{"id":"https://openalex.org/W7154725187","doi":"https://doi.org/10.1145/3810246","title":"Using Task Graph Caching to Accelerate TVM Code Generation","display_name":"Using Task Graph Caching to Accelerate TVM Code Generation","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154725187","doi":"https://doi.org/10.1145/3810246"},"language":"en","primary_location":{"id":"doi:10.1145/3810246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810246","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3810246","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133870674","display_name":"Thais Silva Camacho","orcid":"https://orcid.org/0000-0001-9605-1037"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thais Camacho","raw_affiliation_strings":["Instituto de Computa\u00e7\u00e3o, UNICAMP"],"raw_orcid":"https://orcid.org/0000-0001-9605-1037","affiliations":[{"raw_affiliation_string":"Instituto de Computa\u00e7\u00e3o, UNICAMP","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133841781","display_name":"Lucas Alvarenga e Silva","orcid":"https://orcid.org/0000-0001-9120-476X"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Alvarenga","raw_affiliation_strings":["Instituto de Computa\u00e7\u00e3o, UNICAMP"],"raw_orcid":"https://orcid.org/0000-0001-9120-476X","affiliations":[{"raw_affiliation_string":"Instituto de Computa\u00e7\u00e3o, UNICAMP","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066469939","display_name":"M Francisco Pereira","orcid":null},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcio Pereira","raw_affiliation_strings":["Instituto de Computa\u00e7\u00e3o, UNICAMP"],"raw_orcid":"https://orcid.org/0000-0003-1140-4513","affiliations":[{"raw_affiliation_string":"Instituto de Computa\u00e7\u00e3o, UNICAMP","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067675731","display_name":"Guido Ara\u00fajo","orcid":"https://orcid.org/0000-0003-4869-5190"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guido Araujo","raw_affiliation_strings":["Instituto de Computa\u00e7\u00e3o, UNICAMP"],"raw_orcid":"https://orcid.org/0000-0003-4869-5190","affiliations":[{"raw_affiliation_string":"Instituto de Computa\u00e7\u00e3o, UNICAMP","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48536783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3407000005245209,"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":0.3407000005245209,"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":0.19089999794960022,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.18330000340938568,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6554999947547913},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6304000020027161},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6001999974250793},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5296000242233276},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.48240000009536743},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4577000141143799},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.4546000063419342},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4219000041484833},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.41370001435279846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676999807357788},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6304000020027161},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5296000242233276},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4577000141143799},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.3057999908924103},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3810246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810246","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3810246","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3810246","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1538867357","https://openalex.org/W2097117768","https://openalex.org/W2099001231","https://openalex.org/W2108598243","https://openalex.org/W2153185479","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2417429787","https://openalex.org/W2549139847","https://openalex.org/W2618530766","https://openalex.org/W2742229469","https://openalex.org/W2805566098","https://openalex.org/W2943568678","https://openalex.org/W2963163009","https://openalex.org/W2963446712","https://openalex.org/W2964510705","https://openalex.org/W2979619501","https://openalex.org/W2982083293","https://openalex.org/W2985434555","https://openalex.org/W3012249773","https://openalex.org/W3083117669","https://openalex.org/W3107397589","https://openalex.org/W4221062244","https://openalex.org/W4240212793","https://openalex.org/W4292975105","https://openalex.org/W4318240167","https://openalex.org/W4318256790","https://openalex.org/W4320519434","https://openalex.org/W4321184915","https://openalex.org/W4377710416","https://openalex.org/W4378807770","https://openalex.org/W4379193822","https://openalex.org/W4387490461","https://openalex.org/W4391136507","https://openalex.org/W4413221792","https://openalex.org/W6962867453"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"(DL)":[2],"models":[3,41,181],"are":[4],"at":[5],"the":[6,58,72,78,89,95,98,111,160,170,189,229,234,244],"core":[7],"of":[8,12,97,162,169,246],"a":[9,23,27,140,239],"growing":[10],"number":[11],"applications,":[13],"making":[14,237],"fast,":[15],"low-latency":[16],"execution":[17],"across":[18,121],"diverse":[19],"device":[20,49],"architectures":[21],"both":[22,118],"critical":[24],"requirement":[25],"and":[26,120,173,204],"challenge.":[28],"DL":[29,115,180,247],"compilers,":[30],"such":[31],"as":[32],"TVM,":[33,236],"address":[34],"this":[35],"challenge":[36],"by":[37,101,109,198,215,233],"automatically":[38],"translating":[39],"high-level":[40],"into":[42],"optimized":[43],"low-level":[44],"code":[45,99],"that":[46,69,113,143,183],"effectively":[47],"exploits":[48],"architectures.":[50],"However,":[51],"search-space-based":[52],"algorithms":[53],"face":[54],"difficulties":[55],"in":[56,65,128,149],"exploring":[57],"vast":[59],"optimization":[60,125,146,171,193],"sequence":[61],"space,":[62],"often":[63],"resulting":[64],"lengthy":[66],"compilation":[67,91,245],"times":[68],"significantly":[70,186],"impact":[71],"design":[73],"cycle.":[74],"This":[75,153],"article":[76],"introduces":[77,139],"Task":[79],"Graph":[80],"Caching":[81],"(TGC)":[82],"algorithm,":[83],"1":[84],"which":[85],"aims":[86],"to":[87,131,158,200,217],"reduce":[88],"high":[90],"time":[92,197,214,231],"while":[93],"preserving":[94],"quality":[96],"generated":[100],"TVM.":[102],"In":[103],"particular,":[104],"TGC":[105,138,184,211,226],"enhances":[106],"TVM":[107,151,163],"auto-tuning":[108,196,213],"exploiting":[110],"fact":[112],"similar":[114],"subgraphs":[116],"appear":[117],"within":[119],"models,":[122],"thus":[123],"enabling":[124],"sequences":[126,147],"discovered":[127],"past":[129],"compilations":[130],"guide":[132],"future":[133],"executions.":[134,152],"To":[135],"achieve":[136],"this,":[137],"cache":[141],"structure":[142],"stores":[144],"high-performance":[145],"found":[148],"previous":[150],"information":[154],"is":[155],"then":[156],"used":[157],"seed":[159],"population":[161],"evolutionary":[164],"search,":[165],"avoiding":[166],"redundant":[167],"exploration":[168],"space":[172],"accelerating":[174,243],"convergence.":[175],"Experimental":[176],"results":[177],"on":[178,208,221,224],"twelve":[179],"show":[182],"can":[185,227],"speed":[187],"up":[188,199,216],"search":[190],"for":[191,202,206,219,242],"efficient":[192],"sequences,":[194],"reducing":[195],"2.89\u00d7":[201],"Ansor":[203],"3.13\u00d7":[205],"MetaSchedule":[207,220],"CPU.":[209],"Moreover,":[210],"reduces":[212],"3.25\u00d7":[218],"GPU.":[222],"Furthermore,":[223],"average,":[225],"maintain":[228],"inference":[230],"achieved":[232],"default":[235],"it":[238],"promising":[240],"solution":[241],"models.":[248]},"counts_by_year":[],"updated_date":"2026-06-26T06:17:10.115597","created_date":"2026-04-18T00:00:00"}