{"id":"https://openalex.org/W2786322233","doi":"https://doi.org/10.1145/3178487.3178537","title":"SIMD code generation for stencils on brick decompositions","display_name":"SIMD code generation for stencils on brick decompositions","publication_year":2018,"publication_date":"2018-02-06","ids":{"openalex":"https://openalex.org/W2786322233","doi":"https://doi.org/10.1145/3178487.3178537","mag":"2786322233"},"language":"en","primary_location":{"id":"doi:10.1145/3178487.3178537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178487.3178537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033875105","display_name":"Tuowen Zhao","orcid":"https://orcid.org/0000-0002-6347-7135"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuowen Zhao","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032219555","display_name":"Protonu Basu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Protonu Basu","raw_affiliation_strings":["Computational Research Division"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Computational Research Division"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082013692","display_name":"Hans Johansen","orcid":"https://orcid.org/0000-0002-9644-9982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hans Johansen","raw_affiliation_strings":["Computational Research Division"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Research Division","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4406,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47010743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9841067790985107},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8336441516876221},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8236683011054993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8064832091331482},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6611366271972656},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6304236650466919},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5826067924499512},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.582289457321167},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5819900035858154},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5640332698822021},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5359673500061035},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4500657320022583},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3179815411567688},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18424704670906067},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1781415343284607},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16071650385856628},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.12726658582687378}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9841067790985107},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8336441516876221},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8236683011054993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064832091331482},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6611366271972656},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6304236650466919},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5826067924499512},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.582289457321167},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5819900035858154},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5640332698822021},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5359673500061035},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4500657320022583},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3179815411567688},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18424704670906067},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1781415343284607},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16071650385856628},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.12726658582687378},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178487.3178537","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178487.3178537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1492882524","https://openalex.org/W1553808293","https://openalex.org/W1997147891","https://openalex.org/W1997375049","https://openalex.org/W2003798513","https://openalex.org/W2018280830","https://openalex.org/W2049510645","https://openalex.org/W2076535184","https://openalex.org/W2150319905","https://openalex.org/W2561650451","https://openalex.org/W3147517636"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W3092174096","https://openalex.org/W3205799311","https://openalex.org/W4244894488","https://openalex.org/W1559264847","https://openalex.org/W4285390450","https://openalex.org/W4300860486","https://openalex.org/W2366442643"],"abstract_inverted_index":{"We":[0,88],"present":[1],"a":[2,26,44,68,92],"stencil":[3,17,41,71],"library":[4,82],"and":[5,43,54,57],"associated":[6],"compiler":[7,63],"code":[8,77],"generation":[9],"framework":[10],"designed":[11,31],"to":[12,32,40,64,83,91],"maximize":[13],"performance":[14],"on":[15,95,102],"higher-order":[16],"computations":[18],"through":[19],"the":[20,34,61,75,80,84,96],"use":[21],"of":[22,70],"two":[23],"main":[24],"technologies:":[25],"fine-grained":[27],"brick":[28,81],"data":[29],"layout":[30],"exploit":[33],"inherent":[35],"multidimensional":[36],"spatial":[37],"locality":[38],"endemic":[39],"computations,":[42,72],"vector":[45,52],"scatter":[46],"associative":[47],"reordering":[48],"transformation":[49],"that":[50],"reduces":[51],"loads":[53],"alignment":[55],"operations":[56],"exposes":[58],"opportunities":[59],"for":[60],"backend":[62],"reduce":[65],"computation.":[66],"For":[67],"range":[69],"we":[73],"compare":[74],"generated":[76],"expressed":[78],"in":[79],"standard":[85],"tiled":[86],"code.":[87],"attain":[89],"up":[90],"7.2X":[93],"speedup":[94],"most":[97],"complex":[98],"stencils":[99],"when":[100],"running":[101],"an":[103],"Intel":[104],"Knights":[105],"Landing":[106],"(Xeon":[107],"Phi)":[108],"processor.":[109]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
