{"id":"https://openalex.org/W4226077407","doi":"https://doi.org/10.23919/mipro55190.2022.9803591","title":"Batched matrix operations on distributed GPUs with application in theoretical physics","display_name":"Batched matrix operations on distributed GPUs with application in theoretical physics","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4226077407","doi":"https://doi.org/10.23919/mipro55190.2022.9803591"},"language":"en","primary_location":{"id":"doi:10.23919/mipro55190.2022.9803591","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mipro55190.2022.9803591","pdf_url":null,"source":{"id":"https://openalex.org/S4363605136","display_name":"2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://fulir.irb.hr/7514/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021927301","display_name":"Nenad Miji\u0107","orcid":"https://orcid.org/0000-0001-7738-5007"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nenad Mijic","raw_affiliation_strings":["Ru&#x0111;er Bo&#x0161;kovi&#x0107; Institute,Centre for Informatics and Computing,Zagreb,Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ru&#x0111;er Bo&#x0161;kovi&#x0107; Institute,Centre for Informatics and Computing,Zagreb,Croatia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082491978","display_name":"Davor Davidovi\u0107","orcid":"https://orcid.org/0000-0003-2649-9236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davor Davidovic","raw_affiliation_strings":["Ru&#x0111;er Bo&#x0161;kovi&#x0107; Institute,Centre for Informatics and Computing,Zagreb,Croatia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ru&#x0111;er Bo&#x0161;kovi&#x0107; Institute,Centre for Informatics and Computing,Zagreb,Croatia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.03269502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.3167000114917755,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.3167000114917755,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.18000000715255737,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.16590000689029694,"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":0.725493848323822},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6429429650306702},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6252408027648926},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5687950253486633},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5547887086868286},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5381563305854797},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.5153898000717163},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.45224225521087646},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4409111738204956},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.43083032965660095},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34096378087997437},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28692787885665894},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.190883606672287},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15460669994354248},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11185961961746216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725493848323822},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6429429650306702},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6252408027648926},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5687950253486633},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5547887086868286},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5381563305854797},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.5153898000717163},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.45224225521087646},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4409111738204956},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.43083032965660095},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34096378087997437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28692787885665894},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.190883606672287},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15460669994354248},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11185961961746216},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/mipro55190.2022.9803591","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mipro55190.2022.9803591","pdf_url":null,"source":{"id":"https://openalex.org/S4363605136","display_name":"2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)","raw_type":"proceedings-article"},{"id":"pmh:oai:fulir.irb.hr:7514","is_oa":true,"landing_page_url":"http://fulir.irb.hr/7514/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400095","display_name":"Institutional Repository  of the Ru\u0111er Bo\u0161kovi\u0107 Institute (Ru\u0111er Bo\u0161kovi\u0107 Institute)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123216","host_organization_name":"Ru\u0111er Bo\u0161kovi\u0107 Institute","host_organization_lineage":["https://openalex.org/I4210123216"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:fulir.irb.hr:7514","is_oa":true,"landing_page_url":"http://fulir.irb.hr/7514/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400095","display_name":"Institutional Repository  of the Ru\u0111er Bo\u0161kovi\u0107 Institute (Ru\u0111er Bo\u0161kovi\u0107 Institute)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210123216","host_organization_name":"Ru\u0111er Bo\u0161kovi\u0107 Institute","host_organization_lineage":["https://openalex.org/I4210123216"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1947869163","https://openalex.org/W1974077465","https://openalex.org/W2016279572","https://openalex.org/W2038469228","https://openalex.org/W2049926709","https://openalex.org/W2073061372","https://openalex.org/W2148979214","https://openalex.org/W2268122618","https://openalex.org/W2280571487","https://openalex.org/W2289110059","https://openalex.org/W2499931820","https://openalex.org/W2531348778","https://openalex.org/W2617819327","https://openalex.org/W2753445897","https://openalex.org/W2913790721","https://openalex.org/W3031535742","https://openalex.org/W3043065011","https://openalex.org/W4229666556","https://openalex.org/W6601929215","https://openalex.org/W6637151318","https://openalex.org/W6669400929","https://openalex.org/W6757364461","https://openalex.org/W6764041785"],"related_works":["https://openalex.org/W544946","https://openalex.org/W1356373","https://openalex.org/W9998127","https://openalex.org/W15538807","https://openalex.org/W7500027","https://openalex.org/W14371359","https://openalex.org/W11061678","https://openalex.org/W12589719","https://openalex.org/W9212780","https://openalex.org/W10020330"],"abstract_inverted_index":{"One":[0],"of":[1,28,65,159,172,195],"the":[2,73,157,177,201],"most":[3],"important":[4],"and":[5,41,92,128,152,191],"commonly":[6],"used":[7],"operations":[8,69,89,121],"in":[9,24,156],"many":[10,29,56],"linear":[11],"algebra":[12],"functions":[13,81],"is":[14,19,33,101],"matrix-matrix":[15],"multiplication":[16],"(GEMM),":[17],"which":[18,100],"also":[20],"a":[21,34,61,98,103,113,135,186,193],"key":[22],"component":[23],"obtaining":[25],"high":[26,43],"performance":[27],"scientific":[30],"codes.":[31],"It":[32],"computationally":[35],"intensive":[36],"function":[37],"requiring":[38],"O(n3)":[39],"operations,":[40],"its":[42],"computational":[44],"intensity":[45],"makes":[46],"it":[47],"well-suited":[48],"to":[49,122,134,162,184,197,200],"be":[50],"significantly":[51],"accelerated":[52],"with":[53],"GPUs.":[54],"Today,":[55],"research":[57,108],"problems":[58],"require":[59],"solving":[60],"very":[62],"large":[63],"number":[64],"relatively":[66],"small":[67],"GEMM":[68,88,120,146],"that":[70,85],"cannot":[71],"utilise":[72],"entire":[74],"GPU.":[75,137],"To":[76,138],"overcome":[77],"this":[78,107,154],"bottleneck,":[79],"special":[80],"have":[82,111],"been":[83],"developed":[84],"pack":[86],"several":[87],"into":[90],"one":[91],"then":[93,129],"compute":[94,163],"them":[95],"simultaneously":[96],"on":[97,117],"GPU,":[99],"called":[102],"batch":[104],"operation.":[105],"In":[106],"work,":[109],"we":[110,181],"proposed":[112],"different":[114],"approach":[115,155],"based":[116],"linking":[118],"multiple":[119,131],"Message":[123],"Passing":[124],"Interface":[125],"(MPI)":[126],"processes":[127,133,144],"binding":[130],"MPI":[132,143],"single":[136],"increase":[139],"GPU":[140],"utilisation,":[141],"more":[142],"(i.e.":[145],"operations)":[147],"are":[148],"added.":[149],"We":[150],"implement":[151],"test":[153],"field":[158],"theoretical":[160],"physics":[161],"entanglement":[164],"properties":[165],"through":[166],"simulated":[167],"annealing":[168],"Monte":[169],"Carlo":[170],"simulation":[171],"quantum":[173],"spin":[174,189],"chains.":[175],"For":[176],"specific":[178],"use":[179],"case,":[180],"were":[182],"able":[183],"simulate":[185],"much":[187],"larger":[188],"system":[190],"achieve":[192],"speedup":[194],"up":[196],"35\u00d7":[198],"compared":[199],"parallel":[202],"CPU-only":[203],"version.":[204]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-05-05T00:00:00"}
