{"id":"https://openalex.org/W7140556721","doi":"https://doi.org/10.48550/arxiv.2603.24239","title":"DVM: A Bytecode Virtual Machine Approach for Dynamic Tensor Computation","display_name":"DVM: A Bytecode Virtual Machine Approach for Dynamic Tensor Computation","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140556721","doi":"https://doi.org/10.48550/arxiv.2603.24239"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24239","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077466750","display_name":"Jingzhi Fang","orcid":"https://orcid.org/0000-0001-6462-5825"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fang, Jingzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046970118","display_name":"Xiong Gao","orcid":"https://orcid.org/0000-0003-0677-4325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Xiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772672","display_name":"Renwei Zhang","orcid":"https://orcid.org/0000-0002-9744-5676"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Renwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039897459","display_name":"ZiChun Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Zichun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130634784","display_name":"Lei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130674225","display_name":"Jie Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130656706","display_name":"Chengnuo Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chengnuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130667932","display_name":"Hui Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130708198","display_name":"Xuefeng Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Xuefeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5077466750"],"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.15369999408721924,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.15369999408721924,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.12229999899864197,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.08980000019073486,"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/bytecode","display_name":"Bytecode","score":0.7768999934196472},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.666700005531311},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5881999731063843},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/just-in-time-compilation","display_name":"Just-in-time compilation","score":0.4943999946117401},{"id":"https://openalex.org/keywords/dynamic-compilation","display_name":"Dynamic compilation","score":0.48890000581741333},{"id":"https://openalex.org/keywords/satisfiability-modulo-theories","display_name":"Satisfiability modulo theories","score":0.4228000044822693},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.414000004529953},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.40389999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8946999907493591},{"id":"https://openalex.org/C2779818221","wikidata":"https://www.wikidata.org/wiki/Q837330","display_name":"Bytecode","level":3,"score":0.7768999934196472},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.666700005531311},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5188999772071838},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.4943999946117401},{"id":"https://openalex.org/C8767382","wikidata":"https://www.wikidata.org/wiki/Q1058454","display_name":"Dynamic compilation","level":3,"score":0.48890000581741333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.47269999980926514},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C2778361913","wikidata":"https://www.wikidata.org/wiki/Q7248437","display_name":"Program transformation","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C195701839","wikidata":"https://www.wikidata.org/wiki/Q4008398","display_name":"Partial evaluation","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.30480000376701355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2777472213","wikidata":"https://www.wikidata.org/wiki/Q137496","display_name":"Java bytecode","level":5,"score":0.27079999446868896},{"id":"https://openalex.org/C202973057","wikidata":"https://www.wikidata.org/wiki/Q7380130","display_name":"Runtime verification","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2653999924659729}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24239","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24239","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dynamism":[0],"is":[1,85],"common":[2],"in":[3,16,220,234],"AI":[4],"computation,":[5],"e.g.,":[6],"the":[7,12,20,28,32,38,49,68,79,89,93,143,149,153,162,166,223,237],"dynamic":[8,13,55,74,127,187],"tensor":[9],"shapes":[10],"and":[11,42,76,122,151,183,191,204,212,226],"control":[14],"flows":[15],"models.":[17],"Due":[18],"to":[19,46,83,86,119,196,217,228],"long":[21,39],"compilation":[22,26,40,72,90,94,124,239],"time,":[23],"existing":[24],"runtime":[25,71,110,167,184],"damages":[27],"model":[29],"efficiency,":[30],"while":[31],"offline":[33],"compilers":[34],"either":[35],"suffer":[36],"from":[37],"time":[41],"device":[43],"memory":[44],"footprint":[45],"cover":[47],"all":[48],"possible":[50],"execution":[51,160],"instances":[52],"of":[53,70,135,222,231,236],"a":[54,101,109,115],"model,":[56],"or":[57,91],"sacrifice":[58],"optimization":[59],"opportunities":[60],"for":[61,73,81,125,158],"usability.":[62],"In":[63,105],"this":[64],"paper,":[65],"we":[66,99,107,141,170,214],"rethink":[67],"feasibility":[69],"models":[75,205],"identify":[77],"that":[78],"key":[80],"it":[82],"work":[84],"speed":[87],"up":[88,216,227],"hide":[92],"overhead.":[95],"To":[96],"do":[97],"this,":[98],"propose":[100,172],"real-time":[102],"compiler,":[103,169],"DVM.":[104],"DVM,":[106],"design":[108],"operator":[111,128,144,168,174],"compiler":[112],"based":[113],"on":[114,148,161,165,180,186,201],"bytecode":[116,147,154],"virtual":[117,156],"machine":[118,139],"perform":[120],"effective":[121],"efficient":[123],"each":[126],"instance":[129],"given":[130],"its":[131],"input.":[132],"Specifically,":[133],"instead":[134],"compiling":[136],"programs":[137],"into":[138,146,155],"code,":[140],"encode":[142],"program":[145],"CPU":[150],"decode":[152],"instructions":[157],"direct":[159],"NPU.":[163],"Based":[164],"further":[171],"an":[173],"fuser,":[175],"which":[176],"performs":[177],"symbol-deduction-based":[178],"fusion":[179,185,193,198],"static":[181],"graphs":[182],"graphs.":[188],"Both":[189],"pattern-":[190],"stacking-based":[192],"are":[194,215],"supported":[195],"increase":[197],"opportunities.":[199],"Evaluation":[200],"operators,":[202],"subgraphs,":[203],"shows":[206],"that,":[207],"compared":[208],"with":[209],"TorchInductor,":[210],"PyTorch-eager":[211],"MindSpore-graph-O0,":[213],"11.77$\\times$":[218],"better":[219],"terms":[221,235],"operator/model":[224],"efficiency":[225],"5":[229],"orders":[230],"magnitude":[232],"faster":[233],"maximum":[238],"time.":[240]},"counts_by_year":[],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2026-03-27T00:00:00"}
