{"id":"https://openalex.org/W2169350980","doi":"https://doi.org/10.1109/asap.2008.4580146","title":"Bit matrix multiplication in commodity processors","display_name":"Bit matrix multiplication in commodity processors","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W2169350980","doi":"https://doi.org/10.1109/asap.2008.4580146","mag":"2169350980"},"language":"en","primary_location":{"id":"doi:10.1109/asap.2008.4580146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2008.4580146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Conference on Application-Specific Systems, Architectures and Processors","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/A5038823319","display_name":"Yedidya Hilewitz","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yedidya Hilewitz","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111802221","display_name":"C\u00e9dric Lauradoux","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cedric Lauradoux","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035657440","display_name":"Ruby B. Lee","orcid":"https://orcid.org/0000-0001-9497-0777"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruby B. Lee","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038823319"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":1.3864,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.84909629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"14","issue":null,"first_page":"7","last_page":"12"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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":0.9991999864578247,"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":0.8095559477806091},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.8028122782707214},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6672133207321167},{"id":"https://openalex.org/keywords/bit","display_name":"Bit (key)","score":0.6106598377227783},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.5894609093666077},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5671157240867615},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.49445390701293945},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4383639395236969},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3455032706260681},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1090555489063263},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10567530989646912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095559477806091},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.8028122782707214},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6672133207321167},{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.6106598377227783},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.5894609093666077},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5671157240867615},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.49445390701293945},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4383639395236969},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3455032706260681},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1090555489063263},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10567530989646912},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asap.2008.4580146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asap.2008.4580146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 International Conference on Application-Specific Systems, Architectures and Processors","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":23,"referenced_works":["https://openalex.org/W10036955","https://openalex.org/W130111774","https://openalex.org/W1531802798","https://openalex.org/W1548516269","https://openalex.org/W1551805672","https://openalex.org/W1562115776","https://openalex.org/W1693881312","https://openalex.org/W1909442527","https://openalex.org/W1984972320","https://openalex.org/W2005343162","https://openalex.org/W2033629016","https://openalex.org/W2061055971","https://openalex.org/W2104225326","https://openalex.org/W2111652402","https://openalex.org/W2120781145","https://openalex.org/W2131244370","https://openalex.org/W2132280197","https://openalex.org/W2132918567","https://openalex.org/W2170334586","https://openalex.org/W2942537621","https://openalex.org/W4244570301","https://openalex.org/W4245530642","https://openalex.org/W6605355015"],"related_works":["https://openalex.org/W4312354936","https://openalex.org/W3035076484","https://openalex.org/W2753656749","https://openalex.org/W3197664880","https://openalex.org/W2146406121","https://openalex.org/W2149529325","https://openalex.org/W3129397352","https://openalex.org/W2182319213","https://openalex.org/W2142496304","https://openalex.org/W3003529076"],"abstract_inverted_index":{"Registers":[0],"in":[1,82],"processors":[2],"generally":[3,48],"contain":[4],"words":[5],"or,":[6],"with":[7],"the":[8,27,39,45,66,73,98,123,128],"addition":[9],"of":[10,15,17,29,35,100,125,130],"multimedia":[11],"extensions,":[12],"short":[13],"vectors":[14,32],"subwords":[16],"bytes":[18],"or":[19,33],"16-bit":[20],"elements.":[21],"In":[22,93],"this":[23,94],"paper,":[24,95],"we":[25,96],"view":[26],"contents":[28],"registers":[30],"as":[31],"matrices":[34],"individual":[36],"bits.":[37],"However,":[38],"facility":[40],"to":[41],"operate":[42],"efficiently":[43],"on":[44,127],"bit-level":[46,70],"is":[47,72],"lacking.":[49],"A":[50],"commodity":[51,119],"processor":[52,107],"usually":[53],"only":[54,81],"has":[55],"logical":[56],"and":[57,60,104,134],"shift":[58],"instructions":[59,108],"occasionally":[61],"population":[62],"count":[63],"instructions.":[64],"Perhaps":[65],"most":[67],"powerful":[68],"primitive":[69,113],"operation":[71],"bit":[74,91],"matrix":[75],"multiply":[76],"(BMM)":[77],"instruction,":[78],"currently":[79],"found":[80],"supercomputers":[83],"like":[84],"Cray.":[85],"This":[86],"instruction":[87],"multiplies":[88],"two":[89],"ntimesn":[90],"matrices.":[92],"show":[97,122],"power":[99],"BMM.":[101],"We":[102,121],"propose":[103],"analyze":[105],"new":[106],"that":[109],"implement":[110],"simpler":[111],"BMM":[112,126],"operations":[114],"more":[115],"suitable":[116],"for":[117],"a":[118],"processor.":[120],"impact":[124],"performance":[129],"critical":[131],"application":[132],"kernels":[133],"discuss":[135],"its":[136],"hardware":[137],"cost.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}