{"id":"https://openalex.org/W2016618963","doi":"https://doi.org/10.1145/2259016.2259037","title":"Auto-generation and auto-tuning of 3D stencil codes on GPU clusters","display_name":"Auto-generation and auto-tuning of 3D stencil codes on GPU clusters","publication_year":2012,"publication_date":"2012-03-31","ids":{"openalex":"https://openalex.org/W2016618963","doi":"https://doi.org/10.1145/2259016.2259037","mag":"2016618963"},"language":"en","primary_location":{"id":"doi:10.1145/2259016.2259037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2259016.2259037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Code Generation and Optimization","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/A5002568596","display_name":"Yongpeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongpeng Zhang","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031749427","display_name":"Frank Mueller","orcid":"https://orcid.org/0000-0002-0258-0294"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Mueller","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":13.4729,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.99204124,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9863777160644531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.80751633644104},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.7196695804595947},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.696266770362854},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6195560097694397},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5256748795509338},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4816552400588989},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.47798675298690796},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4327908754348755},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.42786356806755066},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42451682686805725},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40428876876831055},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.27943313121795654},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.0696524977684021}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9863777160644531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80751633644104},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.7196695804595947},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.696266770362854},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6195560097694397},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5256748795509338},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4816552400588989},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.47798675298690796},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4327908754348755},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.42786356806755066},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42451682686805725},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40428876876831055},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.27943313121795654},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0696524977684021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2259016.2259037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2259016.2259037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.7627","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.7627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://moss.csc.ncsu.edu/%7Emueller/ftp/pub/mueller/papers/cgo12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5400000214576721,"display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G2941278053","display_name":null,"funder_award_id":"1.06E+20","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7508379426","display_name":null,"funder_award_id":"DE-FG02-08ER25837","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"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":23,"referenced_works":["https://openalex.org/W1863336885","https://openalex.org/W1964031104","https://openalex.org/W1967264375","https://openalex.org/W1979566015","https://openalex.org/W1982583873","https://openalex.org/W1987588924","https://openalex.org/W2028798345","https://openalex.org/W2039378765","https://openalex.org/W2074833026","https://openalex.org/W2096672917","https://openalex.org/W2099625934","https://openalex.org/W2101650420","https://openalex.org/W2102102439","https://openalex.org/W2104512032","https://openalex.org/W2107483876","https://openalex.org/W2113190809","https://openalex.org/W2135682468","https://openalex.org/W2144511445","https://openalex.org/W2154786353","https://openalex.org/W2156841718","https://openalex.org/W2164197394","https://openalex.org/W3139770841","https://openalex.org/W4231413142"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W2008005532","https://openalex.org/W2889543163","https://openalex.org/W2368959524","https://openalex.org/W2016618963"],"abstract_inverted_index":{"This":[0,77],"paper":[1],"develops":[2],"and":[3,6,66,109],"evaluates":[4],"search":[5,35],"optimization":[7],"techniques":[8],"for":[9,24,62,74,83],"auto-tuning":[10,78],"3D":[11],"stencil":[12,46,113],"(nearest-neighbor)":[13],"computations":[14],"on":[15],"GPUs.":[16,76],"Observations":[17],"indicate":[18],"that":[19,96],"parameter":[20,72],"tuning":[21],"is":[22,102],"necessary":[23],"heterogeneous":[25],"GPUs":[26,87],"to":[27,33,105],"achieve":[28],"optimal":[29,71],"performance":[30,82,101],"with":[31,70],"respect":[32],"a":[34,41,52,116],"space.":[36],"Our":[37],"proposed":[38],"framework":[39],"takes":[40],"most":[42],"concise":[43],"specification":[44],"of":[45,86],"behavior":[47],"from":[48,58],"the":[49,63,68,97],"user":[50],"as":[51],"single":[53],"formula,":[54],"auto-generates":[55],"tunable":[56],"code":[57,69],"it,":[59],"systematically":[60],"searches":[61],"best":[64],"configuration":[65],"generates":[67],"configurations":[73],"different":[75,84],"approach":[79],"guarantees":[80],"adaptive":[81],"generations":[85],"while":[88],"greatly":[89],"enhancing":[90],"programmer":[91],"productivity.":[92],"Experimental":[93],"results":[94],"show":[95],"delivered":[98],"floating":[99],"point":[100],"very":[103],"close":[104],"previous":[106],"handcrafted":[107],"work":[108],"outperforms":[110],"other":[111],"auto-tuned":[112],"codes":[114],"by":[115],"large":[117],"margin.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}