{"id":"https://openalex.org/W2889543163","doi":"https://doi.org/10.1109/jproc.2018.2862896","title":"Domain-Specific Optimization and Generation of High-Performance GPU Code for Stencil Computations","display_name":"Domain-Specific Optimization and Generation of High-Performance GPU Code for Stencil Computations","publication_year":2018,"publication_date":"2018-08-30","ids":{"openalex":"https://openalex.org/W2889543163","doi":"https://doi.org/10.1109/jproc.2018.2862896","mag":"2889543163"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2018.2862896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2018.2862896","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","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/A5101918264","display_name":"Prashant Singh Rawat","orcid":"https://orcid.org/0000-0003-3189-3983"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Singh Rawat","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0003-3189-3983","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077120595","display_name":"Miheer Vaidya","orcid":"https://orcid.org/0000-0003-1788-8491"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miheer Vaidya","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0003-1788-8491","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023732985","display_name":"M. Ravishankar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahesh Ravishankar","raw_affiliation_strings":["NVIDIA Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077691647","display_name":"Vinod Grover","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinod Grover","raw_affiliation_strings":["NVIDIA Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039624297","display_name":"Atanas Rountev","orcid":"https://orcid.org/0000-0003-4556-4937"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanas Rountev","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0003-4556-4937","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040769038","display_name":"Louis-No\u00ebl Pouchet","orcid":"https://orcid.org/0000-0001-5103-3097"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-Noel Pouchet","raw_affiliation_strings":["Colorado State University, Fort Collins, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-4737-2034","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.3637,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.98061837,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"106","issue":"11","first_page":"1902","last_page":"1920"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9894000291824341,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9883000254631042,"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/stencil","display_name":"Stencil","score":0.9378407597541809},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8582562208175659},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8430380821228027},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6646429896354675},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6454872488975525},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.6295070648193359},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5665377974510193},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.5643831491470337},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5404608249664307},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.530303955078125},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5130385160446167},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4893803000450134},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45789581537246704},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.4477338194847107},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4445362687110901},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.4136904180049896},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3584219217300415},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2552415728569031},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.16329380869865417},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10390564799308777},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.09799420833587646}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9378407597541809},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8582562208175659},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8430380821228027},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6646429896354675},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6454872488975525},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.6295070648193359},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5665377974510193},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.5643831491470337},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5404608249664307},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.530303955078125},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5130385160446167},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4893803000450134},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45789581537246704},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.4477338194847107},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4445362687110901},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.4136904180049896},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3584219217300415},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2552415728569031},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.16329380869865417},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10390564799308777},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.09799420833587646},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jproc.2018.2862896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2018.2862896","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1154920154","display_name":null,"funder_award_id":"1513120","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1838942446","display_name":null,"funder_award_id":"1440749","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W51719658","https://openalex.org/W1558370006","https://openalex.org/W1973532523","https://openalex.org/W1975001341","https://openalex.org/W1979457157","https://openalex.org/W1987588924","https://openalex.org/W2016618963","https://openalex.org/W2023415862","https://openalex.org/W2028798345","https://openalex.org/W2035430533","https://openalex.org/W2039378765","https://openalex.org/W2048968833","https://openalex.org/W2049510645","https://openalex.org/W2050297469","https://openalex.org/W2055312318","https://openalex.org/W2063186542","https://openalex.org/W2063610885","https://openalex.org/W2063656563","https://openalex.org/W2068810256","https://openalex.org/W2070961300","https://openalex.org/W2072625243","https://openalex.org/W2074833026","https://openalex.org/W2077143534","https://openalex.org/W2084917734","https://openalex.org/W2100218206","https://openalex.org/W2104512032","https://openalex.org/W2107725926","https://openalex.org/W2113190809","https://openalex.org/W2133352531","https://openalex.org/W2151764765","https://openalex.org/W2153185479","https://openalex.org/W2154078685","https://openalex.org/W2154786353","https://openalex.org/W2157099283","https://openalex.org/W2157685422","https://openalex.org/W2183420951","https://openalex.org/W2315715336","https://openalex.org/W2471164860","https://openalex.org/W2512431201","https://openalex.org/W2561650451","https://openalex.org/W2579915854","https://openalex.org/W2604487429","https://openalex.org/W2755551539","https://openalex.org/W2790475769","https://openalex.org/W3141650078","https://openalex.org/W3147517636","https://openalex.org/W3152199537","https://openalex.org/W4231316372","https://openalex.org/W4232301837","https://openalex.org/W4235662649","https://openalex.org/W4246166885","https://openalex.org/W4255560897","https://openalex.org/W6686093555","https://openalex.org/W6748927140","https://openalex.org/W6995564287"],"related_works":["https://openalex.org/W2104840748","https://openalex.org/W2000618606","https://openalex.org/W2167013139","https://openalex.org/W1604915503","https://openalex.org/W4234370346","https://openalex.org/W4246264663","https://openalex.org/W2950655732","https://openalex.org/W2152397470","https://openalex.org/W4255892077","https://openalex.org/W2050152807"],"abstract_inverted_index":{"Stencil":[0],"computations":[1],"arise":[2],"in":[3],"a":[4,51,64],"number":[5],"of":[6,62],"computational":[7],"domains.":[8],"They":[9],"exhibit":[10],"significant":[11],"data":[12],"parallelism":[13],"and":[14],"are":[15],"thus":[16],"well":[17],"suited":[18],"for":[19,48,55],"execution":[20],"on":[21],"graphical":[22],"processing":[23],"units":[24],"(GPUs),":[25],"but":[26],"can":[27,45],"be":[28,46],"memory-bandwidth":[29],"limited":[30],"unless":[31],"temporal":[32],"locality":[33],"is":[34],"utilized":[35],"via":[36],"tiling.":[37],"This":[38],"paper":[39],"describes":[40],"how":[41],"effective":[42],"tiled":[43],"code":[44],"generated":[47],"GPUs":[49],"from":[50],"domain-specific":[52,65],"language":[53],"(DSL)":[54],"stencils.":[56],"Experimental":[57],"results":[58],"demonstrate":[59],"the":[60],"benefits":[61],"such":[63],"optimization":[66],"approach":[67],"over":[68],"state-of-the-art":[69],"general-purpose":[70],"compiler":[71],"optimizations.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
