{"id":"https://openalex.org/W2061382358","doi":"https://doi.org/10.1137/s1064827599359709","title":"Fast Bit-Reversals on Uniprocessors and Shared-Memory Multiprocessors","display_name":"Fast Bit-Reversals on Uniprocessors and Shared-Memory Multiprocessors","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2061382358","doi":"https://doi.org/10.1137/s1064827599359709","mag":"2061382358"},"language":"en","primary_location":{"id":"doi:10.1137/s1064827599359709","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s1064827599359709","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-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/A5114237685","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0002-8387-6133"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100376221","display_name":"Xiaodong Zhang","orcid":"https://orcid.org/0000-0002-8380-1019"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Zhang","raw_affiliation_strings":["college of william and mary"],"affiliations":[{"raw_affiliation_string":"college of william and mary","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114237685"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2777,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.63087248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"22","issue":"6","first_page":"2113","last_page":"2134"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955000281333923,"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/uniprocessor-system","display_name":"Uniprocessor system","score":0.8804121017456055},{"id":"https://openalex.org/keywords/padding","display_name":"Padding","score":0.8634244203567505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8576839566230774},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8310506939888},{"id":"https://openalex.org/keywords/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.7774926424026489},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7031415104866028},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.520486056804657},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5120123028755188},{"id":"https://openalex.org/keywords/cache-only-memory-architecture","display_name":"Cache-only memory architecture","score":0.4514271020889282},{"id":"https://openalex.org/keywords/workstation","display_name":"Workstation","score":0.4220472574234009},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.41915005445480347},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.33886486291885376},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19611573219299316},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.1441657841205597},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.13795289397239685},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08293238282203674},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.07847419381141663}],"concepts":[{"id":"https://openalex.org/C79189994","wikidata":"https://www.wikidata.org/wiki/Q3488021","display_name":"Uniprocessor system","level":3,"score":0.8804121017456055},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.8634244203567505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8576839566230774},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8310506939888},{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.7774926424026489},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7031415104866028},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.520486056804657},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5120123028755188},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.4514271020889282},{"id":"https://openalex.org/C67953723","wikidata":"https://www.wikidata.org/wiki/Q192525","display_name":"Workstation","level":2,"score":0.4220472574234009},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.41915005445480347},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.33886486291885376},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19611573219299316},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.1441657841205597},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.13795289397239685},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08293238282203674},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.07847419381141663},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1137/s1064827599359709","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s1064827599359709","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.7483","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.7483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.wm.edu/hpcs/WWW/HTML/publications/./papers/TR-01-2.ps.Z","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.3","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.3","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.wm.edu/hpcs/WWW/HTML/publications/papers/TR-01-2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1974232202","https://openalex.org/W1979154698","https://openalex.org/W2011992756","https://openalex.org/W2017417067","https://openalex.org/W2045836768","https://openalex.org/W2049890071","https://openalex.org/W2050879237","https://openalex.org/W2061171222","https://openalex.org/W2061491806","https://openalex.org/W2069738303","https://openalex.org/W2105321788","https://openalex.org/W2117866850","https://openalex.org/W2127391977","https://openalex.org/W2134199184","https://openalex.org/W2143285027","https://openalex.org/W2155070179","https://openalex.org/W2155477811","https://openalex.org/W2188176528"],"related_works":["https://openalex.org/W2144008706","https://openalex.org/W1968886276","https://openalex.org/W2126987530","https://openalex.org/W2155502730","https://openalex.org/W4237553843","https://openalex.org/W2097621668","https://openalex.org/W2515300981","https://openalex.org/W2061382358","https://openalex.org/W2350803493","https://openalex.org/W1929987588"],"abstract_inverted_index":{"In":[0],"this":[1,72],"paper,":[2],"we":[3,45,112],"examine":[4],"different":[5,43],"methods":[6,41,63,106,131],"using":[7],"techniques":[8],"of":[9,17,25,120,135],"blocking,":[10],"buffering,":[11],"and":[12,23,28,31,49,64,83,89,98,111,124,146],"padding":[13,105,130],"for":[14,34],"efficient":[15],"implementations":[16],"bit-reversals.":[18],"We":[19,67,101],"evaluate":[20],"the":[21,40,62,93,116,129],"merits":[22],"limits":[24],"each":[26],"technique":[27],"its":[29],"application":[30],"architecture-dependent":[32],"conditions":[33],"developing":[35],"cache-optimal":[36,97],"methods.":[37],"Besides":[38],"testing":[39],"on":[42,51,142],"uniprocessors,":[44],"conducted":[46],"both":[47,122],"simulation":[48],"measurements":[50],"two":[52,69],"commercial":[53],"symmetric":[54],"multiprocessors":[55],"(SMP)":[56],"to":[57],"provide":[58],"architectural":[59],"insights":[60],"into":[61],"their":[65],"implementations.":[66],"present":[68],"contributions":[70],"in":[71,118],"paper:":[73],"(1)":[74],"Our":[75],"integrated":[76],"blocking":[77],"methods,":[78,110],"which":[79,90],"match":[80],"cache":[81,87],"associativity":[82],"translation-lookaside":[84],"buffer":[85],"(TLB)":[86],"size":[88],"fully":[91],"use":[92],"available":[94],"registers,":[95],"are":[96,115,132],"fast.":[99],"(2)":[100],"show":[102],"that":[103],"our":[104],"outperform":[107],"other":[108],"software-oriented":[109],"believe":[113],"they":[114,137],"fastest":[117],"terms":[119],"minimizing":[121],"CPU":[123],"memory":[125],"access":[126],"cycles.":[127],"Since":[128],"almost":[133],"independent":[134],"hardware,":[136],"could":[138],"be":[139],"widely":[140],"used":[141],"many":[143],"uniprocessor":[144],"workstations":[145],"multiprocessors.":[147]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}