{"id":"https://openalex.org/W7225375373","doi":"https://doi.org/10.5281/zenodo.23997444","title":"CPU-Aware Predictive Computing for Generative AI: Anticipating Future CPU Workloads and Preparing Processing Resources Before Demand Materializes","display_name":"CPU-Aware Predictive Computing for Generative AI: Anticipating Future CPU Workloads and Preparing Processing Resources Before Demand Materializes","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225375373","doi":"https://doi.org/10.5281/zenodo.23997444"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23997444","doi":"https://doi.org/10.5281/zenodo.23997444","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23997444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.6327999830245972,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.6327999830245972,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.21410000324249268,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.06350000202655792,"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/large-language-model-inference","display_name":"large language model inference","score":0.7300000190734863},{"id":"https://openalex.org/keywords/workload-aware-scheduling","display_name":"workload-aware scheduling","score":0.7670000195503235},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"energy consumption","score":0.5540000200271606},{"id":"https://openalex.org/keywords/resource-orchestration","display_name":"resource orchestration","score":0.4830000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314999938011169},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.7730000019073486},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4722999930381775},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.39579999446868896},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3490999937057495},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23997444","doi":"https://doi.org/10.5281/zenodo.23997444","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23997445","doi":"https://doi.org/10.5281/zenodo.23997445","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997445","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23997444","doi":"https://doi.org/10.5281/zenodo.23997444","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23997444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7225376051","https://openalex.org/W7225408802","https://openalex.org/W7225405760","https://openalex.org/W7225267314","https://openalex.org/W7225425116","https://openalex.org/W7225390238","https://openalex.org/W7225432460","https://openalex.org/W7225376960","https://openalex.org/W7225384738","https://openalex.org/W7225378531"],"abstract_inverted_index":{"The":[0,149,205,269,353],"increasing":[1],"deployment":[2],"of":[3,398],"generative":[4,185,405],"artificial":[5],"intelligence":[6],"(AI)":[7],"systems":[8],"has":[9,104],"created":[10],"computational":[11,146,322,400],"infrastructures":[12],"in":[13,34,65,93,192,202],"which":[14],"central":[15],"processing":[16,21,141,167,225,292],"units":[17,22],"(CPUs)":[18],"and":[19,60,82,113,139,166,172,215,232,246,266,287,320,336,350,379],"graphics":[20],"(GPUs)":[23],"perform":[24],"increasingly":[25,403],"interdependent":[26],"operations.":[27],"Although":[28],"GPU":[29,110,216,229,382],"acceleration":[30],"receives":[31],"substantial":[32,71],"attention":[33,325],"large":[35],"language":[36],"model":[37],"(LLM)":[38],"inference":[39,61,78,115],"optimization,":[40],"CPU":[41,72,91,134,153,164,180,203,213,224,248,273,285,291,309,333,361,372,389],"resources":[42,92,142,249],"remain":[43],"essential":[44],"for":[45,123,402],"request":[46,193],"processing,":[47],"tokenization,":[48],"prompt":[49],"preparation,":[50,163,391],"data":[51],"movement,":[52],"retrieval":[53],"operations,":[54,187],"scheduling,":[55,171],"sampling,":[56],"post-processing,":[57],"memory":[58,165],"management,":[59,169],"orchestration.":[62],"Consequently,":[63],"fluctuations":[64],"incoming":[66],"AI":[67,125,186,406],"requests":[68],"may":[69,227],"produce":[70,198],"workload":[73,97,154,157,260,338,370,377],"variations":[74],"that":[75,130,189,222,289,359],"affect":[76],"overall":[77],"throughput,":[79],"response":[80,94],"latency,":[81,313],"infrastructure":[83,316],"utilization.":[84,204,236],"Existing":[85],"resource":[86,111,174,262,278,310,348,373,390],"management":[87,279],"approaches":[88],"predominantly":[89],"allocate":[90],"to":[95,243,258,305,328],"observed":[96],"changes,":[98],"while":[99],"conventional":[100],"predictive":[101,159,277,386,399],"computing":[102,387],"research":[103,355,393],"primarily":[105],"emphasized":[106],"future":[107,133,284],"information":[108],"demand,":[109],"forecasting,":[112,155],"proactive":[114,360],"preparation.":[116],"This":[117],"paper":[118],"introduces":[119,272],"CPU-Aware":[120],"Predictive":[121],"Computing":[122],"Generative":[124],"(CPU-PCGA),":[126],"a":[127,199,276],"conceptual":[128],"framework":[129,151,206,270],"investigates":[131,208,394],"whether":[132],"workloads":[135],"can":[136],"be":[137,251],"anticipated":[138],"corresponding":[140],"prepared":[143],"before":[144],"actual":[145],"demand":[147,214,298],"materializes.":[148],"proposed":[150,354],"integrates":[152],"request-stage":[156],"characterization,":[158],"core":[160],"allocation,":[161],"thread-pool":[162],"capacity":[168,226,293],"workload-aware":[170],"adaptive":[173],"provisioning.":[175],"It":[176],"considers":[177],"the":[178,209,220,329,343],"heterogeneous":[179,404],"requirements":[181],"associated":[182,345],"with":[183,346,381],"different":[184],"recognizing":[188],"an":[190,395],"increase":[191,201],"frequency":[194],"does":[195,356],"not":[196,357],"necessarily":[197],"proportional":[200],"further":[207],"relationship":[210],"between":[211,282,331],"predicted":[212,259],"execution":[217],"requirements,":[218,261],"including":[219],"possibility":[221],"insufficient":[223],"delay":[228],"task":[230],"submission":[231],"reduce":[233],"effective":[234],"accelerator":[235],"A":[237],"unified":[238],"optimization":[239],"formulation":[240],"is":[241,294,303,326,363],"developed":[242],"determine":[244],"when":[245,297],"how":[247],"should":[250],"reserved,":[252],"activated,":[253],"redistributed,":[254],"or":[255],"released":[256],"according":[257],"availability,":[263],"preparation":[264,362,375],"expenditure,":[265],"service-level":[267],"constraints.":[268],"also":[271],"readiness":[274],"as":[275,340,342],"objective,":[280],"distinguishing":[281],"forecasting":[283,307],"utilization":[286,334],"ensuring":[288],"sufficient":[290],"operationally":[295],"available":[296],"arrives.":[299],"An":[300],"experimental":[301],"methodology":[302],"established":[304],"evaluate":[306],"accuracy,":[308],"readiness,":[311],"request-processing":[312],"CPU-GPU":[314],"coordination,":[315],"utilization,":[317],"energy":[318],"consumption,":[319],"total":[321],"expenditure.":[323],"Particular":[324],"given":[327],"distinction":[330],"aggregate":[332],"prediction":[335],"stage-specific":[337],"prediction,":[339],"well":[341],"costs":[344],"unnecessary":[347],"reservation":[349],"premature":[351],"activation.":[352],"assume":[358],"universally":[364],"beneficial;":[365],"its":[366],"effectiveness":[367],"depends":[368],"on":[369],"predictability,":[371],"elasticity,":[374],"overhead,":[376],"characteristics,":[378],"coordination":[380],"execution.":[383],"By":[384],"extending":[385],"toward":[388],"this":[392],"additional":[396],"dimension":[397],"orchestration":[401],"infrastructures.":[407]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}