{"id":"https://openalex.org/W2020102020","doi":"https://doi.org/10.1109/iscas.2010.5537700","title":"Permutation optimization for SIMD devices","display_name":"Permutation optimization for SIMD devices","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2020102020","doi":"https://doi.org/10.1109/iscas.2010.5537700","mag":"2020102020"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2010.5537700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2010.5537700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2010 IEEE International Symposium on Circuits and Systems","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/A5044840341","display_name":"Libo Huang","orcid":"https://orcid.org/0000-0001-7878-3998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Libo Huang","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China","School of Computer National University of Defense Technology Changsha 410073 China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer National University of Defense Technology Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101790620","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-9043-2998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China","School of Computer National University of Defense Technology Changsha 410073 China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer National University of Defense Technology Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047295889","display_name":"Zhiying Wang","orcid":"https://orcid.org/0000-0003-3339-3085"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiying Wang","raw_affiliation_strings":["School of Computer, National University of Defense Technology, Changsha, China","School of Computer National University of Defense Technology Changsha 410073 China"],"affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"School of Computer National University of Defense Technology Changsha 410073 China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5044840341"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.7491,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7202467,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3849","last_page":"3852"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.9243559241294861},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8415144085884094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.802221953868866},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7041534185409546},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6441791653633118},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.6221011281013489},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6147637963294983},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5376976132392883},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.43827542662620544},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08289352059364319}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9243559241294861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415144085884094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.802221953868866},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7041534185409546},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6441791653633118},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.6221011281013489},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6147637963294983},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5376976132392883},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.43827542662620544},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08289352059364319},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2010.5537700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2010.5537700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2010 IEEE International Symposium on Circuits and Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1531065716","https://openalex.org/W1555915743","https://openalex.org/W1965638741","https://openalex.org/W1976158744","https://openalex.org/W2032094184","https://openalex.org/W2069703635","https://openalex.org/W2099404643","https://openalex.org/W2111394443","https://openalex.org/W2118533539","https://openalex.org/W2137249790","https://openalex.org/W2167639788","https://openalex.org/W2725179571","https://openalex.org/W4242539338","https://openalex.org/W4245987756","https://openalex.org/W6658560632"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W1991844655","https://openalex.org/W2105992728","https://openalex.org/W1501159154","https://openalex.org/W1229628","https://openalex.org/W2468095077","https://openalex.org/W2009213655","https://openalex.org/W4400951174","https://openalex.org/W74409296"],"abstract_inverted_index":{"Single-instruction-multiple-data":[0],"(SIMD)":[1],"devices":[2],"have":[3],"been":[4],"widely":[5],"incorporated":[6],"into":[7],"baseline":[8,75],"instruction":[9],"level":[10,19],"parallelism":[11,20,42],"(ILP)":[12],"processors":[13,76],"to":[14,32,65,72,100],"enable":[15],"more":[16],"efficient":[17],"data":[18,46,93],"(DLP)":[21],"support.":[22],"This":[23,105],"paper":[24],"addresses":[25],"the":[26,30,34,74,92,101],"unsolved":[27],"problem":[28],"of":[29],"need":[31],"permute":[33],"SIMD":[35,128],"elements":[36],"packed":[37],"in":[38,98,109],"registers":[39],"for":[40,52],"maximum":[41],"performance.":[43],"An":[44],"implicit":[45],"permutation":[47,55,78,96],"(IDP)":[48],"mechanism":[49],"is":[50,71,107,123],"proposed":[51],"handling":[53],"various":[54],"operations":[56],"without":[57],"performance":[58,117],"overhead.":[59],"Various":[60],"ways":[61],"can":[62,119],"be":[63,120],"used":[64],"implement":[66],"IDP":[67],"mechanism.":[68],"One":[69],"way":[70],"modify":[73],"with":[77],"vector":[79],"register":[80],"file":[81],"(PVRF)":[82],"and":[83,111],"associated":[84],"new":[85],"extended":[86],"instructions.":[87],"The":[88],"PVRF":[89],"allows":[90],"accessing":[91],"by":[94],"using":[95],"pattern":[97],"addition":[99],"existing":[102],"row":[103],"pattern.":[104],"method":[106],"described":[108],"detail":[110],"experimental":[112],"results":[113],"show":[114],"that":[115],"distinct":[116],"speedup":[118],"achieved,":[121],"which":[122],"47%":[124],"higher":[125],"than":[126],"current":[127],"techniques":[129],"on":[130],"average.":[131]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
