overall,":[27],"the":[28,79],"fine":[29,87],"search":[30],"stage":[31],"remains":[32],"a":[33,52],"bottleneck":[34],"due":[35],"its":[37],"compute-intensive":[38],"GEMV":[39,69],"operations,":[40],"particularly":[41],"under":[42],"large":[43],"query":[44,54,114],"volumes.":[45],"To":[46],"address":[47],"this,":[48],"we":[49],"propose":[50],"<monospace>CABANA</monospace>,":[51],"<u>c</u>luster-<u>a</u>ware":[53],"<u>b</u>atching":[55],"for":[56],"<u>AN</u>NS":[57],"<u>a</u>cceleration":[58],"mechanism":[59],"using":[60],"Intel":[61],"Advanced":[62],"Matrix":[63],"Extensions":[64],"(AMX)":[65],"that":[66,102],"reformulates":[67],"these":[68],"computations":[70],"into":[71],"high-throughput":[72],"GEMM":[73],"operations.":[74],"By":[75],"aggregating":[76],"queries":[77],"targeting":[78],"same":[80],"clusters,":[81],"<monospace>CABANA</monospace>":[82,103],"enables":[83],"batched":[84],"computation":[85],"during":[86],"search,":[88],"significantly":[89],"improving":[90],"compute":[91],"intensity":[92],"and":[93],"memory":[94],"access":[95],"regularity.":[96],"Evaluations":[97],"datasets":[100],"show":[101],"outperforms":[104],"traditional":[105],"SIMD-based":[106],"implementations,":[107],"achieving":[108],"up":[109],"<inline-formula><tex-math":[111],"notation=\"LaTeX\">$32.6\\times$</tex-math></inline-formula>":[112],"higher":[113],"throughput":[115],"with":[116],"minimal":[117],"overhead,":[118],"while":[119],"maintaining":[120],"high":[121],"recall":[122],"rates.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
