{"id":"https://openalex.org/W2897567971","doi":"https://doi.org/10.1145/3239576.3239620","title":"Loop-nest Auto-vectorization Method Based on Benefit Analysis","display_name":"Loop-nest Auto-vectorization Method Based on Benefit Analysis","publication_year":2018,"publication_date":"2018-06-16","ids":{"openalex":"https://openalex.org/W2897567971","doi":"https://doi.org/10.1145/3239576.3239620","mag":"2897567971"},"language":"en","primary_location":{"id":"doi:10.1145/3239576.3239620","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3239576.3239620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Advances in Image Processing","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/A5070480701","display_name":"Jinyang Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yao Jinyang","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113746674","display_name":"Rongcai Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao Rongcai","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101923797","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0003-0371-8299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang Qi","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076950526","display_name":"Tao Xiaohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Xiaohan","raw_affiliation_strings":["State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070480701"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13163041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"240","last_page":"244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9970999956130981,"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":0.9943000078201294,"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/vectorization","display_name":"Vectorization (mathematics)","score":0.8861498832702637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8420372009277344},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7948745489120483},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6836045384407043},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.671269416809082},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5291866660118103},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37021806836128235},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3584306836128235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06815233826637268}],"concepts":[{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8861498832702637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420372009277344},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7948745489120483},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6836045384407043},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.671269416809082},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5291866660118103},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37021806836128235},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3584306836128235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06815233826637268},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3239576.3239620","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3239576.3239620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Advances in Image Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W2059807497","https://openalex.org/W2069703635","https://openalex.org/W2082875307","https://openalex.org/W2111394443","https://openalex.org/W2154078685","https://openalex.org/W2157273783","https://openalex.org/W2162323496","https://openalex.org/W2296675410","https://openalex.org/W2328032973","https://openalex.org/W2375927271","https://openalex.org/W3016220765"],"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/W2111180768","https://openalex.org/W2366442643","https://openalex.org/W2090268225","https://openalex.org/W2351155539"],"abstract_inverted_index":{"The":[0,23,139],"SIMD":[1,35],"(Single":[2],"Instruction":[3],"Multiple":[4],"Data)":[5],"extension":[6],"component":[7],"has":[8],"been":[9],"widely":[10],"used":[11],"in":[12,87],"modern":[13],"processors":[14],"to":[15,152],"improve":[16],"the":[17,21,34,44,48,57,70,79,88,102,107,115,144,147,153,160],"execution":[18],"efficiency":[19,161],"of":[20,47,65,146],"program.":[22],"mainstream":[24],"compilers":[25,40],"(such":[26],"as":[27,106],"GCC,":[28],"ICC,":[29],"OPEN64,":[30],"etc.)":[31],"have":[32],"supported":[33],"automatic":[36],"vectorization.":[37,129,164],"Most":[38],"current":[39],"can":[41,93],"only":[42],"vectorize":[43],"innermost":[45],"layer":[46],"loop,":[49],"but":[50],"this":[51,63,122],"way":[52],"often":[53],"does":[54],"not":[55],"get":[56],"optimal":[58],"performance":[59],"promotion.":[60],"Aiming":[61],"at":[62],"kind":[64],"problem":[66],"and":[67,85,100,157],"combining":[68],"with":[69],"processor":[71],"architecture,":[72],"a":[73],"loop-nest":[74,96,118,128,163],"vectorization":[75,97],"method":[76,92,126],"based":[77],"on":[78],"benefit":[80,148],"analysis":[81],"model":[82,149],"is":[83],"proposed":[84],"implemented":[86],"GCC":[89],"compiler.":[90],"This":[91,111],"analyze":[94],"different":[95],"schemes":[98],"effectively":[99],"choose":[101],"most":[103],"profitable":[104],"one":[105],"final":[108],"optimization":[109],"scheme.":[110],"article":[112],"first":[113],"reviewed":[114],"researches":[116],"about":[117],"vectorization,":[119],"then":[120],"introduces":[121],"new":[123],"code":[124],"generation":[125],"for":[127,137,162],"Finally,":[130],"we":[131],"use":[132],"several":[133],"common":[134],"application":[135],"examples":[136],"experiment.":[138],"experimental":[140],"results":[141,145],"show":[142],"that":[143],"are":[150],"similar":[151],"actual":[154],"test":[155],"results,":[156],"accordingly":[158],"increase":[159]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}