{"id":"https://openalex.org/W190064633","doi":null,"title":"Exploiting superword-level locality in multimedia extension architectures","display_name":"Exploiting superword-level locality in multimedia extension architectures","publication_year":2003,"publication_date":"2003-04-01","ids":{"openalex":"https://openalex.org/W190064633","mag":"190064633"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.8317","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jilp.org/vol5/v5paper4.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5023732376","display_name":"Jaewook Shin","orcid":"https://orcid.org/0000-0002-0342-1834","observed_orcids":["https://orcid.org/0000-0002-0342-1834"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaewook Shin","raw_affiliation_strings":["University of Southern California"],"raw_orcid":"https://orcid.org/0000-0002-0342-1834","affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057351225","display_name":"Jacqueline Chame","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacqueline Chame","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary W. Hall","orcid":"https://orcid.org/0000-0002-3058-7573","observed_orcids":["https://orcid.org/0000-0002-3058-7573"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Southern California"],"raw_orcid":"https://orcid.org/0000-0002-3058-7573","affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.7731,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.75497973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"5","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/simd-instruction-set","display_name":"SIMD instruction set","score":0.574999988079071},{"id":"https://openalex.org/keywords/sse","display_name":"SSE","score":0.7089999914169312},{"id":"https://openalex.org/keywords/altivec","display_name":"AltiVec","score":0.9990000128746033},{"id":"https://openalex.org/keywords/register-reuse","display_name":"register reuse","score":0.6980000138282776},{"id":"https://openalex.org/keywords/spatial-reuse","display_name":"spatial reuse","score":0.7799999713897705},{"id":"https://openalex.org/keywords/compiler-optimization","display_name":"compiler optimization","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9078435897827148},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7360963225364685},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6589170694351196},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6508002281188965},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6373898983001709},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.6190600395202637},{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.6042566299438477},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5879338383674622},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5456562042236328},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.522646427154541},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.4794958233833313},{"id":"https://openalex.org/C156972235","wikidata":"https://www.wikidata.org/wiki/Q1443434","display_name":"Instructions per cycle","level":3,"score":0.43132802844047546},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4077829122543335},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3514658510684967},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3352307677268982},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.0766344666481018},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.8317","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.8317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jilp.org/vol5/v5paper4.pdf","raw_type":"text"},{"id":"mag:190064633","doi":null,"is_oa":false,"landing_page_url":"https://www.jilp.org/vol5/v5paper4.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S182003359","display_name":"The journal of instruction-level parallelism","issn_l":"1942-9525","issn":["1942-9525"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"\u0098The \u009cjournal of instruction-level parallelism","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W530071","https://openalex.org/W149469918","https://openalex.org/W204452631","https://openalex.org/W262467192","https://openalex.org/W1500117749","https://openalex.org/W1502340801","https://openalex.org/W1562841074","https://openalex.org/W1600567712","https://openalex.org/W1843640069","https://openalex.org/W1966708457","https://openalex.org/W1969489929","https://openalex.org/W1984972320","https://openalex.org/W2030934436","https://openalex.org/W2063249715","https://openalex.org/W2077903526","https://openalex.org/W2078845975","https://openalex.org/W2098220211","https://openalex.org/W2111394443","https://openalex.org/W2115667390","https://openalex.org/W2119609467","https://openalex.org/W2124969960","https://openalex.org/W2130034571","https://openalex.org/W2137249790","https://openalex.org/W2137857636","https://openalex.org/W2138007781","https://openalex.org/W2142252451","https://openalex.org/W2147423491","https://openalex.org/W2158158791","https://openalex.org/W2159309967","https://openalex.org/W2164431468","https://openalex.org/W2244841219"],"related_works":["https://openalex.org/W7100113529","https://openalex.org/W7097493232","https://openalex.org/W7099393984","https://openalex.org/W2474328930","https://openalex.org/W3016220765","https://openalex.org/W3006518470","https://openalex.org/W7096634262","https://openalex.org/W7099391446","https://openalex.org/W2115089829","https://openalex.org/W2256807614"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,158],"describe":[4,107],"an":[5,108],"algorithm":[6],"and":[7,21,97,134,157],"implementation":[8,109],"of":[9,33,110,126,162],"locality":[10],"optimizations":[11,85],"for":[12],"architectures":[13],"with":[14,114],"instruction":[15],"sets":[16],"such":[17],"as":[18,44,151],"Intel's":[19],"SSE":[20],"Motorola's":[22],"AltiVec":[23],"that":[24,117],"support":[25],"operations":[26],"on":[27,66,130,147],"superwords,":[28],"i.e.,":[29],"aggregate":[30],"objects":[31],"consisting":[32],"several":[34],"machine":[35],"words.":[36],"We":[37,106,122],"treat":[38],"the":[39,91,103,148,160],"large":[40],"superword":[41,57],"register":[42],"file":[43],"a":[45,115,124],"compiler-controlled":[46],"cache,":[47,90],"thus":[48],"avoiding":[49],"unnecessary":[50],"memory":[51,163],"accesses":[52],"by":[53],"exploiting":[54,67],"reuse":[55,68,88],"in":[56,69,89,102],"registers.":[58],"This":[59],"research":[60],"is":[61],"distinguished":[62],"from":[63,143],"previous":[64],"work":[65],"scalar":[70],"registers":[71,101],"because":[72],"it":[73],"considers":[74],"not":[75],"only":[76],"temporal":[77],"but":[78],"also":[79,94],"spatial":[80],"reuse.":[81],"As":[82],"compared":[83,152],"to":[84,86,145,153],"exploit":[87],"compiler":[92,116],"must":[93],"manage":[95],"replacement,":[96],"thus,":[98],"explicitly":[99],"name":[100],"generated":[104],"code.":[105],"our":[111],"approach":[112],"integrated":[113],"exploits":[118],"superword-level":[119],"parallelism":[120],"(SLP).":[121],"present":[123],"set":[125],"results":[127,139],"derived":[128],"automatically":[129],"4":[131],"multimedia":[132],"kernels":[133],"2":[135],"scientific":[136],"benchmarks.":[137],"Our":[138],"show":[140],"speedups":[141],"ranging":[142],"1.3":[144],"3.1X":[146],"6":[149],"programs":[150],"using":[154],"SLP":[155],"alone,":[156],"eliminate":[159],"majority":[161],"accesses.":[164]},"counts_by_year":[{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}
