{"id":"https://openalex.org/W2787850818","doi":"https://doi.org/10.1145/3173456","title":"Improving SIMD Parallelism via Dynamic Binary Translation","display_name":"Improving SIMD Parallelism via Dynamic Binary Translation","publication_year":2018,"publication_date":"2018-02-12","ids":{"openalex":"https://openalex.org/W2787850818","doi":"https://doi.org/10.1145/3173456","mag":"2787850818"},"language":"en","primary_location":{"id":"doi:10.1145/3173456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173456","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-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/A5058175385","display_name":"Ding\u2010Yong Hong","orcid":"https://orcid.org/0000-0002-7649-7581"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ding-Yong Hong","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673297","display_name":"Yuping Liu","orcid":"https://orcid.org/0009-0000-0222-6845"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Ping Liu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031659418","display_name":"Sheng\u2010Yu Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sheng-Yu Fu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103369909","display_name":"Jan\u2010Jan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jan-Jan Wu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017207899","display_name":"Wei\u2010Chung Hsu","orcid":"https://orcid.org/0000-0002-0833-7981"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Chung Hsu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5364,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.90386245,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"17","issue":"3","first_page":"1","last_page":"27"},"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/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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983000159263611,"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":0.9382893443107605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8702182769775391},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8336437940597534},{"id":"https://openalex.org/keywords/binary-translation","display_name":"Binary translation","score":0.7557774782180786},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.690362811088562},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.514628529548645},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43838435411453247},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10034701228141785},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.05870896577835083}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9382893443107605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8702182769775391},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8336437940597534},{"id":"https://openalex.org/C2778971978","wikidata":"https://www.wikidata.org/wiki/Q2287075","display_name":"Binary translation","level":3,"score":0.7557774782180786},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.690362811088562},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.514628529548645},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43838435411453247},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10034701228141785},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.05870896577835083},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3173456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3173456","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5432117592","display_name":null,"funder_award_id":"MOST-106-2218-E-002-040","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W190064633","https://openalex.org/W983986834","https://openalex.org/W1495550651","https://openalex.org/W1522250664","https://openalex.org/W1603583590","https://openalex.org/W1605940800","https://openalex.org/W1930382598","https://openalex.org/W1975594295","https://openalex.org/W2011393414","https://openalex.org/W2037929850","https://openalex.org/W2055674455","https://openalex.org/W2072737419","https://openalex.org/W2073944597","https://openalex.org/W2091675250","https://openalex.org/W2104378884","https://openalex.org/W2107563064","https://openalex.org/W2110138575","https://openalex.org/W2111394443","https://openalex.org/W2113167168","https://openalex.org/W2114368073","https://openalex.org/W2117115928","https://openalex.org/W2121176848","https://openalex.org/W2127691752","https://openalex.org/W2127890955","https://openalex.org/W2143375055","https://openalex.org/W2147654959","https://openalex.org/W2148865465","https://openalex.org/W2148947321","https://openalex.org/W2153185479","https://openalex.org/W2156858199","https://openalex.org/W2157074753","https://openalex.org/W2161992906","https://openalex.org/W2167786944","https://openalex.org/W2171262795","https://openalex.org/W2244555269","https://openalex.org/W2288740281","https://openalex.org/W2294933397","https://openalex.org/W2333659671","https://openalex.org/W2566431638","https://openalex.org/W2574006361","https://openalex.org/W2600258283","https://openalex.org/W4231002400","https://openalex.org/W4238502383","https://openalex.org/W4239813889","https://openalex.org/W4240091400"],"related_works":["https://openalex.org/W1964586167","https://openalex.org/W2369102298","https://openalex.org/W2129537883","https://openalex.org/W2766777357","https://openalex.org/W3005677086","https://openalex.org/W2479669872","https://openalex.org/W2166847391","https://openalex.org/W2911551207","https://openalex.org/W4236526691","https://openalex.org/W2003690377"],"abstract_inverted_index":{"Recent":[0],"trends":[1],"in":[2,19,48],"SIMD":[3,14,74,97,116],"architecture":[4,38],"have":[5,16],"tended":[6],"toward":[7],"longer":[8],"vector":[9,21,45],"lengths,":[10],"and":[11,43,104,131,148,159],"more":[12],"enhanced":[13,44],"features":[15],"been":[17],"introduced":[18],"newer":[20],"instruction":[22],"sets.":[23],"However,":[24],"legacy":[25],"or":[26],"proprietary":[27],"applications":[28],"compiled":[29],"with":[30],"short-SIMD":[31,67,78,91],"ISA":[32],"cannot":[33],"benefit":[34],"from":[35],"the":[36,121,125],"long-SIMD":[37,108],"that":[39,65,86,143],"supports":[40],"improved":[41],"parallelism":[42],"primitives,":[46],"resulting":[47],"only":[49],"a":[50,60,83],"small":[51],"fraction":[52],"of":[53,72,90,146],"potential":[54],"peak":[55],"performance.":[56],"This":[57],"article":[58],"presents":[59],"dynamic":[61,136],"binary":[62,126],"translation":[63,129],"technique":[64],"enables":[66],"binaries":[68],"to":[69,93,107,114,156],"exploit":[70],"benefits":[71],"new":[73],"architectures":[75],"by":[76,124],"rewriting":[77],"loop":[79,98,137,162],"code.":[80],"We":[81],"propose":[82],"general":[84,133],"approach":[85,134],"translates":[87,106],"loops":[88],"consisting":[89],"instructions":[92],"machine-independent":[94],"IR,":[95],"conducts":[96],"transformation/optimization":[99],"at":[100],"this":[101],"IR":[102],"level,":[103],"finally":[105],"instructions.":[109],"Two":[110],"solutions":[111],"are":[112,150],"presented":[113],"enforce":[115],"load/store":[117],"alignment,":[118],"one":[119,132],"for":[120,152],"problem":[122],"caused":[123],"translator\u2019s":[127],"internal":[128],"condition":[130],"using":[135],"peeling":[138],"optimization.":[139],"Benchmark":[140],"results":[141],"show":[142],"average":[144],"speedups":[145],"1.51\u00d7":[147],"2.48\u00d7":[149],"achieved":[151],"an":[153],"ARM":[154],"NEON":[155],"x86":[157,160],"AVX2":[158],"AVX-512":[161],"transformation,":[163],"respectively.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
