{"id":"https://openalex.org/W1509471215","doi":"https://doi.org/10.1145/2935746","title":"GPU-Accelerated Generation of Correctly Rounded Elementary Functions","display_name":"GPU-Accelerated Generation of Correctly Rounded Elementary Functions","publication_year":2016,"publication_date":"2016-12-05","ids":{"openalex":"https://openalex.org/W1509471215","doi":"https://doi.org/10.1145/2935746","mag":"1509471215"},"language":"en","primary_location":{"id":"doi:10.1145/2935746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2935746","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"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 Mathematical Software","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1211.3056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060046643","display_name":"Pierre Fortin","orcid":"https://orcid.org/0000-0003-3117-9122"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pierre Fortin","raw_affiliation_strings":["Sorbonne Universit\u00e9s and CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9s and CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040247934","display_name":"Mourad Gouicem","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mourad Gouicem","raw_affiliation_strings":["LIRMM, CNRS/Universit\u00e9 Montpellier 2, Sorbonne Universit\u00e9s, and CNRS, Paris, France","LIRMM, CNRS/Universit\u00e9 Montpellier 2, Sorbonne Universit\u00e9s, and CNRS, Paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIRMM, CNRS/Universit\u00e9 Montpellier 2, Sorbonne Universit\u00e9s, and CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I19894307","https://openalex.org/I39804081","https://openalex.org/I4210101743"]},{"raw_affiliation_string":"LIRMM, CNRS/Universit\u00e9 Montpellier 2, Sorbonne Universit\u00e9s, and CNRS, Paris, France#TAB#","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I19894307","https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020384391","display_name":"Stef Graillat","orcid":"https://orcid.org/0000-0001-8954-2276"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stef Graillat","raw_affiliation_strings":["Sorbonne Universit\u00e9s and CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9s and CNRS, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00304132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11435","display_name":"Polynomial and algebraic computation","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8572694063186646},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7673430442810059},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7443180084228516},{"id":"https://openalex.org/keywords/rounding","display_name":"Rounding","score":0.5228224992752075},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4745180010795593},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.46394798159599304},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.4569334387779236},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4563373625278473},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4360450506210327},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2713838815689087},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11221680045127869},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10960474610328674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572694063186646},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7673430442810059},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7443180084228516},{"id":"https://openalex.org/C136625980","wikidata":"https://www.wikidata.org/wiki/Q663208","display_name":"Rounding","level":2,"score":0.5228224992752075},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4745180010795593},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.46394798159599304},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4569334387779236},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4563373625278473},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4360450506210327},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2713838815689087},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11221680045127869},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10960474610328674}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/2935746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2935746","pdf_url":null,"source":{"id":"https://openalex.org/S163326656","display_name":"ACM Transactions on Mathematical Software","issn_l":"0098-3500","issn":["0098-3500","1557-7295"],"is_oa":false,"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 Mathematical Software","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1211.3056","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1211.3056","pdf_url":"https://arxiv.org/pdf/1211.3056","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:1509471215","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1211.3056v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.9111","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.9111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/83/05/80/PDF/article.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00751446v2","is_oa":true,"landing_page_url":"https://hal.science/hal-00751446","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Mathematical Software, 2016, 43 (3), pp.22:1--22:26. &#x27E8;10.1145/2935746&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1211.3056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1211.3056","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1211.3056","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1211.3056","pdf_url":"https://arxiv.org/pdf/1211.3056","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G3328265085","display_name":"Table Maker's Dilemma","funder_award_id":"ANR-10-BLAN-0203","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W605824955","https://openalex.org/W1479693001","https://openalex.org/W1980965137","https://openalex.org/W1999155053","https://openalex.org/W2012500323","https://openalex.org/W2017655372","https://openalex.org/W2019044966","https://openalex.org/W2068214544","https://openalex.org/W2101822637","https://openalex.org/W2104895541","https://openalex.org/W2112322691","https://openalex.org/W2113827471","https://openalex.org/W2113841249","https://openalex.org/W2127800982","https://openalex.org/W2149538173","https://openalex.org/W2151686327","https://openalex.org/W2156504613","https://openalex.org/W2167675119","https://openalex.org/W2168921806","https://openalex.org/W2315126270","https://openalex.org/W2565843813","https://openalex.org/W2752853835","https://openalex.org/W3038928148"],"related_works":["https://openalex.org/W2662890769","https://openalex.org/W2253983202","https://openalex.org/W2149395122","https://openalex.org/W3157025177","https://openalex.org/W1945588072","https://openalex.org/W1904463783","https://openalex.org/W2337584457","https://openalex.org/W2588282852","https://openalex.org/W2769553056","https://openalex.org/W2928470165","https://openalex.org/W2008420072","https://openalex.org/W3176486103","https://openalex.org/W2020073675","https://openalex.org/W2762933290","https://openalex.org/W2737794485","https://openalex.org/W2047086434","https://openalex.org/W2401971606","https://openalex.org/W124803327","https://openalex.org/W2478126787","https://openalex.org/W2793714585"],"abstract_inverted_index":{"The":[0],"IEEE":[1],"754-2008":[2],"standard":[3],"recommends":[4],"the":[5,15,38,65,71,107,110,115,119,155,158],"correct":[6],"rounding":[7],"of":[8,25,64,73,106,109,154],"some":[9],"elementary":[10],"functions.":[11],"This":[12],"requires":[13],"solving":[14],"Table":[16],"Maker\u2019s":[17],"Dilemma":[18],"(TMD),":[19],"which":[20,46,148],"implies":[21],"a":[22,52,79,135,145,150],"huge":[23],"amount":[24],"CPU":[26,137],"computation":[27],"time.":[28],"In":[29,118],"this":[30],"article,":[31],"we":[32,121],"consider":[33],"accelerating":[34],"such":[35],"computations,":[36],"namely":[37],"Lef\u00e8vre":[39,66,116],"algorithm":[40,83],"on":[41,89,131],"graphics":[42],"processing":[43],"units":[44],"(GPUs),":[45],"are":[47],"massively":[48],"parallel":[49,81],"architectures":[50],"with":[51],"partial":[53],"single":[54],"instruction,":[55],"multiple":[56],"data":[57],"execution.":[58],"We":[59,76,98],"first":[60],"propose":[61,78],"an":[62,101],"analysis":[63],"hard-to-round":[67],"argument":[68],"search":[69,82],"using":[70],"concept":[72],"continued":[74],"fractions.":[75],"then":[77],"new":[80],"that":[84],"is":[85],"much":[86,151],"more":[87,94],"efficient":[88,102],"GPUs":[90],"thanks":[91],"to":[92,123,128,141],"its":[93],"regular":[95],"control":[96],"flow.":[97],"also":[99],"present":[100],"hybrid":[103],"CPU-GPU":[104],"deployment":[105],"generation":[108],"polynomial":[111],"approximations":[112],"required":[113],"in":[114],"algorithm.":[117],"end,":[120],"manage":[122],"obtain":[124],"overall":[125],"speedups":[126],"up":[127,140],"53.4":[129],"\u00d7":[130,143],"one":[132],"GPU":[133],"over":[134,144],"sequential":[136],"execution":[138],"and":[139],"7.1":[142],"hex-core":[146],"CPU,":[147],"enable":[149],"faster":[152],"solution":[153],"TMD":[156],"for":[157],"double-precision":[159],"format.":[160]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
