{"id":"https://openalex.org/W7165173595","doi":"https://doi.org/10.1145/3787109.3815268","title":"HeteroRAGCache: Software-Hardware Co-Design for Efficient RAG Caching using Emerging Memories","display_name":"HeteroRAGCache: Software-Hardware Co-Design for Efficient RAG Caching using Emerging Memories","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165173595","doi":"https://doi.org/10.1145/3787109.3815268"},"language":null,"primary_location":{"id":"doi:10.1145/3787109.3815268","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815268","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787109.3815268","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062183971","display_name":"J. Park","orcid":null},"institutions":[{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jangseon Park","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0009-0005-3508-3859","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I160856358","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138866564","display_name":"Kiseok Suh","orcid":"https://orcid.org/0009-0004-0198-2613"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kiseok Suh","raw_affiliation_strings":["Foundry Business Division, Samsung Electronics, Suwon, gyeonggi-do, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0004-0198-2613","affiliations":[{"raw_affiliation_string":"Foundry Business Division, Samsung Electronics, Suwon, gyeonggi-do, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082759711","display_name":"Flavio Ponzina","orcid":"https://orcid.org/0000-0002-9662-498X"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Flavio Ponzina","raw_affiliation_strings":["Electrical and Computer Engineering, San Diego State University, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9662-498X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, San Diego State University, San Diego, CA, USA","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025573294","display_name":"Tajana Rosing","orcid":"https://orcid.org/0000-0002-6954-997X"},"institutions":[{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tajana Rosing","raw_affiliation_strings":["Computer Science and Engineering, University of California San Diego, San Diego, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6954-997X","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of California San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I160856358","https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"743","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.41749998927116394,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.41749998927116394,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.07429999858140945,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.05380000174045563,"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/dram","display_name":"Dram","score":0.7088000178337097},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6140000224113464},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.585099995136261},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5180000066757202},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4936999976634979},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.36500000953674316},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.33160001039505005},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.32919999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391000032424927},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7088000178337097},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6140000224113464},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5180000066757202},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.32919999957084656},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C194080101","wikidata":"https://www.wikidata.org/wiki/Q46306","display_name":"Access time","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C5165142","wikidata":"https://www.wikidata.org/wiki/Q5432732","display_name":"False sharing","level":5,"score":0.2694000005722046},{"id":"https://openalex.org/C101722063","wikidata":"https://www.wikidata.org/wiki/Q218825","display_name":"Random access","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787109.3815268","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815268","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3787109.3815268","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815268","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2280557500","https://openalex.org/W2549127863","https://openalex.org/W2963963993","https://openalex.org/W3034383590","https://openalex.org/W3067010295","https://openalex.org/W3099700870","https://openalex.org/W3120797592","https://openalex.org/W3134756900","https://openalex.org/W3142875983","https://openalex.org/W3144700726","https://openalex.org/W3156789018","https://openalex.org/W3161820423","https://openalex.org/W4205436102","https://openalex.org/W4306938157","https://openalex.org/W4360606093","https://openalex.org/W4385573898","https://openalex.org/W4388094051","https://openalex.org/W4392553413","https://openalex.org/W4393405473","https://openalex.org/W4399492476","https://openalex.org/W4404577358","https://openalex.org/W4405935280","https://openalex.org/W4407599443","https://openalex.org/W4409282382","https://openalex.org/W4414371540","https://openalex.org/W4416037017"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"systems":[3],"mitigate":[4],"hallucinations":[5],"in":[6,32],"large":[7],"language":[8],"models":[9],"(LLMs)":[10],"and":[11,28,35,70],"improve":[12],"response":[13],"accuracy":[14],"by":[15],"leveraging":[16],"external":[17,44],"knowledge.":[18],"They":[19],"introduce":[20],"additional":[21],"latency":[22,69],"overhead":[23,72],"due":[24],"to":[25,46,73],"document":[26],"retrieval":[27],"long-context":[29],"processing,":[30],"resulting":[31],"increased":[33],"compute":[34],"memory":[36],"costs.":[37],"Recent":[38],"approaches,":[39],"such":[40],"as":[41],"RAGCache,":[42],"utilize":[43],"DRAM":[45,77],"cache":[47],"key-value":[48],"(KV)":[49],"pairs":[50],"generated":[51],"during":[52],"the":[53,57,75],"prefill":[54],"phase,":[55],"enabling":[56],"reuse":[58],"of":[59],"frequently":[60],"accessed":[61],"documents.":[62],"However,":[63],"DRAM-based":[64],"caches":[65],"incur":[66],"high":[67],"access":[68,74],"energy":[71],"off-package":[76],"frequently.":[78]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-19T00:00:00"}