{"id":"https://openalex.org/W7123844170","doi":"https://doi.org/10.1145/3772052.3772236","title":"10C <scp>ache</scp> : Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training","display_name":"10C <scp>ache</scp> : Heterogeneous Resource-Aware Tensor Caching and Migration for LLM Training","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7123844170","doi":"https://doi.org/10.1145/3772052.3772236"},"language":"en","primary_location":{"id":"doi:10.1145/3772052.3772236","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772236","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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772052.3772236","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115940092","display_name":"Sabiha Afroz","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sabiha Afroz","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0009-0001-2592-8572","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078335469","display_name":"Redwan Ibne Seraj Khan","orcid":"https://orcid.org/0000-0003-3228-6384"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Redwan Ibne Seraj Khan","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0003-3228-6384","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083817094","display_name":"Hadeel Albahar","orcid":"https://orcid.org/0000-0002-4732-2707"},"institutions":[{"id":"https://openalex.org/I36721946","display_name":"Kuwait University","ror":"https://ror.org/021e5j056","country_code":"KW","type":"education","lineage":["https://openalex.org/I36721946"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Hadeel Albahar","raw_affiliation_strings":["Kuwait University, Kuwait City, Kuwait"],"raw_orcid":"https://orcid.org/0000-0002-4732-2707","affiliations":[{"raw_affiliation_string":"Kuwait University, Kuwait City, Kuwait","institution_ids":["https://openalex.org/I36721946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025023715","display_name":"Jingoo Han","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingoo Han","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-9223-8061","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045271329","display_name":"A.E. Butt","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali R. Butt","raw_affiliation_strings":["Virginia Tech, Blacksburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-0871-7263","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, Virginia, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6587697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3691999912261963,"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":0.3691999912261963,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0786999985575676,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0737999975681305,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.7928000092506409},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5900999903678894},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5544000267982483},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4794999957084656},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4562000036239624},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3531000018119812},{"id":"https://openalex.org/keywords/non-volatile-memory","display_name":"Non-volatile memory","score":0.3327000141143799},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3264000117778778}],"concepts":[{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.7928000092506409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630000114440918},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C177950962","wikidata":"https://www.wikidata.org/wiki/Q10997658","display_name":"Non-volatile memory","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3084999918937683},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3075000047683716},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.29179999232292175},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2727000117301941},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.2606000006198883},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3772052.3772236","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772236","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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/141118","is_oa":false,"landing_page_url":"https://hdl.handle.net/10919/141118","pdf_url":null,"source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3772052.3772236","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772052.3772236","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 2025 ACM Symposium on Cloud Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7579118013381958,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2890016880","display_name":null,"funder_award_id":"CSR-2106634, CSR-2312785","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2330958039","https://openalex.org/W2883283076","https://openalex.org/W2903754802","https://openalex.org/W3010830594","https://openalex.org/W3012479151","https://openalex.org/W3129831491","https://openalex.org/W3157864729","https://openalex.org/W4200572326","https://openalex.org/W4360831773","https://openalex.org/W4365511667","https://openalex.org/W4384155663","https://openalex.org/W4389491867","https://openalex.org/W4393407018","https://openalex.org/W4408843954","https://openalex.org/W4413145360","https://openalex.org/W4417241857"],"related_works":[],"abstract_inverted_index":{"Training":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"in":[5,97],"the":[6,14],"cloud":[7,54],"faces":[8],"growing":[9],"memory":[10,24,47,77,95,99,107],"bottlenecks":[11],"due":[12],"to":[13,26,90,109],"limited":[15],"capacity":[16],"and":[17,28,44,53,67,82,105],"high":[18,40],"cost":[19],"of":[20],"GPUs.":[21],"While":[22],"GPU":[23],"offloading":[25],"CPU":[27],"NVMe":[29,83],"has":[30],"made":[31],"large-scale":[32],"training":[33,51,73],"more":[34],"feasible,":[35],"existing":[36],"approaches":[37],"suffer":[38],"from":[39],"tensor":[41,65,87,102],"migration":[42,68],"latency":[43],"suboptimal":[45],"device":[46],"utilization,":[48],"ultimately":[49],"increasing":[50],"time":[52],"costs.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60],"present":[61],"10Cache,":[62],"a":[63],"resource-aware":[64],"caching":[66],"system":[69],"that":[70],"accelerates":[71],"LLM":[72],"by":[74],"intelligently":[75],"coordinating":[76],"usage":[78],"across":[79],"GPU,":[80],"CPU,":[81],"tiers.":[84],"10Cache":[85],"profiles":[86],"execution":[88],"order":[89],"construct":[91],"prefetch":[92],"policies,":[93],"allocates":[94],"buffers":[96,108],"pinned":[98],"based":[100],"on":[101],"size":[103],"distributions,":[104],"reuses":[106],"minimize":[110],"allocation":[111],"overhead.":[112]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}