{"id":"https://openalex.org/W2900476201","doi":"https://doi.org/10.1109/sbcci.2018.8533261","title":"Improving Software Productivity and Performance Through a Transparent SIMD Execution","display_name":"Improving Software Productivity and Performance Through a Transparent SIMD Execution","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2900476201","doi":"https://doi.org/10.1109/sbcci.2018.8533261","mag":"2900476201"},"language":"en","primary_location":{"id":"doi:10.1109/sbcci.2018.8533261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbcci.2018.8533261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 31st Symposium on Integrated Circuits and Systems Design (SBCCI)","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/A5006099481","display_name":"Michael Guilherme Jordan","orcid":"https://orcid.org/0000-0002-5776-2626"},"institutions":[{"id":"https://openalex.org/I33501960","display_name":"Universidade Federal de Santa Maria","ror":"https://ror.org/01b78mz79","country_code":"BR","type":"education","lineage":["https://openalex.org/I33501960"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Michael Guilherme Jordan","raw_affiliation_strings":["Electronics and Computing Department, Federal University of Santa Maria, Santa Maria, Brazil"],"affiliations":[{"raw_affiliation_string":"Electronics and Computing Department, Federal University of Santa Maria, Santa Maria, Brazil","institution_ids":["https://openalex.org/I33501960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084253759","display_name":"Tiago Knorst","orcid":"https://orcid.org/0000-0002-6717-5660"},"institutions":[{"id":"https://openalex.org/I33501960","display_name":"Universidade Federal de Santa Maria","ror":"https://ror.org/01b78mz79","country_code":"BR","type":"education","lineage":["https://openalex.org/I33501960"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Tiago Knorst","raw_affiliation_strings":["Electronics and Computing Department, Federal University of Santa Maria, Santa Maria, Brazil"],"affiliations":[{"raw_affiliation_string":"Electronics and Computing Department, Federal University of Santa Maria, Santa Maria, Brazil","institution_ids":["https://openalex.org/I33501960"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057716015","display_name":"Mateus Beck Rutzig","orcid":"https://orcid.org/0000-0002-2836-2009"},"institutions":[{"id":"https://openalex.org/I33501960","display_name":"Universidade Federal de Santa Maria","ror":"https://ror.org/01b78mz79","country_code":"BR","type":"education","lineage":["https://openalex.org/I33501960"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Mateus Beck Rutzig","raw_affiliation_strings":["Electronics and Computing Department, Federal University of Santa Maria, Santa Maria, Brazil"],"affiliations":[{"raw_affiliation_string":"Electronics and Computing Department, Federal University of Santa Maria, Santa Maria, Brazil","institution_ids":["https://openalex.org/I33501960"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006099481"],"corresponding_institution_ids":["https://openalex.org/I33501960"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14605231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1","last_page":"6"},"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/T10904","display_name":"Embedded Systems Design 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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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":0.9198590517044067},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8599796295166016},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8225647211074829},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7348704934120178},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.6070229411125183},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5682075619697571},{"id":"https://openalex.org/keywords/backward-compatibility","display_name":"Backward compatibility","score":0.46132510900497437},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3771218955516815},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3673403263092041},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28223368525505066}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9198590517044067},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8599796295166016},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8225647211074829},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7348704934120178},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6070229411125183},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5682075619697571},{"id":"https://openalex.org/C20574231","wikidata":"https://www.wikidata.org/wiki/Q844605","display_name":"Backward compatibility","level":2,"score":0.46132510900497437},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3771218955516815},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3673403263092041},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28223368525505066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sbcci.2018.8533261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sbcci.2018.8533261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 31st Symposium on Integrated Circuits and Systems Design (SBCCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"},{"id":"https://openalex.org/F4320322502","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado do Rio Grande do Sul","ror":"https://ror.org/05k49za97"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1686420892","https://openalex.org/W1972547624","https://openalex.org/W2005343162","https://openalex.org/W2104508714","https://openalex.org/W2107307723","https://openalex.org/W2125203716","https://openalex.org/W2146188244","https://openalex.org/W2147657366","https://openalex.org/W2153402554","https://openalex.org/W2488840986","https://openalex.org/W3148466761","https://openalex.org/W4232751114","https://openalex.org/W4236272793","https://openalex.org/W4248701878"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2979513934","https://openalex.org/W2090268225","https://openalex.org/W2366442643","https://openalex.org/W2021715972","https://openalex.org/W2761732860"],"abstract_inverted_index":{"Multimedia":[0],"and":[1,54],"DSP":[2],"applications":[3],"have":[4],"been":[5],"widely":[6],"present":[7],"in":[8,31,137],"embedded":[9,33],"devices.":[10],"Due":[11],"to":[12,99],"their":[13],"intrinsic":[14],"nature,":[15],"such":[16,44,57],"application":[17],"domains":[18],"are":[19],"benefited":[20],"from":[21],"Data":[22],"Level":[23],"Parallelism":[24],"(DLP)":[25],"exploitation,":[26],"which":[27,50,62],"is":[28,76],"mostly":[29],"employed":[30],"current":[32],"platforms":[34],"by":[35],"using":[36],"vectorization":[37],"techniques":[38],"extending":[39],"the":[40,97,109,118],"underlying":[41],"ISA.":[42],"However,":[43],"strategy":[45],"relies":[46],"on":[47],"specific":[48,87],"library":[49,88],"affects":[51],"software":[52],"productivity":[53],"compiler":[55],"support,":[56],"as":[58],"ARM":[59,103,134],"auto-vectorization":[60,135],"approach,":[61],"breaks":[63],"binary":[64,131],"compatibility.":[65],"This":[66],"work":[67],"proposes":[68],"a":[69,92,100],"transparent":[70],"Dynamic":[71,126],"SIMD":[72,127],"Assembler":[73],"(DSA)":[74],"that":[75,108],"capable":[77],"of":[78,115],"detecting":[79],"vectorizable":[80],"code":[81],"regions":[82],"at":[83],"runtime":[84],"without":[85],"requiring":[86],"or":[89],"compilers.":[90],"As":[91],"case":[93],"study,":[94],"we":[95],"coupled":[96],"DSA":[98],"128-bit":[101],"wide":[102],"NEON":[104],"Engine.":[105],"Results":[106],"show":[107],"proposed":[110],"approach":[111],"shows":[112],"performance":[113],"improvements":[114],"31%":[116],"over":[117],"original":[119],"execution":[120],"(without":[121],"DLP":[122],"exploitation).":[123],"In":[124],"addition,":[125],"Assembler,":[128],"besides":[129],"keeping":[130],"compatibility,":[132],"outperforms":[133],"technique":[136],"6%.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
