{"id":"https://openalex.org/W4244917406","doi":"https://doi.org/10.1109/cgo.2019.8661176","title":"From Loop Fusion to Kernel Fusion: A Domain-Specific Approach to Locality Optimization","display_name":"From Loop Fusion to Kernel Fusion: A Domain-Specific Approach to Locality Optimization","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W4244917406","doi":"https://doi.org/10.1109/cgo.2019.8661176"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2019.8661176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-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/A5035954398","display_name":"Bo Qiao","orcid":"https://orcid.org/0000-0001-9644-0577"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Bo Qiao","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051274212","display_name":"Oliver Reiche","orcid":"https://orcid.org/0000-0002-5125-4508"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Reiche","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072039340","display_name":"Frank Hannig","orcid":"https://orcid.org/0000-0003-3663-6484"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Frank Hannig","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047105072","display_name":"Jirgen Teich","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jirgen Teich","raw_affiliation_strings":["Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander University Erlangen-N\u00efrnberg (FAU), Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5035954398"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":1.38951484,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.84997126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/computer-science","display_name":"Computer science","score":0.7992188334465027},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.7321261763572693},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5794064402580261},{"id":"https://openalex.org/keywords/loop-fusion","display_name":"Loop fusion","score":0.5673114061355591},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.5523364543914795},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.5501875281333923},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.511139452457428},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.5077263116836548},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5051665902137756},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.4887380599975586},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.42574092745780945},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.422095388174057},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.40590861439704895},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3574059009552002},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.2889571189880371},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1280742883682251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992188334465027},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.7321261763572693},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5794064402580261},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.5673114061355591},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.5523364543914795},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.5501875281333923},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.511139452457428},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.5077263116836548},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5051665902137756},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.4887380599975586},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.42574092745780945},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.422095388174057},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40590861439704895},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3574059009552002},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.2889571189880371},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1280742883682251},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2019.8661176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W631225344","https://openalex.org/W1551026808","https://openalex.org/W1585509108","https://openalex.org/W1869805942","https://openalex.org/W1922926746","https://openalex.org/W1992558790","https://openalex.org/W2055399164","https://openalex.org/W2057463094","https://openalex.org/W2075745057","https://openalex.org/W2084134149","https://openalex.org/W2084917734","https://openalex.org/W2108315152","https://openalex.org/W2111308925","https://openalex.org/W2116176472","https://openalex.org/W2116988482","https://openalex.org/W2153190325","https://openalex.org/W2167637346","https://openalex.org/W2296218291","https://openalex.org/W2471164860","https://openalex.org/W2524530727","https://openalex.org/W2808498336","https://openalex.org/W3148573243","https://openalex.org/W6677444548","https://openalex.org/W6679388247","https://openalex.org/W6682493520"],"related_works":["https://openalex.org/W2342605656","https://openalex.org/W2040522199","https://openalex.org/W2340721088","https://openalex.org/W4251798485","https://openalex.org/W2122418911","https://openalex.org/W2017719803","https://openalex.org/W1543710109","https://openalex.org/W2119560736","https://openalex.org/W1993227264","https://openalex.org/W2727330431"],"abstract_inverted_index":{"Optimizing":[0],"data-intensive":[1],"applications":[2,175],"such":[3],"as":[4,26],"image":[5,46,161,173],"processing":[6,47,162,174],"for":[7,70,89,106],"GPU":[8],"targets":[9],"with":[10],"complex":[11],"memory":[12],"hierarchies":[13],"requires":[14],"to":[15,37,114,129,141,186],"explore":[16],"the":[17,29,41,74,99,111,125],"tradeoffs":[18],"among":[19],"locality,":[20],"parallelism,":[21],"and":[22,52,66,151,164,169],"computation.":[23],"Loop":[24],"fusion":[25,88,112],"one":[27],"of":[28,55,79,98,184],"classical":[30],"optimization":[31,84],"techniques":[32],"has":[33],"been":[34],"proven":[35],"effective":[36],"improve":[38],"locality":[39,71,91,107,145],"at":[40,73],"function":[42,105],"level.":[43,76],"Algorithms":[44],"in":[45,58,159,191],"are":[48,64],"increasing":[49],"their":[50],"complexities":[51],"generally":[53],"consist":[54],"many":[56],"kernels":[57,132],"a":[59,95,115,121],"pipeline.":[60],"The":[61,77,154],"inter-kernel":[62],"communications":[63],"intensive":[65],"exhibit":[67],"another":[68],"opportunity":[69],"improvement":[72,146],"system":[75],"scope":[78],"this":[80],"paper":[81],"is":[82,157],"an":[83,103,138,160],"technique":[85,128,156],"called":[86,167],"kernel":[87],"data":[90],"improvement.":[92],"We":[93],"present":[94],"formal":[96],"description":[97],"problem":[100,113],"by":[101,147],"defining":[102],"objective":[104],"optimization.":[108],"By":[109],"transforming":[110],"graph":[116],"partitioning":[117],"problem,":[118],"we":[119,136],"propose":[120],"solution":[122],"based":[123],"on":[124,176],"minimum":[126],"cut":[127],"search":[130],"fusible":[131],"recursively.":[133],"In":[134],"addition,":[135],"develop":[137],"analytic":[139],"model":[140],"quantitatively":[142],"estimate":[143],"potential":[144],"incorporating":[148],"domain-specific":[149],"knowledge":[150],"architecture":[152],"details.":[153],"proposed":[155],"implemented":[158],"DSL":[163],"source-to-source":[165],"compiler":[166],"Hipacc,":[168],"evaluated":[170],"over":[171],"six":[172],"three":[177],"Nvidia":[178],"GPUs.":[179],"A":[180],"geometric":[181],"mean":[182],"speedup":[183],"up":[185],"2.52":[187],"can":[188],"be":[189],"observed":[190],"our":[192],"experiments.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}