{"id":"https://openalex.org/W4411485933","doi":"https://doi.org/10.1145/3695053.3731089","title":"HeterRAG: Heterogeneous Processing-in-Memory Acceleration for Retrieval-augmented Generation","display_name":"HeterRAG: Heterogeneous Processing-in-Memory Acceleration for Retrieval-augmented Generation","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4411485933","doi":"https://doi.org/10.1145/3695053.3731089"},"language":"en","primary_location":{"id":"doi:10.1145/3695053.3731089","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731089","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731089","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731089","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049903291","display_name":"Chaoqiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoqiang Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-2180-5428","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115053629","display_name":"Haifeng Liu","orcid":"https://orcid.org/0000-0003-3319-254X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Liu","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-3319-254X","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564451","display_name":"Dan Chen","orcid":"https://orcid.org/0000-0003-4158-5239"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dan Chen","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4158-5239","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052025786","display_name":"Yu Huang","orcid":"https://orcid.org/0000-0002-3927-1102"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Huang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3927-1102","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115053642","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-1845-0160"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-1845-0160","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045486208","display_name":"Wenjing Xiao","orcid":"https://orcid.org/0000-0002-8231-2467"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjing Xiao","raw_affiliation_strings":["Guangxi University, Nanning, China"],"raw_orcid":"https://orcid.org/0000-0002-8231-2467","affiliations":[{"raw_affiliation_string":"Guangxi University, Nanning, China","institution_ids":["https://openalex.org/I150807315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022398389","display_name":"Xiaofei Liao","orcid":"https://orcid.org/0000-0001-6302-813X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Liao","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0001-6302-813X","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3934-7605","affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8954,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98252544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"884","last_page":"898"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648192644119263},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.7072131633758545}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648192644119263},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7072131633758545},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3695053.3731089","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731089","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731089","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3695053.3731089","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3695053.3731089","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3695053.3731089","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7794448185","display_name":null,"funder_award_id":"2023YFB4503400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411485933.pdf","grobid_xml":"https://content.openalex.org/works/W4411485933.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1977182282","https://openalex.org/W2024668293","https://openalex.org/W2034861439","https://openalex.org/W2113235308","https://openalex.org/W2118269922","https://openalex.org/W2251818205","https://openalex.org/W2252136820","https://openalex.org/W2725159389","https://openalex.org/W2912924812","https://openalex.org/W2962985038","https://openalex.org/W2963265099","https://openalex.org/W2963284996","https://openalex.org/W2963339397","https://openalex.org/W2963469388","https://openalex.org/W2979719709","https://openalex.org/W3029693508","https://openalex.org/W3042598257","https://openalex.org/W3043023836","https://openalex.org/W3100710793","https://openalex.org/W3134274954","https://openalex.org/W3156789018","https://openalex.org/W3157531038","https://openalex.org/W3189166979","https://openalex.org/W3196481040","https://openalex.org/W3207399097","https://openalex.org/W4221001402","https://openalex.org/W4240046008","https://openalex.org/W4280496502","https://openalex.org/W4280509186","https://openalex.org/W4280568654","https://openalex.org/W4285504044","https://openalex.org/W4308479188","https://openalex.org/W4317898419","https://openalex.org/W4319870497","https://openalex.org/W4321636588","https://openalex.org/W4327503237","https://openalex.org/W4380875717","https://openalex.org/W4380881178","https://openalex.org/W4385570777","https://openalex.org/W4385571271","https://openalex.org/W4387835442","https://openalex.org/W4388778348","https://openalex.org/W4389491850","https://openalex.org/W4392427708","https://openalex.org/W4392806438","https://openalex.org/W4394998968","https://openalex.org/W4394999021","https://openalex.org/W4395073431","https://openalex.org/W4395106409","https://openalex.org/W4400909749","https://openalex.org/W4401720589","https://openalex.org/W4402671542","https://openalex.org/W4404534210","https://openalex.org/W4408848702"],"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":{"By":[0],"integrating":[1],"external":[2],"knowledge":[3,111],"bases,":[4,112],"Retrieval-augmented":[5],"Generation":[6],"(RAG)":[7],"enhances":[8],"natural":[9],"language":[10],"generation":[11,53],"for":[12,155],"knowledgeintensive":[13],"scenarios":[14],"and":[15,25,35,47,127],"specialized":[16],"domains,":[17],"producing":[18],"content":[19],"that":[20,141],"is":[21,55,124],"both":[22,125],"more":[23],"informative":[24],"personalized.RAG":[26],"systems":[27],"typically":[28],"consist":[29],"of":[30,69],"two":[31,75],"fundamental":[32],"stages:":[33],"retrieval":[34,37,98],"generation.The":[36],"stage":[38,54,99],"experiences":[39],"low":[40],"bandwidth":[41,60],"utilization":[42],"due":[43,104],"to":[44,79,90,105,108,129],"its":[45],"random":[46],"irregular":[48],"memory":[49,59,80],"access":[50],"patterns.Meanwhile,":[51],"the":[52,97,106,131],"also":[56],"constrained":[57],"by":[58],"limitations,":[61],"which":[62],"arise":[63],"from":[64],"involving":[65],"a":[66,115,137,149],"significant":[67],"number":[68],"General":[70],"Matrix-Vector":[71],"Multiplications":[72],"(GEMV)":[73],"operations.These":[74],"stages":[76],"collectively":[77],"lead":[78],"bottlenecks":[81],"within":[82],"RAG":[83,123],"systems.Recent":[84],"efforts":[85],"leverage":[86],"HBM-based":[87,120],"Processing-in-Memory":[88],"(PIM)":[89],"accelerate":[91],"conventional":[92],"Large":[93],"Language":[94],"Models":[95],"(LLMs).However,":[96],"incurs":[100],"substantial":[101],"storage":[102],"overhead":[103],"need":[107],"maintain":[109],"large-scale":[110],"resulting":[113],"in":[114,122],"capacity":[116,132],"bottleneck.Solely":[117],"relying":[118],"on":[119],"PIM":[121,135,152],"costly":[126],"insufficient":[128],"meet":[130],"demands.Fortunately,":[133],"DIMM-based":[134],"provides":[136],"low-cost,":[138],"high-capacity":[139],"alternative":[140],"complements":[142],"HBM.In":[143],"this":[144],"work,":[145],"we":[146],"propose":[147],"HeterRAG,":[148],"novel":[150],"heterogeneous":[151],"acceleration":[153],"system":[154],"RAG.It":[156],"combines":[157]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
