{"id":"https://openalex.org/W4399282325","doi":"https://doi.org/10.1145/3650200.3656624","title":"Accurate Computation of the Logarithm of Modified Bessel Functions on GPUs","display_name":"Accurate Computation of the Logarithm of Modified Bessel Functions on GPUs","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399282325","doi":"https://doi.org/10.1145/3650200.3656624"},"language":"en","primary_location":{"id":"doi:10.1145/3650200.3656624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656624","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656624","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656624","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011473405","display_name":"Andreas Plesner","orcid":"https://orcid.org/0000-0002-8596-8103"},"institutions":[{"id":"https://openalex.org/I2799323385","display_name":"Board of the Swiss Federal Institutes of Technology","ror":"https://ror.org/01rvn4p91","country_code":"CH","type":"government","lineage":["https://openalex.org/I2799323385"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Plesner","raw_affiliation_strings":["ETH, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-8596-8103","affiliations":[{"raw_affiliation_string":"ETH, Switzerland","institution_ids":["https://openalex.org/I2799323385"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103191639","display_name":"Hans Henrik Brandenborg S\u00f8rensen","orcid":"https://orcid.org/0009-0008-5166-3468"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Hans Henrik Brandenborg S\u00f8rensen","raw_affiliation_strings":["Technical University of Denmark, Denmark"],"raw_orcid":"https://orcid.org/0009-0008-5166-3468","affiliations":[{"raw_affiliation_string":"Technical University of Denmark, Denmark","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072186051","display_name":"S\u00f8ren Hauberg","orcid":"https://orcid.org/0000-0001-7223-877X"},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"S\u00f8ren Hauberg","raw_affiliation_strings":["Technical University of Denmark, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-7223-877X","affiliations":[{"raw_affiliation_string":"Technical University of Denmark, Denmark","institution_ids":["https://openalex.org/I96673099"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3077,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54989888,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9757999777793884,"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":0.9757999777793884,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9542999863624573,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9470000267028809,"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/logarithm","display_name":"Logarithm","score":0.8224101066589355},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7603086233139038},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7459433078765869},{"id":"https://openalex.org/keywords/bessel-function","display_name":"Bessel function","score":0.6782386898994446},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6288766860961914},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.532094419002533},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5177180171012878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4854353070259094},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47857239842414856},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4723934829235077},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.39691755175590515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15643784403800964},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10111662745475769},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08768165111541748}],"concepts":[{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.8224101066589355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603086233139038},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7459433078765869},{"id":"https://openalex.org/C107706756","wikidata":"https://www.wikidata.org/wiki/Q219637","display_name":"Bessel function","level":2,"score":0.6782386898994446},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6288766860961914},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.532094419002533},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5177180171012878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4854353070259094},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47857239842414856},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4723934829235077},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.39691755175590515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15643784403800964},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10111662745475769},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08768165111541748},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3650200.3656624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656624","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656624","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.08729","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08729","pdf_url":"https://arxiv.org/pdf/2409.08729","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:publications/93fba5b6-5c6c-431c-90b2-8c77ee54889a","is_oa":false,"landing_page_url":"https://orbit.dtu.dk/en/publications/93fba5b6-5c6c-431c-90b2-8c77ee54889a","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Plesner , A L , S\u00f8rensen , H H B &amp; Hauberg , S 2024 , Accurate Computation of the Logarithm of Modified Bessel Functions on GPUs . in Proceedings of the 38th ACM International Conference on Supercomputing . Association for Computing Machinery , pp. 213-224 , 38 th ACM International Conference on Supercomputing , Kyoto , Japan , 04/06/2024 . https://doi.org/10.1145/3650200.3656624","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.1145/3650200.3656624","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3650200.3656624","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3650200.3656624","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 38th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G1811976741","display_name":null,"funder_award_id":"757360","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G2345421240","display_name":null,"funder_award_id":"42062","funder_id":"https://openalex.org/F4320310490","funder_display_name":"Villum Fonden"},{"id":"https://openalex.org/G2923990082","display_name":null,"funder_award_id":"NNF20OC0062606","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G409749632","display_name":null,"funder_award_id":"42062","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G5623766242","display_name":"Measuring with no tape","funder_award_id":"757360","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8363685846","display_name":null,"funder_award_id":"NNF20OC0062606","funder_id":"https://openalex.org/F4320325957","funder_display_name":"Novo Nordisk Fonden"}],"funders":[{"id":"https://openalex.org/F4320310490","display_name":"Villum Fonden","ror":"https://ror.org/007ww2d15"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320325957","display_name":"Novo Nordisk Fonden","ror":"https://ror.org/04txyc737"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399282325.pdf"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W220935706","https://openalex.org/W434781108","https://openalex.org/W1484503832","https://openalex.org/W1557032310","https://openalex.org/W2028837575","https://openalex.org/W2056568469","https://openalex.org/W2100415730","https://openalex.org/W2156787958","https://openalex.org/W2194775991","https://openalex.org/W2487122920","https://openalex.org/W2521490668","https://openalex.org/W2562016696","https://openalex.org/W2618046004","https://openalex.org/W2980936641","https://openalex.org/W2998648801"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Bessel":[0,68],"functions":[1,69],"are":[2,41,86],"critical":[3],"in":[4],"scientific":[5],"computing":[6,63,77],"for":[7,26,62,107,126,132,158,164],"applications":[8],"such":[9,30],"as":[10,31],"machine":[11,104],"learning,":[12],"protein":[13],"structure":[14],"modeling,":[15],"and":[16,38,73,88,119,124,128,130,140,151,156,160,162],"robotics.":[17],"However,":[18],"currently,":[19],"available":[20],"routines":[21],"lack":[22],"precision":[23,46],"or":[24,94],"fail":[25],"certain":[27],"input":[28],"ranges,":[29],"when":[32],"the":[33,45,55,64,71,101,136,147,168],"order":[34,102],"v":[35],"is":[36],"large,":[37],"GPU-specific":[39],"implementations":[40,51],"limited.":[42],"We":[43,57],"address":[44],"limitations":[47],"of":[48,66,70,103,122,138,154,170],"current":[49],"numerical":[50],"while":[52,96],"dramatically":[53],"improving":[54],"runtime.":[56],"propose":[58],"two":[59],"novel":[60],"algorithms":[61,85,116,148],"logarithm":[65],"modified":[67],"first":[72],"second":[74],"kinds":[75],"by":[76],"intermediate":[78],"values":[79],"on":[80,100],"a":[81],"logarithmic":[82],"scale.":[83],"Our":[84],"robust":[87],"never":[89],"have":[90,117,149],"issues":[91],"with":[92],"underflows":[93],"overflows":[95],"having":[97],"relative":[98],"errors":[99],"precision,":[105],"even":[106],"inputs":[108,139,171],"where":[109],"existing":[110],"libraries":[111,142],"fail.":[112],"In":[113],"C++/CUDA,":[114],"our":[115],"median":[118,150],"maximum":[120,152],"speedups":[121,153],"45x":[123],"6150x":[125],"GPU":[127,159],"17x":[129],"3403x":[131],"CPU,":[133,165],"respectively,":[134,166],"over":[135,167],"ranges":[137,169],"third-party":[141],"tested.":[143,172],"Compared":[144],"to":[145],"SciPy,":[146],"77x":[155],"300x":[157],"35x":[161],"98x":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}
