{"id":"https://openalex.org/W2128125098","doi":"https://doi.org/10.1145/1693453.1693510","title":"Data transformations enabling loop vectorization on multithreaded data parallel architectures","display_name":"Data transformations enabling loop vectorization on multithreaded data parallel architectures","publication_year":2010,"publication_date":"2010-01-09","ids":{"openalex":"https://openalex.org/W2128125098","doi":"https://doi.org/10.1145/1693453.1693510","mag":"2128125098"},"language":"en","primary_location":{"id":"doi:10.1145/1693453.1693510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1693453.1693510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5011494558","display_name":"Byunghyun Jang","orcid":"https://orcid.org/0000-0001-8316-4323"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byunghyun Jang","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038365055","display_name":"Perhaad Mistry","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Perhaad Mistry","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042145789","display_name":"Dana Schaa","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dana Schaa","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673519","display_name":"Rodrigo Dom\u00ednguez","orcid":"https://orcid.org/0000-0003-1651-4842"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodrigo Dominguez","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":3.5436,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93260829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"354"},"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":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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/vectorization","display_name":"Vectorization (mathematics)","score":0.8727774620056152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8441194295883179},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8160178065299988},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6970958709716797},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6351097226142883},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5965594053268433},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5278354287147522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5166183114051819},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5085450410842896},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.4732138216495514},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.4171349108219147},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4116635024547577},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.32272714376449585},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13685902953147888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0878499448299408},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07494646310806274}],"concepts":[{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8727774620056152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441194295883179},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8160178065299988},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6970958709716797},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6351097226142883},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5965594053268433},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5278354287147522},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5166183114051819},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5085450410842896},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.4732138216495514},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4171349108219147},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4116635024547577},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.32272714376449585},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13685902953147888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0878499448299408},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07494646310806274},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1693453.1693510","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1693453.1693510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.410.3493","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.410.3493","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.neu.edu/groups/nucar/publications/bjang-ppopp10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.705.2295","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.705.2295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www1.coe.neu.edu/%7Epmistry/perhaad/Research_files/ppopp196-jang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2116065632","https://openalex.org/W2116963870","https://openalex.org/W2142252451","https://openalex.org/W2160245390"],"related_works":["https://openalex.org/W2890419659","https://openalex.org/W2378016289","https://openalex.org/W2121941320","https://openalex.org/W7941220","https://openalex.org/W2021715972","https://openalex.org/W2286348849","https://openalex.org/W2484588007","https://openalex.org/W2899265977","https://openalex.org/W2166191672","https://openalex.org/W4240756795"],"abstract_inverted_index":{"Loop":[0],"vectorization,":[1],"a":[2,49],"key":[3],"feature":[4],"exploited":[5],"to":[6,38,67,139],"obtain":[7],"high":[8,126],"performance":[9,127,136],"on":[10],"Single":[11],"Instruction":[12],"Multiple":[13],"Data":[14],"(SIMD)":[15],"vector":[16],"architectures,":[17],"is":[18],"significantly":[19,80],"hindered":[20],"by":[21,141],"irregular":[22],"memory":[23,55],"access":[24,56],"patterns":[25,57],"in":[26,65],"the":[27,60,75,82,92,102,114,117,123],"data":[28,33,44,63,77,107,119,146],"stream.":[29],"This":[30],"paper":[31],"describes":[32],"transformations":[34,64,78,108],"that":[35,52,74,86,101],"allow":[36],"us":[37],"vectorize":[39],"loops":[40,85],"targeting":[41],"massively":[42],"multithreaded":[43],"parallel":[45],"architectures.":[46],"We":[47],"present":[48],"mathematical":[50],"model":[51],"captures":[53],"loop-based":[54],"and":[58,90,134],"computes":[59],"most":[61],"appropriate":[62],"order":[66],"enable":[68],"vectorization.":[69],"Our":[70,97],"experimental":[71],"results":[72,98],"show":[73,100],"proposed":[76],"can":[79,87,109],"increase":[81],"number":[83],"of":[84,95,116,125],"be":[88,110],"vectorized":[89],"enhance":[91],"data-level":[93],"parallelism":[94],"applications.":[96],"also":[99],"overhead":[103],"associated":[104],"with":[105],"our":[106,145],"easily":[111],"amortized":[112],"as":[113],"size":[115],"input":[118],"set":[120,124],"increases.":[121],"For":[122],"benchmark":[128],"kernels":[129],"studied,":[130],"we":[131],"achieve":[132],"consistent":[133],"significant":[135],"improvements":[137],"(up":[138],"11.4X)":[140],"applying":[142],"vectorization":[143],"using":[144],"transformation":[147],"approach.":[148]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}