{"id":"https://openalex.org/W3017116334","doi":"https://doi.org/10.1145/3392032","title":"SIMT-X","display_name":"SIMT-X","publication_year":2020,"publication_date":"2020-05-29","ids":{"openalex":"https://openalex.org/W3017116334","doi":"https://doi.org/10.1145/3392032","mag":"3017116334"},"language":"en","primary_location":{"id":"doi:10.1145/3392032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3392032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3392032","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3392032","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063297401","display_name":"Anita Tino","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA","FR"],"is_corresponding":true,"raw_author_name":"Anita Tino","raw_affiliation_strings":["INRIA, France","PACAP - Pushing Architecture and Compilation for Application Performance (Campus de Beaulieu 35042 Rennes cedex - France)","SFU.ca - Simon Fraser University (8888 University Drive, Burnaby, B.C. Canada V5A 1S6 - Canada)"],"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PACAP - Pushing Architecture and Compilation for Application Performance (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]},{"raw_affiliation_string":"SFU.ca - Simon Fraser University (8888 University Drive, Burnaby, B.C. Canada V5A 1S6 - Canada)","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040945336","display_name":"Caroline Collange","orcid":null},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Caroline Collange","raw_affiliation_strings":["INRIA, France","PACAP - Pushing Architecture and Compilation for Application Performance (Campus de Beaulieu 35042 Rennes cedex - France)"],"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PACAP - Pushing Architecture and Compilation for Application Performance (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075222745","display_name":"Andr\u00e9 Seznec","orcid":"https://orcid.org/0000-0002-3058-6503"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Seznec","raw_affiliation_strings":["INRIA, France","PACAP - Pushing Architecture and Compilation for Application Performance (Campus de Beaulieu 35042 Rennes cedex - France)"],"affiliations":[{"raw_affiliation_string":"INRIA, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PACAP - Pushing Architecture and Compilation for Application Performance (Campus de Beaulieu 35042 Rennes cedex - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063297401"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I18014758"],"apc_list":null,"apc_paid":null,"fwci":1.1552,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7565331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"23"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9988999962806702,"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":0.9980999827384949,"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":0.8097098469734192},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.7647793889045715},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7370390892028809},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.695939302444458},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6948559880256653},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.6841129660606384},{"id":"https://openalex.org/keywords/out-of-order-execution","display_name":"Out-of-order execution","score":0.47509467601776123},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4729188084602356},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45049938559532166},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3076825737953186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8097098469734192},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.7647793889045715},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7370390892028809},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.695939302444458},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6948559880256653},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.6841129660606384},{"id":"https://openalex.org/C1793878","wikidata":"https://www.wikidata.org/wiki/Q1153762","display_name":"Out-of-order execution","level":2,"score":0.47509467601776123},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4729188084602356},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45049938559532166},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3076825737953186},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3392032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3392032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3392032","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-02542333v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02542333","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Architecture and Code Optimization, 2020, 17 (2), pp.15. ⟨10.1145/3392032⟩","raw_type":"Journal articles"}],"best_oa_location":{"id":"doi:10.1145/3392032","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3392032","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3392032","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3017116334.pdf","grobid_xml":"https://content.openalex.org/works/W3017116334.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1538245821","https://openalex.org/W1972663160","https://openalex.org/W1976936446","https://openalex.org/W2030680937","https://openalex.org/W2076740275","https://openalex.org/W2080592089","https://openalex.org/W2094710396","https://openalex.org/W2101005180","https://openalex.org/W2134633067","https://openalex.org/W2143104153","https://openalex.org/W2152620203","https://openalex.org/W2155503253","https://openalex.org/W2163681909","https://openalex.org/W2170382128","https://openalex.org/W2588282852","https://openalex.org/W2613264175","https://openalex.org/W2765095808","https://openalex.org/W3123542955","https://openalex.org/W3149591378","https://openalex.org/W4247008581","https://openalex.org/W4251500183","https://openalex.org/W4251833217"],"related_works":["https://openalex.org/W2994245508","https://openalex.org/W4242172182","https://openalex.org/W2082875307","https://openalex.org/W4237780868","https://openalex.org/W4285302443","https://openalex.org/W2019451907","https://openalex.org/W2111412181","https://openalex.org/W4250432526","https://openalex.org/W2101536355","https://openalex.org/W2562747857"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"Single":[3,53],"Instruction":[4,54,115],"Multi-Thread":[5],"Express":[6],"(SIMT-X),":[7],"a":[8,64,76,86,113],"general-purpose":[9,114],"Central":[10],"Processing":[11,18],"Unit":[12],"(CPU)":[13],"microarchitecture":[14,83],"that":[15,72],"enables":[16],"Graphics":[17],"Units":[19],"(GPUs)-style":[20],"SIMT":[21],"execution":[22,94],"across":[23],"multiple":[24],"threads":[25],"of":[26,38,45,79,88,91,108],"the":[27,35,42,51,82,89],"same":[28],"program":[29],"for":[30],"high":[31],"throughput,":[32],"while":[33,105],"retaining":[34],"latency":[36],"benefits":[37,90],"out-of-order":[39],"execution,":[40],"and":[41,111],"programming":[43],"convenience":[44],"homogeneous":[46],"multi-thread":[47],"processors.":[48],"SIMT-X":[49,74],"leverages":[50],"existing":[52],"Multiple":[55],"Data":[56],"(SIMD)":[57],"back-end":[58],"to":[59],"provide":[60],"CPU/GPU-like":[61],"processing":[62],"on":[63],"single":[65],"core":[66],"with":[67],"minimal":[68],"overhead.":[69],"We":[70],"demonstrate":[71],"although":[73],"invokes":[75],"restricted":[77],"form":[78],"Out-of-Order":[80],"(OoO),":[81],"successfully":[84],"captures":[85],"majority":[87],"aggressive":[92],"OoO":[93],"using":[95],"at":[96],"most":[97],"two":[98],"concurrent":[99],"register":[100],"mappings":[101],"per":[102],"architectural":[103],"register,":[104],"addressing":[106],"issues":[107],"partial":[109],"dependencies":[110],"supporting":[112],"Set":[116],"Architecture":[117],"(ISA).":[118]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-04-24T00:00:00"}