{"id":"https://openalex.org/W4391305604","doi":"https://doi.org/10.1109/access.2024.3359296","title":"Gem5-AVX: Extension of the Gem5 Simulator to Support AVX Instruction Sets","display_name":"Gem5-AVX: Extension of the Gem5 Simulator to Support AVX Instruction Sets","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391305604","doi":"https://doi.org/10.1109/access.2024.3359296"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3359296","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3359296","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10415419.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10415419.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100427596","display_name":"Seungmin Lee","orcid":"https://orcid.org/0000-0003-2965-1205"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]},{"id":"https://openalex.org/I878022262","display_name":"Korea Institute of Science & Technology Information","ror":"https://ror.org/01k4yrm29","country_code":"KR","type":"facility","lineage":["https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098","https://openalex.org/I878022262"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seungmin Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea","Korea Institute of Science and Technology Information (KISTI), Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"Korea Institute of Science and Technology Information (KISTI), Daejeon, South Korea","institution_ids":["https://openalex.org/I878022262"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088551237","display_name":"Youngsok Kim","orcid":"https://orcid.org/0000-0002-1015-9969"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngsok Kim","raw_affiliation_strings":["Department of Computer Science, Yonsei University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003405959","display_name":"Dukyun Nam","orcid":"https://orcid.org/0000-0003-1023-7311"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dukyun Nam","raw_affiliation_strings":["School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Kyungpook National University, Daegu, South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635272","display_name":"Jong Kim","orcid":"https://orcid.org/0000-0002-0484-0790"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pohang University of Science and Technology (POSTECH), Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100427596"],"corresponding_institution_ids":["https://openalex.org/I123900574","https://openalex.org/I878022262"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.9297,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84995642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"20767","last_page":"20778"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9994999766349792,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.7725112438201904},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.713007926940918},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6391149163246155},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.57276451587677},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5696209669113159},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.5270457863807678},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3063468933105469},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.23516392707824707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725112438201904},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.713007926940918},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6391149163246155},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.57276451587677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5696209669113159},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.5270457863807678},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3063468933105469},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.23516392707824707},{"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":2,"locations":[{"id":"doi:10.1109/access.2024.3359296","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3359296","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10415419.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6875dea4b3a648d4a7e5ac745b041726","is_oa":true,"landing_page_url":"https://doaj.org/article/6875dea4b3a648d4a7e5ac745b041726","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 20767-20778 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3359296","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3359296","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10415419.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1039416476","display_name":null,"funder_award_id":"CRC 21011","funder_id":"https://openalex.org/F4320325370","funder_display_name":"National Research Council of Science and Technology"},{"id":"https://openalex.org/G1927813677","display_name":null,"funder_award_id":"CRC 21011","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G4734302306","display_name":null,"funder_award_id":"21011","funder_id":"https://openalex.org/F4320325370","funder_display_name":"National Research Council of Science and Technology"},{"id":"https://openalex.org/G6844502353","display_name":null,"funder_award_id":"CRC 21011","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7685055460","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320325370","display_name":"National Research Council of Science and Technology","ror":"https://ror.org/058rymf81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391305604.pdf","grobid_xml":"https://content.openalex.org/works/W4391305604.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W123140645","https://openalex.org/W182691100","https://openalex.org/W1983157164","https://openalex.org/W2044206819","https://openalex.org/W2103884786","https://openalex.org/W2108755937","https://openalex.org/W2113167168","https://openalex.org/W2147657366","https://openalex.org/W2164264749","https://openalex.org/W2555860941","https://openalex.org/W2623993198","https://openalex.org/W2946072469","https://openalex.org/W2954241526","https://openalex.org/W2982848142","https://openalex.org/W3036557299","https://openalex.org/W3102724434","https://openalex.org/W3157391606","https://openalex.org/W3211923058","https://openalex.org/W4205396740","https://openalex.org/W4229666556","https://openalex.org/W4245923077","https://openalex.org/W4360605760","https://openalex.org/W6602296379","https://openalex.org/W6751518279","https://openalex.org/W6778035576"],"related_works":["https://openalex.org/W2129537883","https://openalex.org/W2911551207","https://openalex.org/W2291920536","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W4226140811","https://openalex.org/W1603583590","https://openalex.org/W4225987401","https://openalex.org/W4236526691","https://openalex.org/W2003690377"],"abstract_inverted_index":{"Recent":[0],"commodity":[1],"x86":[2,46,64],"CPUs":[3],"still":[4],"dominate":[5],"the":[6,57,116,120,158,197,207],"majority":[7],"of":[8,12,35,56,84,98,119,160,168,209,222],"supercomputers":[9],"and":[10,33,82,89,103,123,128,134,171,187,202,224,237,241],"most":[11],"them":[13],"implement":[14],"vector":[15,78,141,144],"architectures":[16],"to":[17,109,166,213],"support":[18,44],"single":[19],"instruction":[20],"multiple":[21],"data":[22],"(SIMD).":[23],"Although":[24],"research":[25],"for":[26,69,87,239],"architectural":[27],"exploration":[28],"requires":[29],"computer":[30],"architecture":[31],"simulators":[32,36],"number":[34],"have":[37],"been":[38],"developed,":[39],"only":[40],"a":[41],"few":[42],"tools":[43],"recent":[45,63],"SIMD":[47,65,100],"instructions.":[48,92],"This":[49],"paper":[50],"describes":[51],"gem5-AVX,":[52],"an":[53],"extended":[54],"version":[55],"gem5":[58,201],"simulator":[59],"that":[60,106],"enables":[61],"simulating":[62],"extensions,":[66],"especially":[67],"targeted":[68],"high":[70],"performance":[71],"computing":[72],"(HPC).":[73],"The":[74,200],"gem5-AVX":[75,161,203],"comprises":[76],"advanced":[77],"extension":[79],"(AVX),":[80],"AVX2":[81,122],"subsets":[83],"AVX-512,":[85],"except":[86],"cache":[88],"memory":[90,153],"management":[91],"Moreover,":[93],"it":[94],"covers":[95],"full":[96],"set":[97],"streaming":[99],"extensions":[101,105],"(SSE)":[102],"subsequent":[104],"are":[107,193,204],"required":[108],"simulate":[110,115],"HPC":[111,198],"workloads.":[112],"It":[113],"can":[114],"key":[117],"features":[118],"AVX,":[121],"AVX-512":[124],"such":[125],"as":[126],"256":[127],"512":[129],"bits":[130],"wide":[131],"registers,":[132,148],"three":[133],"four":[135],"operands":[136],"syntax,":[137],"fused":[138],"multiply-add":[139],"(FMA),":[140],"gather-scatter":[142],"using":[143],"scale-index-base":[145],"(VSIB),":[146],"mask":[147],"embedded":[149],"broadcasting,":[150],"compressed":[151],"displacement":[152],"addressing":[154],"mode.":[155],"We":[156],"evaluate":[157],"accuracy":[159],"by":[162],"comparing":[163],"its":[164],"results":[165],"those":[167],"real":[169],"hardware":[170],"Intel\u2019s":[172],"software":[173],"development":[174],"emulator":[175],"(SDE)":[176],"running":[177],"benchmark":[178,190,211],"suites,i.e.,":[179],"high-performance":[180,183],"linpack":[181],"(HPL),":[182],"conjugate":[184],"gradient":[185],"(HPCG)":[186],"NAS":[188],"parallel":[189],"(NPB)":[191],"which":[192,231],"representative":[194],"programs":[195],"in":[196],"field.":[199],"compared":[205],"with":[206,217],"speed-up":[208],"HPL":[210],"according":[212],"configuration":[214],"combinations.":[215],"Gem5-AVX,":[216],"mean":[218,233],"absolute":[219,234],"percentage":[220],"errors":[221,235],"7.3-9.2%":[223],"9.2-11.9%,":[225],"is":[226],"more":[227],"accurate":[228],"than":[229],"gem5,":[230],"shows":[232],"17.9-21.5%":[236],"19.7-29.7%":[238],"Haswell":[240],"Skylake":[242],"processors,":[243],"respectively.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}