{"id":"https://openalex.org/W2034339832","doi":"https://doi.org/10.1109/hipc.2011.6152712","title":"Parallel multiple precision division by a single precision divisor","display_name":"Parallel multiple precision division by a single precision divisor","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2034339832","doi":"https://doi.org/10.1109/hipc.2011.6152712","mag":"2034339832"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2011.6152712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2011.6152712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 18th International Conference on High Performance Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053551643","display_name":"Niall Emmart","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Niall Emmart","raw_affiliation_strings":["Computer Science Department, University of Massachusetts, Amherst, MA, USA","Computer Science Department, University of Massachusetts Amherst, MA 01003-4610, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Computer Science Department, University of Massachusetts Amherst, MA 01003-4610, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069608160","display_name":"Charles Weems","orcid":"https://orcid.org/0000-0002-8535-0258"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Weems","raw_affiliation_strings":["Computer Science Department, University of Massachusetts, Amherst, MA, USA","Computer Science Department, University of Massachusetts Amherst, MA 01003-4610, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"Computer Science Department, University of Massachusetts Amherst, MA 01003-4610, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"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":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.14786057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"4818","issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11435","display_name":"Polynomial and algebraic computation","score":0.9995999932289124,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.780726969242096},{"id":"https://openalex.org/keywords/division-algorithm","display_name":"Division algorithm","score":0.7240880727767944},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6837095022201538},{"id":"https://openalex.org/keywords/divisor","display_name":"Divisor (algebraic geometry)","score":0.596242368221283},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5835980772972107},{"id":"https://openalex.org/keywords/integer","display_name":"Integer (computer science)","score":0.5600172281265259},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5480672121047974},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5277020931243896},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4917786419391632},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.49061647057533264},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.4722660779953003},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.466905415058136},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4425179362297058},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4207899570465088},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3341842591762543},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.2645100951194763},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.20435908436775208},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.1622782051563263},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08152046799659729}],"concepts":[{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.780726969242096},{"id":"https://openalex.org/C190715199","wikidata":"https://www.wikidata.org/wiki/Q3526714","display_name":"Division algorithm","level":3,"score":0.7240880727767944},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6837095022201538},{"id":"https://openalex.org/C203492994","wikidata":"https://www.wikidata.org/wiki/Q909669","display_name":"Divisor (algebraic geometry)","level":2,"score":0.596242368221283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5835980772972107},{"id":"https://openalex.org/C97137487","wikidata":"https://www.wikidata.org/wiki/Q729138","display_name":"Integer (computer science)","level":2,"score":0.5600172281265259},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5480672121047974},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5277020931243896},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4917786419391632},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.49061647057533264},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.4722660779953003},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.466905415058136},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4425179362297058},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4207899570465088},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3341842591762543},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2645100951194763},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.20435908436775208},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.1622782051563263},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08152046799659729},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2011.6152712","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2011.6152712","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 18th International Conference on High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1498685334","https://openalex.org/W1534726137","https://openalex.org/W1554747120","https://openalex.org/W1581400690","https://openalex.org/W1969260620","https://openalex.org/W1981663184","https://openalex.org/W1983892874","https://openalex.org/W2003519998","https://openalex.org/W2065245432","https://openalex.org/W2167854327","https://openalex.org/W2752853835","https://openalex.org/W2752908210","https://openalex.org/W6629789561","https://openalex.org/W6634659418","https://openalex.org/W6744529318"],"related_works":["https://openalex.org/W2348330046","https://openalex.org/W2020279179","https://openalex.org/W2077822074","https://openalex.org/W2538869119","https://openalex.org/W2168914470","https://openalex.org/W1984179473","https://openalex.org/W2114188853","https://openalex.org/W2016834232","https://openalex.org/W2294413769","https://openalex.org/W3127478215"],"abstract_inverted_index":{"We":[0,48,86],"report":[1,87],"an":[2,101],"algorithm":[3,22,31,36,70,81,112,149],"for":[4,37,58,89,108],"division":[5,30,60,142],"of":[6,27,46,93],"a":[7,12,16,24,33,156],"multi-":[8],"precision":[9],"integer":[10],"by":[11,123,143],"single-precision":[13],"value":[14],"using":[15],"graphics":[17],"processing":[18],"unit":[19],"(GPU).":[20],"Our":[21],"combines":[23],"parallel":[25],"version":[26],"Jebelean's":[28],"exact":[29],"with":[32,91,145,155],"left-to-":[34],"right":[35],"computing":[38],"the":[39,44],"borrow":[40],"chain,":[41],"to":[42,61,120,136,161],"relax":[43],"requirement":[45],"exactness.":[47],"also":[49],"employ":[50],"Takahashi's":[51,80],"recently":[52],"reported":[53],"cyclic":[54],"reduction":[55],"technique":[56],"[10]":[57],"GPU":[59],"further":[62],"enhance":[63],"performance.":[64],"The":[65],"result":[66],"is":[67,71,113,150],"that":[68],"our":[69,111,148],"asymptotically":[72],"faster,":[73,128],"at":[74,82,116,130,152],"O(n/p":[75],"+":[76],"log":[77,84],"p),":[78],"than":[79],"0(n/p":[83],"p).":[85],"results":[88],"dividends":[90],"precisions":[92],"1024,":[94],"2048,":[95],"and":[96,105,129],"4096":[97,131],"bits":[98,118,132],"running":[99],"on":[100],"NVIDIA":[102],"GTX":[103],"480,":[104],"show":[106],"that,":[107],"non-constant":[109],"divisors,":[110],"20%":[114],"slower":[115],"1024":[117],"(due":[119],"startup":[121],"overhead),":[122],"2048":[124],"we":[125,133],"are":[126,134],"40%":[127],"able":[135],"run":[137],"2.5":[138],"times":[139,163],"faster.":[140,164],"For":[141],"constants,":[144],"precomputed":[146],"tables,":[147],"faster":[151],"all":[153],"sizes":[154],"speedup":[157],"ranging":[158],"from":[159],"2.3":[160],"6":[162]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
