{"id":"https://openalex.org/W1789507677","doi":"https://doi.org/10.1142/s0218126615501145","title":"Simultaneous Multithreaded Matrix Processor","display_name":"Simultaneous Multithreaded Matrix Processor","publication_year":2015,"publication_date":"2015-05-29","ids":{"openalex":"https://openalex.org/W1789507677","doi":"https://doi.org/10.1142/s0218126615501145","mag":"1789507677"},"language":"en","primary_location":{"id":"doi:10.1142/s0218126615501145","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126615501145","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","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/A5045915414","display_name":"Mostafa I. Soliman","orcid":"https://orcid.org/0000-0002-4386-8235"},"institutions":[{"id":"https://openalex.org/I23075662","display_name":"Taibah University","ror":"https://ror.org/01xv1nn60","country_code":"SA","type":"education","lineage":["https://openalex.org/I23075662"]},{"id":"https://openalex.org/I86310350","display_name":"Aswan University","ror":"https://ror.org/048qnr849","country_code":"EG","type":"education","lineage":["https://openalex.org/I86310350"]}],"countries":["EG","SA"],"is_corresponding":false,"raw_author_name":"Mostafa I. Soliman","raw_affiliation_strings":["Computer Science and Information Department, Community College, Taibah University, Al-Madinah Al-Munawwarah 2898, Saudi Arabia","Computer and System Section, Electrical Engineering Department, Faculty of Engineering, Aswan University, Aswan 81542, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Information Department, Community College, Taibah University, Al-Madinah Al-Munawwarah 2898, Saudi Arabia","institution_ids":["https://openalex.org/I23075662"]},{"raw_affiliation_string":"Computer and System Section, Electrical Engineering Department, Faculty of Engineering, Aswan University, Aswan 81542, Egypt","institution_ids":["https://openalex.org/I86310350"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054051313","display_name":"Elsayed A. Elsayed","orcid":"https://orcid.org/0000-0002-2245-1967"},"institutions":[{"id":"https://openalex.org/I86310350","display_name":"Aswan University","ror":"https://ror.org/048qnr849","country_code":"EG","type":"education","lineage":["https://openalex.org/I86310350"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Elsayed A. Elsayed","raw_affiliation_strings":["Computer and System Section, Electrical Engineering Department, Faculty of Engineering, Aswan University, Aswan 81542, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer and System Section, Electrical Engineering Department, Faculty of Engineering, Aswan University, Aswan 81542, Egypt","institution_ids":["https://openalex.org/I86310350"]}]}],"institutions":[],"countries_distinct_count":2,"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":0,"citation_normalized_percentile":{"value":0.04704003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":"08","first_page":"1550114","last_page":"1550114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9958000183105469,"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/speedup","display_name":"Speedup","score":0.8826614618301392},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7757470011711121},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7732757329940796},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.564739465713501},{"id":"https://openalex.org/keywords/scalar-multiplication","display_name":"Scalar multiplication","score":0.49330487847328186},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.47933587431907654},{"id":"https://openalex.org/keywords/scalar","display_name":"Scalar (mathematics)","score":0.44461750984191895},{"id":"https://openalex.org/keywords/strassen-algorithm","display_name":"Strassen algorithm","score":0.4356766641139984},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.42358097434043884},{"id":"https://openalex.org/keywords/dot-product","display_name":"Dot product","score":0.4156794846057892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18310868740081787}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8826614618301392},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7757470011711121},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732757329940796},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.564739465713501},{"id":"https://openalex.org/C171182647","wikidata":"https://www.wikidata.org/wiki/Q126736","display_name":"Scalar multiplication","level":3,"score":0.49330487847328186},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.47933587431907654},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.44461750984191895},{"id":"https://openalex.org/C39096654","wikidata":"https://www.wikidata.org/wiki/Q728507","display_name":"Strassen algorithm","level":4,"score":0.4356766641139984},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.42358097434043884},{"id":"https://openalex.org/C32900221","wikidata":"https://www.wikidata.org/wiki/Q181365","display_name":"Dot product","level":2,"score":0.4156794846057892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18310868740081787},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218126615501145","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218126615501145","pdf_url":null,"source":{"id":"https://openalex.org/S167602672","display_name":"Journal of Circuits Systems and Computers","issn_l":"0218-1266","issn":["0218-1266","1793-6454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Circuits, Systems and Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1506585561","https://openalex.org/W1552828809","https://openalex.org/W1555915743","https://openalex.org/W1567646530","https://openalex.org/W1920227747","https://openalex.org/W1964975335","https://openalex.org/W1984333965","https://openalex.org/W1984637917","https://openalex.org/W2086479094","https://openalex.org/W2107978915","https://openalex.org/W2151345470","https://openalex.org/W2169040626","https://openalex.org/W2345726388","https://openalex.org/W2725179571","https://openalex.org/W2913795363","https://openalex.org/W4242141188"],"related_works":["https://openalex.org/W1974407206","https://openalex.org/W2004916460","https://openalex.org/W2962985479","https://openalex.org/W2020777648","https://openalex.org/W1523285705","https://openalex.org/W2772956802","https://openalex.org/W2056120647","https://openalex.org/W1829171354","https://openalex.org/W2069906535","https://openalex.org/W3006227194"],"abstract_inverted_index":{"This":[0],"paper":[1,81],"proposes":[2],"a":[3],"simultaneous":[4],"multithreaded":[5],"matrix":[6],"processor":[7],"(SMMP)":[8],"to":[9,39,208],"improve":[10],"the":[11,30,67,83,96,106,116,126,178,183,194],"performance":[12,97],"of":[13,69,85,98,119,132,148,196],"data-parallel":[14],"applications":[15],"by":[16],"exploiting":[17],"instruction-level":[18],"parallelism":[19,22,26],"(ILP)":[20],"data-level":[21],"(DLP)":[23],"and":[24,141,170,182],"thread-level":[25],"(TLP).":[27],"In":[28,94],"SMMP,":[29],"well-known":[31],"five-stage":[32],"pipeline":[33],"(baseline":[34],"scalar":[35,52,128,152],"processor)":[36],"is":[37,74,100,121,180,188,198,214],"extended":[38],"execute":[40],"multi-scalar/vector/matrix":[41],"instructions":[42,53,71],"on":[43,102,145,210],"unified":[44],"parallel":[45],"execution":[46,68],"datapaths.":[47],"SMMP":[48,88,99,120,197],"can":[49],"issue":[50],"four":[51,60],"from":[54,63,105,206],"two":[55],"threads":[56,73],"each":[57],"cycle":[58],"or":[59],"vector/matrix":[61,70,211],"operations":[62],"one":[64],"thread,":[65],"where":[66],"in":[72,76,216],"done":[75],"round-robin":[77],"fashion.":[78],"Moreover,":[79],"this":[80],"presents":[82],"implementation":[84],"our":[86],"proposed":[87],"using":[89],"VHDL":[90],"targeting":[91],"FPGA":[92],"Virtex-6.":[93],"addition,":[95,158],"evaluated":[101],"some":[103],"kernels":[104,147],"basic":[107],"linear":[108],"algebra":[109],"subprograms":[110],"(BLAS).":[111],"Our":[112],"results":[113],"show":[114],"that,":[115],"hardware":[117],"complexity":[118,187,195],"5.68":[122],"times":[123,153,200],"higher":[124],"than":[125],"baseline":[127,179],"processor.":[129],"However,":[130],"speedups":[131],"4.9,":[133],"6.09,":[134],"6.98,":[135],"8.2,":[136],"8.25,":[137],"8.72,":[138],"9.36,":[139],"11.84":[140],"21.57":[142],"are":[143],"achieved":[144],"BLAS":[146],"applying":[149],"Givens":[150,163],"rotation,":[151,164],"vector":[154,157,159],"plus":[155],"another,":[156],"scaling,":[160],"setting":[161],"up":[162],"dot-product,":[165],"matrix\u2013vector":[166],"multiplication,":[167],"Euclidean":[168],"length,":[169],"matrix\u2013matrix":[171],"multiplications,":[172],"respectively.":[173],"The":[174],"average":[175,184],"speedup":[176,185,204],"over":[177,186],"9.55":[181],"1.68.":[189],"Comparing":[190],"with":[191],"Xilinx":[192],"MicroBlaze,":[193],"6.36":[199],"higher,":[201],"however,":[202],"its":[203],"ranges":[205],"6.87":[207],"12.07":[209],"kernels,":[212],"which":[213],"9.46":[215],"average.":[217]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
