{"id":"https://openalex.org/W3047196046","doi":"https://doi.org/10.1145/3406117","title":"Schedule Synthesis for Halide Pipelines on GPUs","display_name":"Schedule Synthesis for Halide Pipelines on GPUs","publication_year":2020,"publication_date":"2020-08-03","ids":{"openalex":"https://openalex.org/W3047196046","doi":"https://doi.org/10.1145/3406117","mag":"3047196046"},"language":"en","primary_location":{"id":"doi:10.1145/3406117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3406117","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3406117","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":null,"license_id":null,"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://dl.acm.org/doi/pdf/10.1145/3406117","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062737440","display_name":"Savvas Sioutas","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Savvas Sioutas","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032436846","display_name":"Sander Stuijk","orcid":"https://orcid.org/0000-0002-2518-6847"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sander Stuijk","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026760188","display_name":"Twan Basten","orcid":"https://orcid.org/0000-0002-2274-7274"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Twan Basten","raw_affiliation_strings":["Eindhoven University of Technology and ESI, TNO, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology and ESI, TNO, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081768631","display_name":"Henk Corporaal","orcid":"https://orcid.org/0000-0003-4506-5732"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Henk Corporaal","raw_affiliation_strings":["Eindhoven University of Technology, Eindhoven, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112241649","display_name":"Lou Somers","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137410","display_name":"Canon (Netherlands)","ror":"https://ror.org/03nvvdm73","country_code":"NL","type":"company","lineage":["https://openalex.org/I1320697193","https://openalex.org/I4210137410"]},{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lou Somers","raw_affiliation_strings":["Canon Production Printing and Eindhoven University of Technology, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Canon Production Printing and Eindhoven University of Technology, The Netherlands","institution_ids":["https://openalex.org/I83019370","https://openalex.org/I4210137410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062737440"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":2.3565,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88693078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":"3","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":0.9987000226974487,"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":0.9987000226974487,"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":0.9955000281333923,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9922999739646912,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8770031929016113},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.7610948085784912},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7237621545791626},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6584252119064331},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5811835527420044},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.5521619319915771},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.47746920585632324},{"id":"https://openalex.org/keywords/digital-subscriber-line","display_name":"Digital subscriber line","score":0.4713827073574066},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4520067572593689},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.44041261076927185},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.4237278997898102},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18312481045722961},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14404335618019104},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.12995457649230957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770031929016113},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.7610948085784912},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7237621545791626},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6584252119064331},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5811835527420044},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.5521619319915771},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.47746920585632324},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.4713827073574066},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4520067572593689},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.44041261076927185},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4237278997898102},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18312481045722961},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14404335618019104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.12995457649230957},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/3406117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3406117","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3406117","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:pure.tue.nl:openaire/7c628c4a-cf28-4060-b2d2-97618b9b4305","is_oa":true,"landing_page_url":"https://research.tue.nl/en/publications/7c628c4a-cf28-4060-b2d2-97618b9b4305","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sioutas, S, Stuijk, S, Basten, T, Corporaal, H & Somers, L 2020, 'Schedule Synthesis for Halide Pipelines on GPUs', ACM Transactions on Architecture and Code Optimization, vol. 17, no. 3, 3406117. https://doi.org/10.1145/3406117","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:oai-pmh.tno.nl:51687","is_oa":true,"landing_page_url":"https://resolver.tno.nl/uuid:fe1b61fe-e500-4a2d-b351-129fbf261231","pdf_url":"https://publications.tno.nl/publication/34637272/ZVQZaV/sioutas-2020-schedule.pdf","source":{"id":"https://openalex.org/S7407055233","display_name":"TNO Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization, 17(3)","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"pmh:tno:oai:tudelft.nl:uuid:fe1b61fe-e500-4a2d-b351-129fbf261231","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:fe1b61fe-e500-4a2d-b351-129fbf261231","pdf_url":"http://resolver.tudelft.nl/uuid:fe1b61fe-e500-4a2d-b351-129fbf261231","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pure.tue.nl:publications/7c628c4a-cf28-4060-b2d2-97618b9b4305","is_oa":true,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85090419210&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sioutas, S, Stuijk, S, Basten, T, Corporaal, H & Somers, L 2020, 'Schedule Synthesis for Halide Pipelines on GPUs', ACM Transactions on Architecture and Code Optimization, vol. 17, no. 3, 3406117. https://doi.org/10.1145/3406117","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:tue:oai:pure.tue.nl:publications/7c628c4a-cf28-4060-b2d2-97618b9b4305","is_oa":true,"landing_page_url":"https://research.tue.nl/nl/publications/7c628c4a-cf28-4060-b2d2-97618b9b4305","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization, 17(3):3406117. Association for Computing Machinery, Inc","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3406117","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3406117","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3406117","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":null,"license_id":null,"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":[{"display_name":"Affordable and clean energy","score":0.550000011920929,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047196046.pdf","grobid_xml":"https://content.openalex.org/works/W3047196046.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1993164261","https://openalex.org/W2002555321","https://openalex.org/W2023415862","https://openalex.org/W2034601083","https://openalex.org/W2055312318","https://openalex.org/W2075745057","https://openalex.org/W2077143534","https://openalex.org/W2084917734","https://openalex.org/W2100218206","https://openalex.org/W2108315152","https://openalex.org/W2133352531","https://openalex.org/W2153190325","https://openalex.org/W2154078685","https://openalex.org/W2185637430","https://openalex.org/W2471164860","https://openalex.org/W2512431201","https://openalex.org/W2579915854","https://openalex.org/W2774096293","https://openalex.org/W2786320458","https://openalex.org/W2793666465","https://openalex.org/W2804032941","https://openalex.org/W2808498336","https://openalex.org/W2810610794","https://openalex.org/W2938476095","https://openalex.org/W2949967139","https://openalex.org/W2961619211","https://openalex.org/W3104140109","https://openalex.org/W4244917406","https://openalex.org/W4255653201"],"related_works":["https://openalex.org/W320786","https://openalex.org/W3089190408","https://openalex.org/W2292282166","https://openalex.org/W1508811940","https://openalex.org/W2186887852","https://openalex.org/W2033485113","https://openalex.org/W4236919333","https://openalex.org/W1994316441","https://openalex.org/W816557000","https://openalex.org/W2612497434"],"abstract_inverted_index":{"The":[0],"Halide":[1,60,97],"DSL":[2],"and":[3,23,84,120],"compiler":[4],"have":[5],"enabled":[6],"high-performance":[7],"code":[8],"generation":[9,29],"for":[10,34,48,70],"image":[11],"processing":[12],"pipelines":[13],"targeting":[14],"heterogeneous":[15],"architectures":[16],"through":[17],"the":[18,58],"separation":[19],"of":[20,82,94],"algorithmic":[21],"description":[22],"optimization":[24,64],"schedule.":[25],"However,":[26],"automatic":[27],"schedule":[28],"is":[30,43],"currently":[31],"only":[32],"possible":[33],"multi-core":[35],"CPU":[36],"architectures.":[37,73],"As":[38],"a":[39,80],"result,":[40],"expert":[41],"knowledge":[42],"still":[44],"required":[45],"when":[46],"optimizing":[47],"platforms":[49],"with":[50,62,92],"GPU":[51,72],"capabilities.":[52],"In":[53],"this":[54],"work,":[55],"we":[56],"extend":[57],"current":[59],"Autoscheduler":[61],"novel":[63],"passes":[65],"to":[66],"efficiently":[67],"generate":[68],"schedules":[69,111,119],"CUDA-based":[71],"We":[74],"evaluate":[75],"our":[76,110],"proposed":[77],"method":[78],"across":[79],"variety":[81],"applications":[83],"show":[85,108],"that":[86,93,109],"it":[87],"can":[88],"achieve":[89],"performance":[90],"competitive":[91],"manually":[95],"tuned":[96],"schedules,":[98],"or":[99],"in":[100],"many":[101],"cases":[102],"even":[103],"better":[104],"performance.":[105],"Experimental":[106],"results":[107],"are":[112],"on":[113],"average":[114],"10%":[115],"faster":[116,123],"than":[117,124],"manual":[118],"over":[121],"2\u00d7":[122],"previous":[125],"autoscheduling":[126],"attempts.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}