{"id":"https://openalex.org/W4386709684","doi":"https://doi.org/10.1145/3605573.3605631","title":"Communication Optimizations for State-vector Quantum Simulator on CPU+GPU Clusters","display_name":"Communication Optimizations for State-vector Quantum Simulator on CPU+GPU Clusters","publication_year":2023,"publication_date":"2023-08-07","ids":{"openalex":"https://openalex.org/W4386709684","doi":"https://doi.org/10.1145/3605573.3605631"},"language":"en","primary_location":{"id":"doi:10.1145/3605573.3605631","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","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/A5092863050","display_name":"Chenyang Jiao","orcid":"https://orcid.org/0009-0001-9663-1215"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenyang Jiao","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0009-0001-9663-1215","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370316","display_name":"Weihua Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Zhang","raw_affiliation_strings":["Fudan University, China"],"raw_orcid":"https://orcid.org/0000-0003-1224-2237","affiliations":[{"raw_affiliation_string":"Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101790620","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-9043-2998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-9043-2998","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092863050"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.3429,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84711236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"203","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":1.0,"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":1.0,"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/T10020","display_name":"Quantum Information and Cryptography","score":0.9994999766349792,"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/T10382","display_name":"Quantum and electron transport phenomena","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8125338554382324},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6569196581840515},{"id":"https://openalex.org/keywords/quantum-computer","display_name":"Quantum computer","score":0.6305656433105469},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5638707876205444},{"id":"https://openalex.org/keywords/qubit","display_name":"Qubit","score":0.5275477766990662},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5124765038490295},{"id":"https://openalex.org/keywords/data-transmission","display_name":"Data transmission","score":0.4451250731945038},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4305427074432373},{"id":"https://openalex.org/keywords/quantum-circuit","display_name":"Quantum circuit","score":0.42932164669036865},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.4137295186519623},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3267212510108948},{"id":"https://openalex.org/keywords/quantum-network","display_name":"Quantum network","score":0.27691733837127686},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.205061674118042},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09525856375694275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125338554382324},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6569196581840515},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.6305656433105469},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5638707876205444},{"id":"https://openalex.org/C203087015","wikidata":"https://www.wikidata.org/wiki/Q378201","display_name":"Qubit","level":3,"score":0.5275477766990662},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5124765038490295},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.4451250731945038},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4305427074432373},{"id":"https://openalex.org/C124148022","wikidata":"https://www.wikidata.org/wiki/Q2122210","display_name":"Quantum circuit","level":5,"score":0.42932164669036865},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.4137295186519623},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3267212510108948},{"id":"https://openalex.org/C186468114","wikidata":"https://www.wikidata.org/wiki/Q836478","display_name":"Quantum network","level":4,"score":0.27691733837127686},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.205061674118042},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09525856375694275},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":1,"locations":[{"id":"doi:10.1145/3605573.3605631","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3605573.3605631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 52nd International Conference on Parallel Processing","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":33,"referenced_works":["https://openalex.org/W1864199185","https://openalex.org/W2027511901","https://openalex.org/W2072969317","https://openalex.org/W2272008584","https://openalex.org/W2288904158","https://openalex.org/W2559394418","https://openalex.org/W2566002283","https://openalex.org/W2607213325","https://openalex.org/W2736592352","https://openalex.org/W2740579034","https://openalex.org/W2772850285","https://openalex.org/W2789114820","https://openalex.org/W2798868564","https://openalex.org/W2799080830","https://openalex.org/W2903600347","https://openalex.org/W2944581240","https://openalex.org/W2946158922","https://openalex.org/W2986871396","https://openalex.org/W3009955364","https://openalex.org/W3038067977","https://openalex.org/W3098397564","https://openalex.org/W3100200555","https://openalex.org/W3102885034","https://openalex.org/W3103654209","https://openalex.org/W3104413728","https://openalex.org/W3108987040","https://openalex.org/W3109010114","https://openalex.org/W3128354053","https://openalex.org/W3166407463","https://openalex.org/W3208078891","https://openalex.org/W4293571283","https://openalex.org/W6891753407","https://openalex.org/W6910768893"],"related_works":["https://openalex.org/W2134613344","https://openalex.org/W4200149527","https://openalex.org/W2045473016","https://openalex.org/W4284882292","https://openalex.org/W2997740458","https://openalex.org/W4379115997","https://openalex.org/W2792100442","https://openalex.org/W3092615945","https://openalex.org/W4214847524","https://openalex.org/W3133505863"],"abstract_inverted_index":{"Simulating":[0],"the":[1,12,29,72],"behavior":[2],"of":[3,11,40,67,99,202],"quantum":[4,18,22,30,68,115,123,190,199,204],"circuits":[5],"on":[6,101,153,161,165,175],"classical":[7,57],"computers":[8],"are":[9,62],"one":[10],"widely":[13],"used":[14],"approaches":[15],"for":[16,103,188,206],"current":[17],"computing":[19],"device":[20],"and":[21,42,48,75,178],"algorithm":[23],"research.":[24],"State-vector":[25],"simulators":[26],"keep":[27],"all":[28,76],"states":[31],"in":[32,44],"main":[33],"memory,":[34],"thus":[35],"consuming":[36],"a":[37,83,97,111,138,156],"large":[38],"amount":[39],"memory":[41,46],"resulting":[43],"great":[45],"access":[47],"communication":[49,87,114,120,141],"overhead":[50],"far":[51],"longer":[52],"than":[53],"calculation":[54],"time.":[55],"Many":[56],"simulators,":[58],"such":[59,92],"as":[60,93],"QuEST,":[61],"designed":[63],"by":[64],"serial":[65],"execution":[66],"gates":[69],"without":[70],"using":[71],"data":[73,86,104,140,147],"locality,":[74],"amplitudes":[77],"need":[78],"to":[79,95,118,133,145,186,196],"be":[80],"exchanged.":[81],"Such":[82],"gate-unaware":[84],"full":[85],"scheme":[88,142],"forces":[89],"powerful":[90],"computation":[91,150],"GPUs":[94,174],"spend":[96],"lot":[98],"time":[100],"waiting":[102],"transmission.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"propose":[110],"gate-aware":[112],"on-demand":[113,139],"simulation":[116],"framework":[117],"optimize":[119,146],"overhead.":[121],"A":[122],"circuit":[124],"partition":[125],"method":[126],"through":[127],"gate":[128],"fusion":[129],"is":[130,143],"first":[131],"proposed":[132,144],"avoid":[134],"unnecessary":[135],"communications.":[136],"Moreover,":[137],"transfer":[148],"among":[149],"nodes.":[151],"Based":[152],"these":[154],"designs,":[155],"prototype":[157],"has":[158],"been":[159],"implemented":[160],"QuEST.":[162,207],"We":[163],"evaluated":[164],"an":[166],"8-node":[167],"cluster":[168],"with":[169],"four":[170],"NVIDIA":[171],"Tesla":[172],"V100":[173],"each":[176],"node":[177],"our":[179],"designs":[180],"can":[181,194],"achieve":[182],"3.0x-15.6x":[183],"speedup":[184],"compared":[185],"QuEST":[187],"32-34-qubit":[189],"systems.":[191],"Moverover,":[192],"it":[193],"scale":[195],"simulate":[197],"37-qubit":[198],"system":[200,205],"instead":[201],"34-qubit":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}
