{"id":"https://openalex.org/W2099404643","doi":"https://doi.org/10.1145/996841.996853","title":"Vectorization for SIMD architectures with alignment constraints","display_name":"Vectorization for SIMD architectures with alignment constraints","publication_year":2004,"publication_date":"2004-06-09","ids":{"openalex":"https://openalex.org/W2099404643","doi":"https://doi.org/10.1145/996841.996853","mag":"2099404643"},"language":"en","primary_location":{"id":"doi:10.1145/996841.996853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/996841.996853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGPLAN 2004 conference on Programming language design and implementation","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/A5068763494","display_name":"Alexandre E. Eichenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alexandre E. Eichenberger","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108630261","display_name":"Peng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Wu","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110091665","display_name":"Kevin O\u2019Brien","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin O'Brien","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068763494"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":13.7328,"has_fulltext":false,"cited_by_count":200,"citation_normalized_percentile":{"value":0.99316907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"93"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9965999722480774,"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/simd","display_name":"SIMD","score":0.8870830535888672},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8488985896110535},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8101645112037659},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.673821210861206},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39838907122612},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33584633469581604}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8870830535888672},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8488985896110535},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101645112037659},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.673821210861206},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39838907122612},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33584633469581604}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/996841.996853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/996841.996853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGPLAN 2004 conference on Programming language design and implementation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W127897580","https://openalex.org/W1495550651","https://openalex.org/W1591319746","https://openalex.org/W1856176155","https://openalex.org/W2037929850","https://openalex.org/W2069703635","https://openalex.org/W2111394443","https://openalex.org/W2135736783","https://openalex.org/W2137249790","https://openalex.org/W2137857636","https://openalex.org/W2143964612","https://openalex.org/W2147423491","https://openalex.org/W2162018717","https://openalex.org/W6659810996"],"related_works":["https://openalex.org/W2378016289","https://openalex.org/W2890419659","https://openalex.org/W2787898679","https://openalex.org/W2601539487","https://openalex.org/W4245302940","https://openalex.org/W4224215426","https://openalex.org/W2088893383","https://openalex.org/W2020484966","https://openalex.org/W2807356003","https://openalex.org/W2388790079"],"abstract_inverted_index":{"When":[0],"vectorizing":[1,32],"for":[2,160,167,173],"SIMD":[3],"architectures":[4],"that":[5,18,62,126],"are":[6,38,187],"commonly":[7],"employed":[8],"by":[9,91],"today's":[10],"multimedia":[11],"extensions,":[12],"one":[13],"of":[14,23,44,69,75,108,176,182],"the":[15,21,67,87,92,96,106,114,141,183],"new":[16],"challenges":[17],"arise":[19],"is":[20,78],"handling":[22],"memory":[24,36,52,71,129,185],"alignment.":[25],"Prior":[26],"research":[27],"has":[28],"focused":[29],"primarily":[30],"on":[31],"loops":[33,65,177],"where":[34,178],"all":[35],"references":[37,125,186],"properly":[39],"aligned.":[40],"An":[41],"important":[42],"aspect":[43],"this":[45],"problem,":[46],"namely,":[47],"how":[48],"to":[49,79,85,104,138],"vectorize":[50],"misaligned":[51,70],"references,":[53],"still":[54],"remains":[55],"unaddressed.This":[56],"paper":[57],"presents":[58],"a":[59,146,174],"compilation":[60],"scheme":[61,136],"systematically":[63],"vectorizes":[64],"in":[66,83],"presence":[68],"references.":[72],"The":[73],"core":[74],"our":[76,117],"technique":[77],"automatically":[80],"reorganize":[81],"data":[82,97,109,143,162,169],"registers":[84],"satisfy":[86],"alignment":[88],"requirement":[89],"imposed":[90],"hardware.":[93],"To":[94],"reduce":[95],"reorganization":[98,110],"overhead,":[99],"we":[100],"propose":[101],"several":[102],"techniques":[103],"minimize":[105],"number":[107],"operations":[111],"generated.":[112],"During":[113],"code":[115,134],"generation,":[116],"algorithm":[118],"also":[119],"exploits":[120],"temporal":[121],"reuse":[122],"when":[123],"aligning":[124],"access":[127,149],"contiguous":[128],"across":[130],"loop":[131],"iterations.":[132],"Our":[133],"generation":[135],"guarantees":[137],"never":[139],"load":[140],"same":[142],"associated":[144],"with":[145],"single":[147],"static":[148,184],"twice.":[150],"Experimental":[151],"results":[152],"indicate":[153],"near":[154],"peak":[155],"speedup":[156],"factors,":[157],"e.g.,":[158],"3.71":[159],"4":[161],"per":[163,170],"vector":[164],"and":[165],"6.06":[166],"8":[168],"vector,":[171],"respectively,":[172],"set":[175],"75%":[179],"or":[180],"more":[181],"misaligned.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"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":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":18}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}