{"id":"https://openalex.org/W4409328045","doi":"https://doi.org/10.1145/3622781.3674172","title":"MaxEmbed: Maximizing SSD bandwidth utilization for huge embedding models serving","display_name":"MaxEmbed: Maximizing SSD bandwidth utilization for huge embedding models serving","publication_year":2024,"publication_date":"2024-04-27","ids":{"openalex":"https://openalex.org/W4409328045","doi":"https://doi.org/10.1145/3622781.3674172"},"language":"en","primary_location":{"id":"doi:10.1145/3622781.3674172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622781.3674172","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674172","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674172","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ruwen Fan","orcid":"https://orcid.org/0009-0002-3590-7473"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruwen Fan","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3590-7473","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101139637","display_name":"Minhui Xie","orcid":"https://orcid.org/0000-0001-6684-8336"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minhui Xie","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6684-8336","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haodi Jiang","orcid":"https://orcid.org/0009-0007-2347-1680"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodi Jiang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-2347-1680","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052095173","display_name":"Youyou Lu","orcid":"https://orcid.org/0000-0002-6214-5390"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Youyou Lu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6214-5390","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3122,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65126373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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/T11478","display_name":"Caching and Content Delivery","score":0.9840999841690063,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9674000144004822,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636799812316895},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.6794153451919556},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5622527599334717},{"id":"https://openalex.org/keywords/bandwidth-allocation","display_name":"Bandwidth allocation","score":0.4333270788192749},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.40690848231315613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07007110118865967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636799812316895},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6794153451919556},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5622527599334717},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.4333270788192749},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.40690848231315613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07007110118865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3622781.3674172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622781.3674172","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674172","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3622781.3674172","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3622781.3674172","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3622781.3674172","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 4","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G4440035852","display_name":null,"funder_award_id":"62332011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409328045.pdf","grobid_xml":"https://content.openalex.org/works/W4409328045.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W288065879","https://openalex.org/W2013652529","https://openalex.org/W2040924621","https://openalex.org/W2158598102","https://openalex.org/W2738781142","https://openalex.org/W2964182926","https://openalex.org/W3018808210","https://openalex.org/W3155243801","https://openalex.org/W3157410348","https://openalex.org/W4210431029","https://openalex.org/W4213153339","https://openalex.org/W4226435553","https://openalex.org/W4245659846","https://openalex.org/W4318541545","https://openalex.org/W4376272906","https://openalex.org/W6966608766"],"related_works":["https://openalex.org/W2148705057","https://openalex.org/W4251345889","https://openalex.org/W2141211540","https://openalex.org/W1990230466","https://openalex.org/W2044253388","https://openalex.org/W2073876121","https://openalex.org/W2128382336","https://openalex.org/W2389240193","https://openalex.org/W1999486158","https://openalex.org/W2142810995"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"recommendation":[2,32],"models":[3],"(DLRMs)":[4],"have":[5],"gained":[6],"widespread":[7],"application":[8],"across":[9],"search,":[10],"advertising,":[11],"and":[12,41,68],"e-commerce.":[13],"Still,":[14],"DLRMs":[15],"present":[16],"notable":[17],"challenges":[18,81],"as":[19,104],"they":[20,56],"depend":[21],"heavily":[22],"on":[23],"large":[24],"embedding":[25,66,74],"tables":[26],"to":[27,78,86],"represent":[28],"sparse":[29],"features":[30],"in":[31],"systems.":[33],"This":[34],"raises":[35],"concerns":[36],"about":[37],"both":[38],"memory":[39],"capacity":[40],"cost.":[42],"Solid-state":[43],"drives":[44],"(SSDs)":[45],"offer":[46],"a":[47,51,102],"cost-effective":[48],"solution":[49],"with":[50],"significantly":[52],"larger":[53],"capacity,":[54],"but":[55],"introduce":[57],"read":[58,70,96],"amplification":[59],"issues":[60],"because":[61],"of":[62],"the":[63,91],"mismatch":[64],"between":[65,115],"size":[67],"SSD":[69,73,93],"granularity.":[71],"Prior":[72],"storage":[75],"systems":[76],"aim":[77],"tackle":[79],"these":[80],"by":[82],"employing":[83],"hypergraph":[84],"partitioning":[85],"co-locate":[87],"co-appearing":[88],"embeddings":[89,107],"onto":[90],"same":[92],"page,":[94],"alleviating":[95],"amplification.":[97],"However,":[98],"this":[99],"approach":[100],"has":[101],"drawback":[103],"it":[105],"divides":[106],"into":[108],"completely":[109],"disjoint":[110],"clusters,":[111],"limiting":[112],"potential":[113],"combinations":[114],"embeddings.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
