{"id":"https://openalex.org/W2288740281","doi":"https://doi.org/10.1145/2854038.2854054","title":"Exploiting mixed SIMD parallelism by reducing data reorganization overhead","display_name":"Exploiting mixed SIMD parallelism by reducing data reorganization overhead","publication_year":2016,"publication_date":"2016-02-29","ids":{"openalex":"https://openalex.org/W2288740281","doi":"https://doi.org/10.1145/2854038.2854054","mag":"2288740281"},"language":"en","primary_location":{"id":"doi:10.1145/2854038.2854054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2854038.2854054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","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/A5100397092","display_name":"Hao Zhou","orcid":"https://orcid.org/0009-0009-3536-7623"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["UNSW, Australia"],"affiliations":[{"raw_affiliation_string":"UNSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024664385","display_name":"Jingling Xue","orcid":"https://orcid.org/0000-0003-0380-3506"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingling Xue","raw_affiliation_strings":["UNSW, Australia"],"affiliations":[{"raw_affiliation_string":"UNSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100397092"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":10.2734,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98703433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"69"},"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/T11181","display_name":"Advanced Data Storage Technologies","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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9972000122070312,"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/parallel-computing","display_name":"Parallel computing","score":0.8787755370140076},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8688992857933044},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.819922924041748},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.7025334239006042},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.6845744252204895},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.6677530407905579},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6033276319503784},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.594281792640686},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.568861186504364},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46573013067245483},{"id":"https://openalex.org/keywords/implicit-parallelism","display_name":"Implicit parallelism","score":0.45530954003334045},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.43419817090034485},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0637819766998291}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8787755370140076},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8688992857933044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819922924041748},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.7025334239006042},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.6845744252204895},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.6677530407905579},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6033276319503784},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.594281792640686},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.568861186504364},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46573013067245483},{"id":"https://openalex.org/C3543717","wikidata":"https://www.wikidata.org/wiki/Q6007302","display_name":"Implicit parallelism","level":4,"score":0.45530954003334045},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.43419817090034485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0637819766998291},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2854038.2854054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2854038.2854054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6631425554","display_name":null,"funder_award_id":"DP110104628","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1966324811","https://openalex.org/W1975594295","https://openalex.org/W1991009705","https://openalex.org/W2011393414","https://openalex.org/W2013156670","https://openalex.org/W2020166439","https://openalex.org/W2022711417","https://openalex.org/W2037929850","https://openalex.org/W2040281526","https://openalex.org/W2099404643","https://openalex.org/W2100579514","https://openalex.org/W2104378884","https://openalex.org/W2108556169","https://openalex.org/W2111394443","https://openalex.org/W2124273985","https://openalex.org/W2135736783","https://openalex.org/W2137249790","https://openalex.org/W2137857636","https://openalex.org/W2147654959","https://openalex.org/W2157273783","https://openalex.org/W2167639788","https://openalex.org/W2294933397","https://openalex.org/W3140469843","https://openalex.org/W4244894488","https://openalex.org/W4245987756","https://openalex.org/W6659810996"],"related_works":["https://openalex.org/W2526302199","https://openalex.org/W2003935582","https://openalex.org/W4240606930","https://openalex.org/W74409296","https://openalex.org/W2105992728","https://openalex.org/W3007272028","https://openalex.org/W2494130044","https://openalex.org/W305742777","https://openalex.org/W2468095077","https://openalex.org/W3189160234"],"abstract_inverted_index":{"Existing":[0],"loop":[1],"vectorization":[2],"techniques":[3],"can":[4],"exploit":[5],"either":[6],"intra-":[7],"or":[8],"inter-iteration":[9],"SIMD":[10,66,87,126],"parallelism":[11,28,63,88,101,127],"alone":[12],"in":[13,68,115],"a":[14,54,79],"code":[15,70],"region":[16,22,41],"if":[17],"one":[18,25,98],"part":[19,38],"of":[20,27,39,47,56,62,100],"the":[21,36,40,44,92,105,141],"vectorized":[23,42],"for":[24,43,83],"type":[26,46,99],"has":[29,112],"data":[30,75,93],"dependences":[31],"(called":[32],"mixed-parallelism-inhibiting":[33,74],"dependences)":[34],"on":[35,121],"other":[37,45],"parallelism.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"consider":[53],"class":[55],"loops":[57],"that":[58,72],"exhibit":[59],"both":[60],"types":[61],"(i.e.,":[64],"mixed":[65,86,125],"parallelism)":[67],"its":[69,137],"regions":[71],"contain":[73],"dependences.":[76],"We":[77,118],"present":[78],"new":[80],"compiler":[81],"approach":[82],"exploiting":[84],"such":[85],"effectively":[89],"by":[90],"reducing":[91],"reorganization":[94],"overhead":[95],"incurred":[96],"when":[97],"is":[102,109],"switched":[103],"to":[104],"other.":[106],"Our":[107],"auto-vectorizer":[108],"simple":[110],"and":[111,131,135],"been":[113],"implemented":[114],"LLVM":[116],"(3.5.0).":[117],"evaluate":[119],"it":[120],"seven":[122],"benchmarks":[123],"with":[124],"selected":[128],"from":[129],"SPEC":[130],"NAS":[132],"benchmark":[133],"suites":[134],"demonstrate":[136],"performance":[138],"advantages":[139],"over":[140],"state-of-the-art.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}