{"id":"https://openalex.org/W7154033851","doi":"https://doi.org/10.1145/3806056","title":"A Decoupled Analytical Model for Tile Size Selection in Affine Programs","display_name":"A Decoupled Analytical Model for Tile Size Selection in Affine Programs","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154033851","doi":"https://doi.org/10.1145/3806056"},"language":"en","primary_location":{"id":"doi:10.1145/3806056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806056","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/10.1145/3806056","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shihan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihan Yuan","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133547493","display_name":"Zuoyan Zhang","orcid":"https://orcid.org/0009-0005-2615-2541"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuoyan Zhang","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103082764","display_name":"Guanghui Song","orcid":"https://orcid.org/0009-0001-8089-1151"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui Song","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junhui Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Peng","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431429","display_name":"Feng Wang","orcid":"https://orcid.org/0009-0002-4009-6783"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103472424","display_name":"Zhuo Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuo Tang","raw_affiliation_strings":["Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I24407930","display_name":"Hunan University of Science and Engineering","ror":"https://ror.org/04ymz0q33","country_code":"CN","type":"education","lineage":["https://openalex.org/I24407930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["Computer Science, Hunan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, Hunan University","institution_ids":["https://openalex.org/I24407930","https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0003-2303-9736"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["Hunan University"],"raw_orcid":"https://orcid.org/0000-0003-2303-9736","affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]}],"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":0.46693614,"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":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9785000085830688,"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":0.9785000085830688,"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/T10126","display_name":"Logic, programming, and type systems","score":0.002400000113993883,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.002099999925121665,"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/tile","display_name":"Tile","score":0.6498000025749207},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5776000022888184},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.5529999732971191},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.5044999718666077},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47929999232292175},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.47699999809265137},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.46480000019073486},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3993000090122223},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.39640000462532043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8578000068664551},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5776000022888184},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.5529999732971191},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40689998865127563},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C2778361913","wikidata":"https://www.wikidata.org/wiki/Q7248437","display_name":"Program transformation","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3328999876976013},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.31279999017715454},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C56951928","wikidata":"https://www.wikidata.org/wiki/Q3539213","display_name":"Trimming","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806056","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:10.1145/3806056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806056","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":[{"id":"https://openalex.org/G867358703","display_name":null,"funder_award_id":"U24A20235, 62225205, and T2422007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W38784877","https://openalex.org/W1191262899","https://openalex.org/W1964031104","https://openalex.org/W1973532523","https://openalex.org/W2003798513","https://openalex.org/W2025093669","https://openalex.org/W2034761517","https://openalex.org/W2050203172","https://openalex.org/W2055312318","https://openalex.org/W2073061372","https://openalex.org/W2077143534","https://openalex.org/W2084917734","https://openalex.org/W2098220211","https://openalex.org/W2099059741","https://openalex.org/W2102976251","https://openalex.org/W2108737583","https://openalex.org/W2156316655","https://openalex.org/W2158158791","https://openalex.org/W2471164860","https://openalex.org/W2516525699","https://openalex.org/W2528222261","https://openalex.org/W2788233622","https://openalex.org/W2793666465","https://openalex.org/W2913790721","https://openalex.org/W2979365412","https://openalex.org/W2983923412","https://openalex.org/W3102973548","https://openalex.org/W3104745751","https://openalex.org/W3123054690","https://openalex.org/W3170375455","https://openalex.org/W3171525923","https://openalex.org/W3172873298","https://openalex.org/W3205717712","https://openalex.org/W4230289604","https://openalex.org/W4243796884","https://openalex.org/W4308596141","https://openalex.org/W4313419123","https://openalex.org/W4318328349","https://openalex.org/W4390604805","https://openalex.org/W4391952402","https://openalex.org/W4392265917","https://openalex.org/W4399304396","https://openalex.org/W4399918171"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"tile":[1,25,43,94,192,196],"size":[2,44,95],"selection":[3,45,96],"approaches":[4],"are":[5],"tightly":[6],"coupled":[7],"with":[8,63,76,110,125,168,200],"compiler":[9,64],"transformation":[10],"pipelines,":[11],"often":[12],"leading":[13],"to":[14,60,80,128],"inaccurate":[15],"modeling":[16],"of":[17,185,216],"cache":[18],"behavior":[19],"and":[20,39,143,152,198,203],"limited":[21],"effectiveness":[22,189],"for":[23,42,93,116,194],"non-rectangular":[24,195],"shapes.":[26],"This":[27,99],"article":[28],"presents":[29],"TileMind":[30,139,173,217],",":[31],"a":[32,51,82,90,105],"decoupled":[33,58],"analytical":[34,163],"model":[35,164],"that":[36,55],"combines":[37],"compile-time":[38,68],"runtime":[40,78],"information":[41],"in":[46],"affine":[47],"programs.":[48],"It":[49],"introduces":[50],"transformation-aware":[52],"pre-tiling":[53],"step":[54],"enables":[56],"the":[57,161,213],"selector":[59],"remain":[61],"consistent":[62],"transformations":[65],"while":[66,178],"extracting":[67],"metadata.":[69],"The":[70],"extracted":[71],"metadata":[72],"is":[73,97,101],"then":[74],"combined":[75],"profiled":[77],"characteristics":[79],"construct":[81],"richer":[83],"yet":[84],"tractable":[85],"feasible":[86],"domain,":[87],"within":[88,132],"which":[89],"nonlinear":[91,112],"objective":[92,100],"formulated.":[98],"subsequently":[102],"transformed":[103],"into":[104],"binary":[106],"product":[107],"linearization":[108],"problem,":[109],"its":[111],"constraints":[113],"also":[114],"linearized":[115],"efficient":[117],"optimization.":[118],"Finally,":[119],"an":[120],"intra-tile":[121],"optimization":[122],"aligns":[123],"computation":[124],"data":[126,130],"layout":[127],"enhance":[129],"reuse":[131],"tiles.":[133],"Across":[134],"two":[135],"multi-core":[136],"Intel":[137],"CPUs,":[138],"achieves":[140],"1.49\u00d7":[141],"(sequential)":[142],"1.33\u00d7":[144],"(parallel)":[145],"mean":[146,176],"speedups":[147,154,177],"on":[148,155,190,210],"twenty":[149],"PolyBench":[150],"kernels,":[151],"2.08\u20133.54\u00d7":[153],"three":[156],"deep":[157],"learning":[158],"workloads":[159],"over":[160],"state-of-the-art":[162],"Pluto-tss":[165],".":[166],"Compared":[167],"TVM\u2019s":[169],"latest":[170],"autotuner":[171],"MetaSchedule,":[172],"delivers":[174],"1.35\u20131.46\u00d7":[175],"reducing":[179],"tuning":[180],"overhead":[181],"by":[182],"2\u20134":[183],"orders":[184],"magnitude.":[186],"While":[187],"demonstrating":[188],"selecting":[191],"sizes":[193],"shapes":[197],"compatibility":[199],"PPCG,":[201],"Pluto,":[202],"TVM,":[204],"we":[205],"further":[206],"provide":[207],"proof-of-concept":[208],"results":[209],"GPUs,":[211],"illustrating":[212],"potential":[214],"portability":[215],"across":[218],"architectures.":[219]},"counts_by_year":[],"updated_date":"2026-06-27T06:13:17.587685","created_date":"2026-04-14T00:00:00"}