{"id":"https://openalex.org/W7125418156","doi":"https://doi.org/10.1145/3784828.3785400","title":"Prototyping an Autotuning Framework for Program Optimization Using Exo Language","display_name":"Prototyping an Autotuning Framework for Program Optimization Using Exo Language","publication_year":2026,"publication_date":"2026-01-22","ids":{"openalex":"https://openalex.org/W7125418156","doi":"https://doi.org/10.1145/3784828.3785400"},"language":null,"primary_location":{"id":"doi:10.1145/3784828.3785400","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785400","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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784828.3785400","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114538369","display_name":"Rin Iwai","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rin Iwai","raw_affiliation_strings":["Toyohashi University of Technology, Toyohashi, Japan"],"raw_orcid":"https://orcid.org/0009-0008-9876-1639","affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology, Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039069961","display_name":"Jens Domke","orcid":"https://orcid.org/0000-0002-5343-414X"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jens Domke","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5343-414X","affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042298121","display_name":"Emil Vatai","orcid":"https://orcid.org/0000-0001-7494-5048"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Emil Vatai","raw_affiliation_strings":["Center for Computational Science, RIKEN, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7494-5048","affiliations":[{"raw_affiliation_string":"Center for Computational Science, RIKEN, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038208057","display_name":"Yukinori Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I136259955","display_name":"Toyohashi University of Technology","ror":"https://ror.org/04ezg6d83","country_code":"JP","type":"education","lineage":["https://openalex.org/I136259955"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukinori Sato","raw_affiliation_strings":["Toyohashi University of Technology, Toyohashi, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3491-1692","affiliations":[{"raw_affiliation_string":"Toyohashi University of Technology, Toyohashi, Japan","institution_ids":["https://openalex.org/I136259955"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.13894104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.5422999858856201,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.5422999858856201,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.39149999618530273,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.013100000098347664,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.8418999910354614},{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.7716000080108643},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6499000191688538},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6195999979972839},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5978000164031982},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5460000038146973},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.5181999802589417},{"id":"https://openalex.org/keywords/program-transformation","display_name":"Program transformation","score":0.43970000743865967},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.435699999332428}],"concepts":[{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.8418999910354614},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773000001907349},{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.7716000080108643},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6499000191688538},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5978000164031982},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5922999978065491},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.527899980545044},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.5181999802589417},{"id":"https://openalex.org/C2778361913","wikidata":"https://www.wikidata.org/wiki/Q7248437","display_name":"Program transformation","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.435699999332428},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.3889999985694885},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C165443888","wikidata":"https://www.wikidata.org/wiki/Q1482183","display_name":"Transformation matrix","level":3,"score":0.3506999909877777},{"id":"https://openalex.org/C2780395129","wikidata":"https://www.wikidata.org/wiki/Q1128971","display_name":"Rapid prototyping","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2777362769","wikidata":"https://www.wikidata.org/wiki/Q40056","display_name":"Computer program","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C2776697782","wikidata":"https://www.wikidata.org/wiki/Q576460","display_name":"Software prototyping","level":4,"score":0.27639999985694885},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784828.3785400","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785400","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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3784828.3785400","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784828.3785400","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 Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region Workshops","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6909367442131042}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2100218206","https://openalex.org/W2613264175","https://openalex.org/W4281707342"],"related_works":[],"abstract_inverted_index":{"Vectorization":[0],"and":[1,27,39,110,116],"loop":[2],"transformation":[3],"are":[4],"important":[5],"but":[6],"labor-intensive":[7],"process":[8,60],"for":[9,51,94,121],"achieving":[10],"high":[11],"performance":[12],"in":[13,42],"numerical":[14],"computations.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"develop":[20],"a":[21],"tool":[22,55],"\"ExoAutoTuner\"":[23],"that":[24],"helps":[25],"semi-automate":[26],"optimize":[28],"those":[29],"processes":[30],"by":[31],"automatically":[32],"refactoring":[33],"optimization":[34,59,105],"parameters":[35],"such":[36],"as":[37],"unrolling":[38],"tiling":[40],"sizes":[41],"matrix":[43,95],"multiplication":[44,96],"operations.":[45,97],"Coupled":[46],"with":[47],"the":[48,54,70,76,82,85,91,102,114],"Exo":[49],"language":[50],"program":[52,119],"description,":[53],"bridges":[56],"high-level":[57],"user-defined":[58],"to":[61,112],"low-level":[62],"hardware-specific":[63],"instructions.":[64],"We":[65],"perform":[66],"evaluation":[67],"experiments":[68],"on":[69],"Fujitsu":[71],"A64FX":[72],"processor,":[73],"which":[74,88],"drives":[75],"supercomputer":[77],"Fugaku.":[78],"The":[79],"results":[80],"show":[81],"effectiveness":[83],"of":[84,104,118],"proposed":[86],"method,":[87],"significantly":[89],"reduces":[90],"execution":[92],"time":[93],"Our":[98],"ExoAutoTuner":[99],"can":[100],"expand":[101],"possibilities":[103],"using":[106],"new":[107],"instruction":[108],"sets":[109],"contribute":[111],"increasing":[113],"efficiency":[115],"productivity":[117],"development":[120],"unknown":[122],"hardware.":[123]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-23T00:00:00"}
