{"id":"https://openalex.org/W3150920444","doi":"https://doi.org/10.1109/ipdps.2006.1639613","title":"The general matrix multiply-add operation on 2D torus","display_name":"The general matrix multiply-add operation on 2D torus","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W3150920444","doi":"https://doi.org/10.1109/ipdps.2006.1639613","mag":"3150920444"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2006.1639613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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/A5002750875","display_name":"Ahmed Zekri","orcid":"https://orcid.org/0000-0001-8518-1581"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"A.S. Zekri","raw_affiliation_strings":["The Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"The Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005107451","display_name":"Stanislav G. Sedukhin","orcid":"https://orcid.org/0000-0002-0071-5140"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"S.G. Sedukhin","raw_affiliation_strings":["The Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan"],"affiliations":[{"raw_affiliation_string":"The Graduate School of Computer Science and Engineering, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5002750875"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.6036,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75387709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8 pp.","last_page":"8 pp."},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":1.0,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980000257492065,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9857000112533569,"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/transpose","display_name":"Transpose","score":0.8844014406204224},{"id":"https://openalex.org/keywords/torus","display_name":"Torus","score":0.785338282585144},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7099471092224121},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6330100297927856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6087719202041626},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5470384955406189},{"id":"https://openalex.org/keywords/processor-array","display_name":"Processor array","score":0.5055091381072998},{"id":"https://openalex.org/keywords/toroid","display_name":"Toroid","score":0.5020830631256104},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.46064358949661255},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46040499210357666},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41050219535827637},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3029845058917999},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2691173553466797},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1530596911907196},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13748687505722046}],"concepts":[{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.8844014406204224},{"id":"https://openalex.org/C9767117","wikidata":"https://www.wikidata.org/wiki/Q12510","display_name":"Torus","level":2,"score":0.785338282585144},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7099471092224121},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6330100297927856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6087719202041626},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5470384955406189},{"id":"https://openalex.org/C2776189500","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Processor array","level":2,"score":0.5055091381072998},{"id":"https://openalex.org/C15001198","wikidata":"https://www.wikidata.org/wiki/Q3241394","display_name":"Toroid","level":3,"score":0.5020830631256104},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.46064358949661255},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46040499210357666},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41050219535827637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3029845058917999},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2691173553466797},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1530596911907196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13748687505722046},{"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/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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C82706917","wikidata":"https://www.wikidata.org/wiki/Q10251","display_name":"Plasma","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2006.1639613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2006.1639613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 20th IEEE International Parallel & Distributed Processing Symposium","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":18,"referenced_works":["https://openalex.org/W10020330","https://openalex.org/W1501077214","https://openalex.org/W1598993252","https://openalex.org/W1964711958","https://openalex.org/W1988425770","https://openalex.org/W2002257715","https://openalex.org/W2038469228","https://openalex.org/W2079658918","https://openalex.org/W2082292996","https://openalex.org/W2082887106","https://openalex.org/W2093608182","https://openalex.org/W2121609535","https://openalex.org/W2129392664","https://openalex.org/W2156172744","https://openalex.org/W4230944386","https://openalex.org/W6600402609","https://openalex.org/W6671248171","https://openalex.org/W6812672278"],"related_works":["https://openalex.org/W2013173893","https://openalex.org/W2163803384","https://openalex.org/W2321297009","https://openalex.org/W4313654668","https://openalex.org/W3099927136","https://openalex.org/W44066255","https://openalex.org/W2030364907","https://openalex.org/W1980904075","https://openalex.org/W3150920444","https://openalex.org/W2080342459"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,7,35,41,58,61,76,92,97,106,110,117,120,128,139,148,152,156,161],"index":[4,44],"space":[5,45],"of":[6,91,105,127,147,155],"(n":[8],"times":[9,24,26,64],"n)-matrix":[10],"multiply-add":[11],"problem":[12,77],"C":[13,15],"=":[14],"+":[16],"AmiddotB":[17],"is":[18,89,123,136],"represented":[19],"as":[20],"a":[21,53],"3D":[22,42],"n":[23,25,27,63,65,79],"torus.":[28],"All":[29,69],"possible":[30,153],"time-scheduling":[31],"functions":[32],"to":[33,101],"activate":[34],"computation":[36],"and":[37],"data":[38,72,99,118,159],"rolling":[39],"inside":[40],"torus":[43],"are":[46,82],"determined.":[47],"To":[48],"maximize":[49],"efficiency":[50],"when":[51],"solving":[52],"single":[54],"problem,":[55],"we":[56,143],"mapped":[57],"computations":[59],"into":[60,160],"2D":[62,71,111],"toroidal":[66,112],"array":[67,113,162],"processor.":[68,114],"optimal":[70,98],"allocations":[73,100],"that":[74],"solve":[75],"in":[78,125],"multiply-add-roll":[80],"steps":[81],"obtained.":[83],"The":[84],"well":[85],"known":[86],"Cannon's":[87],"algorithm":[88],"one":[90,133],"resulting":[93],"allocations.":[94],"We":[95],"used":[96],"describe":[102],"all":[103],"variants":[104],"GEMM":[107,129,149],"operation":[108,122,150],"on":[109],"By":[115],"controling":[116],"movement,":[119],"transposition":[121],"avoided":[124],"75%":[126],"variants.":[130],"However,":[131],"only":[132],"matrix":[134],"transpose":[135],"needed":[137],"for":[138],"remaining":[140],"25%.":[141],"Ultimately,":[142],"described":[144],"four":[145],"versions":[146],"covering":[151],"layouts":[154],"initially":[157],"loaded":[158],"processor":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}