{"id":"https://openalex.org/W1976214698","doi":"https://doi.org/10.1587/elex.10.20130798","title":"Decoupled iteration mapping: improving dependency-loop performance on SIMD processors","display_name":"Decoupled iteration mapping: improving dependency-loop performance on SIMD processors","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W1976214698","doi":"https://doi.org/10.1587/elex.10.20130798","mag":"1976214698"},"language":"en","primary_location":{"id":"doi:10.1587/elex.10.20130798","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.10.20130798","pdf_url":"https://www.jstage.jst.go.jp/article/elex/10/21/10_10.20130798/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.jstage.jst.go.jp/article/elex/10/21/10_10.20130798/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087185487","display_name":"Hui Yang","orcid":"https://orcid.org/0000-0002-2867-5574"},"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":"Hui Yang","raw_affiliation_strings":["College of Computer, National University of Defense Technology","College of Computer, National University of Defense Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644317","display_name":"Shuming Chen","orcid":"https://orcid.org/0000-0003-4441-2202"},"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":"Shuming Chen","raw_affiliation_strings":["College of Computer, National University of Defense Technology","College of Computer, National University of Defense Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109218335","display_name":"Jianghua Wan","orcid":null},"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":"Jianghua Wan","raw_affiliation_strings":["College of Computer, National University of Defense Technology","College of Computer, National University of Defense Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039583115","display_name":"Huanyao Dai","orcid":"https://orcid.org/0009-0002-5797-6584"},"institutions":[{"id":"https://openalex.org/I72565114","display_name":"Luoyang Institute of Science and Technology","ror":"https://ror.org/04nraex26","country_code":"CN","type":"education","lineage":["https://openalex.org/I72565114"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanyao Dai","raw_affiliation_strings":["Luoyang Electronic Equipment Test Center of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luoyang Electronic Equipment Test Center of China","institution_ids":["https://openalex.org/I72565114"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11073193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"21","first_page":"20130798","last_page":"20130798"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9968000054359436,"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/instruction-prefetch","display_name":"Instruction prefetch","score":0.8581196069717407},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8469454050064087},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.81414794921875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7917640209197998},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5801945328712463},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5413662195205688},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.49324744939804077},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.46331357955932617},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.45057258009910583},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4397146999835968},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.41011151671409607},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32117384672164917},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15441545844078064},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.10975143313407898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0895993709564209}],"concepts":[{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.8581196069717407},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8469454050064087},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.81414794921875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917640209197998},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5801945328712463},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5413662195205688},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.49324744939804077},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.46331357955932617},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.45057258009910583},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4397146999835968},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.41011151671409607},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32117384672164917},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15441545844078064},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.10975143313407898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0895993709564209},{"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:10.1587/elex.10.20130798","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.10.20130798","pdf_url":"https://www.jstage.jst.go.jp/article/elex/10/21/10_10.20130798/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/elex.10.20130798","is_oa":true,"landing_page_url":"https://doi.org/10.1587/elex.10.20130798","pdf_url":"https://www.jstage.jst.go.jp/article/elex/10/21/10_10.20130798/_pdf","source":{"id":"https://openalex.org/S207433681","display_name":"IEICE Electronics Express","issn_l":"1349-2543","issn":["1349-2543","1349-9467"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Electronics Express","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6505718541","display_name":"\u591a\u6838\u591a\u7ebf\u7a0bDSP\u9002\u5e94\u6027\u5b58\u50a8\u7ed3\u6784\u7814\u7a76","funder_award_id":"61070036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8960961476","display_name":null,"funder_award_id":"61301236","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1976214698.pdf","grobid_xml":"https://content.openalex.org/works/W1976214698.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1974986661","https://openalex.org/W2026034142","https://openalex.org/W2044831861","https://openalex.org/W2093143612","https://openalex.org/W2127306778"],"related_works":["https://openalex.org/W1509422975","https://openalex.org/W1992352827","https://openalex.org/W3016777042","https://openalex.org/W2994245508","https://openalex.org/W3173074201","https://openalex.org/W4242172182","https://openalex.org/W2082875307","https://openalex.org/W4237780868","https://openalex.org/W4285302443","https://openalex.org/W2069137912"],"abstract_inverted_index":{"Wide":[0],"Single":[1],"Instruction":[2,70,79],"Multiple":[3],"Data":[4,85],"(SIMD)":[5],"architectures":[6],"are":[7,24],"very":[8],"important":[9],"in":[10],"the":[11,47,60,93],"compute-intensive":[12],"applications,":[13],"but":[14],"less":[15],"efficient":[16],"for":[17],"applications":[18],"with":[19,103],"cross-iteration":[20,43],"dependency":[21,44],"loops":[22],"which":[23,51],"difficult":[25],"to":[26],"parallelize":[27],"and":[28,83],"vectorize.":[29],"This":[30],"paper":[31],"introduces":[32],"Decoupled":[33],"Iteration":[34],"Mapping":[35],"(DIM),":[36],"a":[37,42,66,74,84,104],"technique":[38],"that":[39],"dynamically":[40],"maps":[41],"loop":[45],"onto":[46],"improved":[48],"SIMD":[49],"architecture":[50,62],"achieved":[52],"multicore-like":[53],"thread-parallel":[54],"performance.":[55],"The":[56],"minor":[57],"modification":[58],"on":[59],"baseline":[61],"is":[63],"composed":[64],"of":[65,106],"Prefetch":[67],"Unit":[68,77,81],"&":[69,78],"Buffer":[71,86],"Array":[72],"(PU&IBA),":[73],"Loop":[75],"Control":[76],"Dispatch":[80],"(LCU&IDU),":[82],"Chain":[87],"(DBC).":[88],"Experimental":[89],"results":[90],"show":[91],"that,":[92],"proposed":[94],"DIM":[95],"scheme":[96],"can":[97],"achieve":[98],"average":[99],"3.04x":[100],"performance":[101],"speedup":[102],"cost":[105],"only":[107],"6.44%":[108],"area":[109],"overhead.":[110]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
