{"id":"https://openalex.org/W4389245786","doi":"https://doi.org/10.1145/3635305","title":"Modeling the Interplay between Loop Tiling and Fusion in Optimizing Compilers Using Affine Relations","display_name":"Modeling the Interplay between Loop Tiling and Fusion in Optimizing Compilers Using Affine Relations","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389245786","doi":"https://doi.org/10.1145/3635305"},"language":"en","primary_location":{"id":"doi:10.1145/3635305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3635305","pdf_url":null,"source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000546902","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":true,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, China"],"raw_orcid":"https://orcid.org/0000-0003-2303-9736","affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743219","display_name":"Jinchen Xu","orcid":"https://orcid.org/0000-0002-6275-2617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchen Xu","raw_affiliation_strings":["Information Engineering University, China"],"raw_orcid":"https://orcid.org/0000-0002-6275-2617","affiliations":[{"raw_affiliation_string":"Information Engineering University, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000833287","display_name":"Peng Di","orcid":"https://orcid.org/0000-0002-5799-5876"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Di","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-5799-5876","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066629373","display_name":"Wang Nie","orcid":"https://orcid.org/0000-0001-9903-8217"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Nie","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0001-9903-8217","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085610234","display_name":"Jiahui Hu","orcid":"https://orcid.org/0000-0002-4367-0464"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Hu","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-4367-0464","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044802292","display_name":"Yanzhi Yi","orcid":"https://orcid.org/0000-0002-3486-3731"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhi Yi","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-3486-3731","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911059","display_name":"Sijia Yang","orcid":"https://orcid.org/0009-0005-5634-398X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sijia Yang","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0009-0005-5634-398X","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007511354","display_name":"Zhen Geng","orcid":"https://orcid.org/0000-0003-1031-6431"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Geng","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0003-1031-6431","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101772672","display_name":"Renwei Zhang","orcid":"https://orcid.org/0000-0002-9744-5676"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renwei Zhang","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-9744-5676","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bojie Li","orcid":"https://orcid.org/0000-0002-7390-3548"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bojie Li","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0002-7390-3548","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083785921","display_name":"Zhiliang Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiliang Gan","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0000-0001-8983-4666","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xuefeng Jin","orcid":"https://orcid.org/0009-0006-2487-9402"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefeng Jin","raw_affiliation_strings":["Huawei Technologies Co. Ltd., China","Huawei Technologies Co., Ltd., China"],"raw_orcid":"https://orcid.org/0009-0006-2487-9402","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5000546902"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.5875,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64833993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"41","issue":"1-4","first_page":"1","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.8965826034545898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.87088942527771},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6125602722167969},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5431725978851318},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.5330893397331238},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.5172567963600159},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.49620896577835083},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.4531926214694977},{"id":"https://openalex.org/keywords/loop-fusion","display_name":"Loop fusion","score":0.45300590991973877},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.4392603635787964},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42194652557373047},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3644302487373352},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3314546048641205},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.20806404948234558},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13169941306114197},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08512359857559204}],"concepts":[{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.8965826034545898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.87088942527771},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6125602722167969},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5431725978851318},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.5330893397331238},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.5172567963600159},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.49620896577835083},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.4531926214694977},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.45300590991973877},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.4392603635787964},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42194652557373047},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3644302487373352},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3314546048641205},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.20806404948234558},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13169941306114197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08512359857559204},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3635305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3635305","pdf_url":null,"source":{"id":"https://openalex.org/S193109227","display_name":"ACM Transactions on Computer Systems","issn_l":"0734-2071","issn":["0734-2071","1557-7333"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Computer Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G7619151073","display_name":null,"funder_award_id":"U20A20226","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":50,"referenced_works":["https://openalex.org/W1191262899","https://openalex.org/W1545258949","https://openalex.org/W1558370006","https://openalex.org/W1972612668","https://openalex.org/W1973532523","https://openalex.org/W1975964164","https://openalex.org/W2003798513","https://openalex.org/W2025093669","https://openalex.org/W2031373197","https://openalex.org/W2032391783","https://openalex.org/W2034761517","https://openalex.org/W2051305716","https://openalex.org/W2055312318","https://openalex.org/W2077143534","https://openalex.org/W2084917734","https://openalex.org/W2100218206","https://openalex.org/W2102976251","https://openalex.org/W2111308925","https://openalex.org/W2112391112","https://openalex.org/W2112796928","https://openalex.org/W2126464777","https://openalex.org/W2127419850","https://openalex.org/W2194775991","https://openalex.org/W2295982679","https://openalex.org/W2296218291","https://openalex.org/W2475334473","https://openalex.org/W2528222261","https://openalex.org/W2570343428","https://openalex.org/W2788233622","https://openalex.org/W2788464413","https://openalex.org/W2799269451","https://openalex.org/W2949967139","https://openalex.org/W2961619211","https://openalex.org/W2963341956","https://openalex.org/W2979365412","https://openalex.org/W2995257150","https://openalex.org/W3090425474","https://openalex.org/W3091055609","https://openalex.org/W3102973548","https://openalex.org/W3104745751","https://openalex.org/W3122286897","https://openalex.org/W3157657667","https://openalex.org/W3174529902","https://openalex.org/W3177452048","https://openalex.org/W3203568064","https://openalex.org/W3206129030","https://openalex.org/W4231316372","https://openalex.org/W4235662649","https://openalex.org/W4246500121","https://openalex.org/W6740283659"],"related_works":["https://openalex.org/W2342605656","https://openalex.org/W2040522199","https://openalex.org/W2058764256","https://openalex.org/W154155438","https://openalex.org/W1596526459","https://openalex.org/W1508919682","https://openalex.org/W2109246102","https://openalex.org/W1532159642","https://openalex.org/W2340721088","https://openalex.org/W2062111218"],"abstract_inverted_index":{"Loop":[0],"tiling":[1,23,81,99,143],"and":[2,24,47,82,95,190,214,232,259,275,292,296],"fusion":[3,25,139,164,192],"are":[4,120,129,158,227],"two":[5,206],"essential":[6],"transformations":[7],"in":[8,26,50,71],"optimizing":[9,51,207],"compilers":[10],"to":[11,74,100,131,237,283],"enhance":[12],"the":[13,77,101,109,125,133,137,152,172,175,185,191,202,215,239,242,264,303],"data":[14,106,128,168],"locality":[15,169],"of":[16,32,66,136,174,187,193,241,248,271],"programs.":[17],"Existing":[18],"heuristics":[19],"either":[20],"perform":[21],"loop":[22,68,80,89],"a":[27,45,58,142,162,197,211,217,233,245,268],"particular":[28],"order,":[29],"missing":[30],"some":[31],"their":[33,93],"profitable":[34],"compositions,":[35],"or":[36],"execute":[37],"ad-hoc":[38],"implementations":[39],"for":[40,44,63,166,220,244,302],"domain-specific":[41,218],"applications,":[42],"calling":[43],"generalized":[46],"systematic":[48],"solution":[49],"compilers.":[52],"In":[53,262],"this":[54],"article,":[55],"we":[56],"present":[57],"so-called":[59],"basteln":[60,85,179,203,265],"(an":[61],"abbreviation":[62],"backward":[64],"slicing":[65],"tiled":[67],"nests)":[69],"strategy":[70,86,180,204,266],"polyhedral":[72],"compilation":[73],"better":[75],"model":[76],"interplay":[78],"between":[79,154],"fusion.":[83],"The":[84,113,178,225],"first":[87],"groups":[88,103],"nests":[90],"by":[91,117,151,161,294],"preserving":[92],"parallelism/tilability":[94,173],"next":[96],"performs":[97],"rectangular/parallelogram":[98],"output":[102,176],"that":[104],"produce":[105],"consumed":[107],"outside":[108],"considered":[110],"program":[111],"fragment.":[112],"memory":[114],"footprints":[115],"required":[116],"each":[118],"tile":[119,134,148],"then":[121],"computed,":[122],"from":[123],"which":[124,157],"upward":[126],"exposed":[127],"extracted":[130],"determine":[132],"shapes":[135,149],"remaining":[138],"groups.":[140,177],"Such":[141],"mechanism":[144],"can":[145],"construct":[146],"complex":[147],"imposed":[150],"dependences":[153],"these":[155],"groups,":[156,195],"further":[159],"merged":[160],"post-tiling":[163],"algorithm":[165],"enhancing":[167],"without":[170],"losing":[171],"also":[181,289],"takes":[182],"into":[183,205],"account":[184],"amount":[186],"redundant":[188],"computations":[189],"independent":[194],"exhibiting":[196],"general":[198],"applicability.":[199],"We":[200],"integrate":[201],"compilers,":[208],"with":[209],"one":[210],"general-purpose":[212],"optimizer":[213],"other":[216],"compiler":[219],"deploying":[221],"deep":[222,234,252,285,304],"learning":[223,235,286,305],"models.":[224],"experiments":[226],"conducted":[228],"on":[229,279],"CPU,":[230],"GPU,":[231],"accelerator":[236],"demonstrate":[238],"effectiveness":[240],"approach":[243],"wide":[246],"class":[247],"application":[249],"domains,":[250],"including":[251],"learning,":[253],"image":[254],"processing,":[255],"sparse":[256],"matrix":[257],"computation,":[258],"linear":[260],"algebra.":[261],"particular,":[263],"achieves":[267],"mean":[269],"speedup":[270],"1.8\u00d7":[272],"over":[273,277],"cuBLAS/cuDNN":[274],"1.1\u00d7":[276],"TVM":[278,293],"GPU":[280],"when":[281,299],"used":[282],"optimize":[284],"models;":[287],"it":[288],"outperforms":[290],"PPCG":[291],"11%":[295],"20%,":[297],"respectively,":[298],"generating":[300],"code":[301],"accelerator.":[306]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
