{"id":"https://openalex.org/W2172667799","doi":"https://doi.org/10.1109/snpd.2014.6888709","title":"Padding free bank conflict resolution for CUDA-based matrix transpose algorithm","display_name":"Padding free bank conflict resolution for CUDA-based matrix transpose algorithm","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W2172667799","doi":"https://doi.org/10.1109/snpd.2014.6888709","mag":"2172667799"},"language":"en","primary_location":{"id":"doi:10.1109/snpd.2014.6888709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2014.6888709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5006797454","display_name":"Ayaz H. Khan","orcid":"https://orcid.org/0000-0003-1167-7319"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"A. Khan","raw_affiliation_strings":["Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057598450","display_name":"Mayez Al-Mouhamed","orcid":"https://orcid.org/0000-0002-6309-699X"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"M. Al-Mouhamed","raw_affiliation_strings":["Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091698226","display_name":"A. Fatayar","orcid":null},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"A. Fatayar","raw_affiliation_strings":["Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066961640","display_name":"A. Almousa","orcid":null},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"A. Almousa","raw_affiliation_strings":["Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000439817","display_name":"Abdulrahman Ahmed Bobakr Baqais","orcid":null},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"A. Baqais","raw_affiliation_strings":["Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"last","author":{"id":null,"display_name":"M. Assayony","orcid":null},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"M. Assayony","raw_affiliation_strings":["Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I134085113"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9932000041007996,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9918000102043152,"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/transpose","display_name":"Transpose","score":0.9806454181671143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7901265621185303},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.6142789721488953},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5737639665603638},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5662403702735901},{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.5469598174095154},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5226207375526428},{"id":"https://openalex.org/keywords/padding","display_name":"Padding","score":0.5144572257995605},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.46717438101768494},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.44329187273979187},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.35228991508483887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08992809057235718}],"concepts":[{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.9806454181671143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7901265621185303},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.6142789721488953},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5737639665603638},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5662403702735901},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.5469598174095154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5226207375526428},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.5144572257995605},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.46717438101768494},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.44329187273979187},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.35228991508483887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08992809057235718},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/snpd.2014.6888709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/snpd.2014.6888709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W86601866","https://openalex.org/W1967802285","https://openalex.org/W2020634604","https://openalex.org/W2048558763","https://openalex.org/W2129541371","https://openalex.org/W2141978748","https://openalex.org/W2153667821","https://openalex.org/W2167334577","https://openalex.org/W2171473263","https://openalex.org/W2997701623","https://openalex.org/W3141650078","https://openalex.org/W6603575332","https://openalex.org/W6662580226","https://openalex.org/W6684857869","https://openalex.org/W7070871703"],"related_works":["https://openalex.org/W2142641794","https://openalex.org/W2946726629","https://openalex.org/W4384947563","https://openalex.org/W4231428344","https://openalex.org/W4322753435","https://openalex.org/W4243974052","https://openalex.org/W4315882065","https://openalex.org/W4244331477","https://openalex.org/W4236539272","https://openalex.org/W2103295001"],"abstract_inverted_index":{"Matrix":[0],"Transposition":[1],"is":[2,111],"an":[3,141],"important":[4],"linear":[5],"algebra":[6],"procedure":[7],"that":[8,112],"has":[9],"deep":[10],"impact":[11],"in":[12,36,47,54,151,175],"various":[13],"computational":[14],"science":[15],"and":[16,51,82,170],"engineering":[17],"applications.":[18],"Several":[19],"factors":[20],"hinder":[21],"the":[22,39,48,55,62,75,95,124,131,136,152,159],"expected":[23],"performance":[24,37],"of":[25,58,78,108,130,138,144,167],"large":[26],"matrix":[27,68,102],"transpose":[28,69,103,161],"on":[29],"Graphic":[30],"Processing":[31],"Units":[32],"(GPUs).":[33],"The":[34,87,105],"degradation":[35],"involves":[38],"memory":[40,50,57,120],"access":[41,46,81],"pattern":[42],"such":[43],"as":[44],"coalesced":[45,80],"global":[49],"bank":[52,85,98,115],"conflict":[53,83,99],"shared":[56,119],"streaming":[59],"multiprocessors":[60],"within":[61],"GPU.":[63],"In":[64],"this":[65],"paper,":[66],"two":[67],"algorithms":[70,89,110],"are":[71],"proposed":[72,88,109,160],"to":[73,123,135,148,163],"alleviate":[74],"aforementioned":[76],"issues":[77],"ensuring":[79],"free":[84,101],"access.":[86],"have":[90,156],"comparable":[91],"execution":[92],"times":[93],"with":[94],"NVIDIA":[96,168],"SDK":[97,169],"-":[100],"implementation.":[104],"main":[106],"advantage":[107],"they":[113],"eliminate":[114],"conflicts":[116],"while":[117],"allocating":[118],"exactly":[121],"equal":[122],"tile":[125],"size":[126],"(T":[127],"\u00d7":[128],"T)":[129],"problem":[132],"space.":[133],"However,":[134],"best":[137],"our":[139],"knowledge":[140],"extra":[142],"space":[143],"Tx(T":[145],"+1)":[146],"needs":[147],"be":[149],"allocated":[150],"published":[153],"research.":[154],"We":[155],"also":[157],"applied":[158],"algorithm":[162],"recursive":[164],"Gaussian":[165],"implementation":[166],"achieved":[171],"about":[172],"6%":[173],"improvement":[174],"performance.":[176]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
