{"id":"https://openalex.org/W4384824822","doi":"https://doi.org/10.5821/dissertation-2117-368618","title":"On the co-design of scientific applications and long vector architectures","display_name":"On the co-design of scientific applications and long vector architectures","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4384824822","doi":"https://doi.org/10.5821/dissertation-2117-368618"},"language":"en","primary_location":{"id":"doi:10.5821/dissertation-2117-368618","is_oa":true,"landing_page_url":"https://doi.org/10.5821/dissertation-2117-368618","pdf_url":"https://upcommons.upc.edu/bitstream/2117/368618/1/TCGC1de1.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Universitat Polit\u00e8cnica de Catalunya","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://upcommons.upc.edu/bitstream/2117/368618/1/TCGC1de1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065367605","display_name":"Constantino G\u00f3mez Crespo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"G\u00f3mez Crespo, Constantino","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065367605"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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":0.9977999925613403,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.7743513584136963},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.641334593296051},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5841507315635681},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5382051467895508},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5227023363113403},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.49872446060180664},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44241487979888916},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.413139283657074},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36764445900917053},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3457649052143097},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.32366061210632324},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.291165828704834},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17466944456100464},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.14135396480560303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743513584136963},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.641334593296051},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5841507315635681},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5382051467895508},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5227023363113403},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.49872446060180664},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44241487979888916},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.413139283657074},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36764445900917053},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3457649052143097},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.32366061210632324},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.291165828704834},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17466944456100464},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.14135396480560303},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5821/dissertation-2117-368618","is_oa":true,"landing_page_url":"https://doi.org/10.5821/dissertation-2117-368618","pdf_url":"https://upcommons.upc.edu/bitstream/2117/368618/1/TCGC1de1.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Universitat Polit\u00e8cnica de Catalunya","raw_type":"dissertation"},{"id":"pmh:oai:www.tdx.cat:10803/674412","is_oa":true,"landing_page_url":"http://hdl.handle.net/10803/674412","pdf_url":null,"source":{"id":"https://openalex.org/S4306401111","display_name":"Tesis Doctorals en Xarxa (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TDX (Tesis Doctorals en Xarxa)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.5821/dissertation-2117-368618","is_oa":true,"landing_page_url":"https://doi.org/10.5821/dissertation-2117-368618","pdf_url":"https://upcommons.upc.edu/bitstream/2117/368618/1/TCGC1de1.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Universitat Polit\u00e8cnica de Catalunya","raw_type":"dissertation"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8799999952316284,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4384824822.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2735130281","https://openalex.org/W1990309876","https://openalex.org/W79990711","https://openalex.org/W4295935130","https://openalex.org/W1480947737","https://openalex.org/W2953368509","https://openalex.org/W3010779417","https://openalex.org/W4294538768","https://openalex.org/W2529649238","https://openalex.org/W1835470271"],"abstract_inverted_index":{"The":[0,96],"landscape":[1],"of":[2,21,81,90,101,131,149,156,219,237,260,280,300,317,327,365],"High":[3],"Performance":[4],"Computing":[5],"(HPC)":[6],"system":[7,178],"architectures":[8,86],"keeps":[9],"expanding":[10],"with":[11,171,196],"new":[12,150],"technologies":[13],"and":[14,83,92,111,128,137,145,169,180,200,205,243,263,277,305,312,339,349,357],"increased":[15],"complexity.":[16],"To":[17,134],"improve":[18],"the":[19,31,37,43,73,78,88,99,106,112,115,125,132,147,154,173,177,235,258,288,310,318,324,362],"efficiency":[20],"next-generation":[22,230],"compute":[23,79,129,198,367],"devices,":[24],"architects":[25],"are":[26],"looking":[27],"for":[28,143,315,361],"solutions":[29],"beyond":[30],"commodity":[32],"CPU":[33,58,136],"approach.":[34],"In":[35,162,250],"2021,":[36,420],"five":[38],"most":[39],"powerful":[40],"supercomputers":[41],"in":[42,72,98,103,124,226,241,292,322],"world":[44],"use":[45],"either":[46],"GP-GPU":[47],"(General-purpose":[48],"computing":[49,231],"on":[50,153,257,331],"graphics":[51],"processing":[52],"units)":[53],"accelerators":[54],"or":[55],"a":[56,104,121,164,184,216,238,270,297,432,510,568,775,792],"customized":[57],"specially":[59],"designed":[60],"to":[61,70,192,210,214,224],"target":[62],"HPC":[63,282,294,710,729],"applications.":[64,301,319],"This":[65],"trend":[66],"is":[67,183],"only":[68],"expected":[69],"grow":[71],"next":[74,363],"years":[75],"motivated":[76],"by":[77,246],"demands":[80],"science":[82],"industry.":[84],"As":[85],"evolve,":[87],"ecosystem":[89],"tools":[91,142],"applications":[93,159,188,244,262,330],"must":[94,189],"follow.":[95],"choices":[97],"number":[100],"cores":[102],"socket,":[105],"floating":[107],"point-units":[108],"per":[109],"core":[110],"bandwidth":[113,202,342],"through":[114],"memory":[116,201,341],"hierarchy":[117],"among":[118],"others,":[119],"have":[120],"large":[122,165,227,289],"impact":[123,148],"power":[126,278],"consumption":[127,307],"capabilities":[130,199],"devices.":[133,368],"balance":[135],"accelerators,":[138,334],"designers":[139],"require":[140],"accurate":[141,275],"analyzing":[144,309],"predicting":[146],"architectural":[151,348],"features":[152],"performance":[155,276,338],"complex":[157,174],"scientific":[158,261],"at":[160],"scale.":[161],"such":[163],"design":[166,290],"space,":[167],"capturing":[168],"modeling":[170],"simulators":[172],"interactions":[175],"between":[176],"software":[179,358,586,807],"hardware":[181,242,356,593,663,805],"components":[182],"defying":[185],"challenge.":[186],"Moreover,":[187],"be":[190,211,234],"able":[191],"exploit":[193],"those":[194],"designs":[195],"aggressive":[197],"configurations.":[203],"Algorithms":[204],"data":[206],"structures":[207],"will":[208,233,353],"need":[209],"redesigned":[212],"accordingly":[213],"expose":[215],"high":[217],"degree":[218],"data-level":[220],"parallelism":[221],"allowing":[222],"them":[223],"scale":[225],"systems.":[228,283],"Therefore,":[229],"devices":[232],"result":[236],"co-design":[239,259,359],"effort":[240],"supported":[245],"advanced":[247],"simulation":[248,272],"tools.":[249],"this":[251],"thesis,":[252],"we":[253,286,345],"focus":[254],"our":[255],"work":[256],"long":[264],"vector":[265,333],"architectures.":[266],"We":[267,302,320],"significantly":[268],"extend":[269],"multi-scale":[271],"toolchain":[273],"enabling":[274],"estimations":[279],"large-scale":[281],"Through":[284],"simulation,":[285],"explore":[287],"space":[291],"current":[293],"trends":[295],"over":[296],"wide":[298],"range":[299],"extract":[303],"speedup":[304],"energy":[306],"figures":[308],"trade-offs":[311],"optimal":[313],"configurations":[314],"each":[316],"describe":[321],"detail":[323],"optimization":[325],"process":[326],"two":[328],"challenging":[329],"real":[332],"achieving":[335],"outstanding":[336],"operation":[337],"full":[340],"utilization.":[343],"Overall,":[344],"provide":[346],"evidence-based":[347],"programming":[350],"recommendations":[351],"that":[352],"serve":[354],"as":[355],"guidelines":[360],"generation":[364],"specialized":[366],"El":[369],"panorama":[370],"de":[371,374,380,384,401,405,407,416,436,463,466,468,482,494,500,508,512,515,526,531,533,555,558,564,574,587,592,604,611,615,617,623,633,635,649,651,656,659,672,683,694,704,708,711,716,722,724,734,755,763,765,777,784,794,812,814],"las":[372,417,461,477,498,529,538,581,599,725,746,749,756],"arquitecturas":[373,478,687],"los":[375,409,421,449,534,541,543,590],"sistemas":[376,709],"para":[377,445,549,628,696,752,802,808],"la":[378,399,402,469,472,513,559,646,697,739,809],"Computaci\u00f3n":[379],"Alto":[381],"Rendimiento":[382],"(HPC,":[383],"sus":[385,437],"siglas":[386,438],"en":[387,439,523,561,640,662,665,680,728,759,768],"ingl\u00e9s)":[388,440],"sigue":[389],"expandi\u00e9ndose":[390],"con":[391,579,608],"nuevas":[392,556],"tecnolog\u00edas":[393],"y":[394,471,484,505,528,540,551,577,589,613,621,667,686,706,741,748,779,796,806],"complejidad":[395],"adicional.":[396],"Para":[397,536],"mejorar":[398],"eficiencia":[400],"pr\u00f3xima":[403],"generaci\u00f3n":[404,648,811],"dispositivos":[406,813],"computaci\u00f3n,":[408],"arquitectos":[410],"est\u00e1n":[411],"buscando":[412],"soluciones":[413],"m\u00e1s":[414,424,464],"all\u00e1":[415],"CPUs.":[418],"En":[419,448,674],"cinco":[422],"supercomputadores":[423],"potentes":[425],"del":[426,782],"mundo":[427],"utilizan":[428],"aceleradores":[429,769],"gr\u00e1ficos":[430],"aplicados":[431],"prop\u00f3sito":[433],"general":[434],"(GP-GPU,":[435],"o":[441],"CPUs":[442,539],"dise\u00f1adas":[443],"especialmente":[444],"aplicaciones":[446,485,566,600,666,684,767],"HPC.":[447],"pr\u00f3ximos":[450],"a\u00f1os,":[451],"se":[452],"espera":[453],"que":[454,476,798],"esta":[455,675],"tendencia":[456],"siga":[457],"creciendo":[458],"motivada":[459],"por":[460,496,503,669],"demandas":[462],"potencia":[465,707],"computaci\u00f3n":[467],"ciencia":[470],"industria.":[473],"A":[474,714],"medida":[475],"evolucionan,":[479],"el":[480,492,506,524,553,562,585,654,681,719,742,761],"ecosistema":[481],"herramientas":[483,547,671,695],"les":[486],"debe":[487],"seguir.":[488],"Las":[489],"decisiones":[490],"eligiendo":[491],"n\u00famero":[493],"n\u00facleos":[495],"z\u00f3calo,":[497],"unidades":[499],"coma":[501],"flotante":[502],"n\u00facleo":[504],"ancho":[507,614,783],"banda":[509,616],"trav\u00e9s":[511,715],"jerarqu\u00eda":[514],"memor\u00eda":[516],"entre":[517,584],"otros,":[518],"tienen":[519],"un":[520,595,630,657,731,772],"gran":[521,569,712,720],"impacto":[522,554],"consumo":[525,743],"energ\u00eda":[527],"capacidades":[530,610],"c\u00f3mputo":[532,612],"dispositivos.":[535],"equilibrar":[537],"aceleradores,":[542],"dise\u00f1adores":[544],"deben":[545,601],"utilizar":[546],"precisas":[548],"analizar":[550],"predecir":[552],"caracter\u00edsticas":[557],"arquitectura":[560,795],"rendimiento":[563,705,773],"complejas":[565,582],"cient\u00edficas":[567,685],"escala.":[570,713],"Dado":[571],"semejante":[572],"espacio":[573,721],"dise\u00f1o,":[575],"capturar":[576],"modelar":[578],"simuladores":[580],"interacciones":[583],"sistema":[588],"componentes":[591],"es":[594],"reto":[596],"desafiante.":[597],"Adem\u00e1s,":[598],"ser":[602,626],"capaces":[603],"explotar":[605],"tales":[606],"dise\u00f1os":[607],"agresivas":[609],"memoria.":[618],"Los":[619],"algoritmos":[620],"estructuras":[622],"datos":[624,636,737],"deber\u00e1n":[625],"redise\u00f1adas":[627],"exponer":[629],"alto":[631],"grado":[632],"paralelismo":[634],"permitiendo":[637,700],"as\u00ed":[638,701],"escalarlos":[639],"grandes":[641],"sistemas.":[642],"Por":[643],"lo":[644],"tanto,":[645],"siguiente":[647,810],"disp\u00f3sitivos":[650],"c\u00e1lculo":[652,815],"ser\u00e1":[653],"resultado":[655],"esfuerzo":[658],"codise\u00f1o":[660,682],"tanto":[661],"como":[664,800],"soportado":[668],"avanzadas":[670],"simulaci\u00f3n.":[673],"tesis,":[676],"centramos":[677],"nuestro":[678],"trabajo":[679],"vectoriales":[688],"largas.":[689],"Extendemos":[690],"significativamente":[691],"una":[692,754],"serie":[693],"simulaci\u00f3n":[698],"multiescala":[699],"obtener":[702],"estimaciones":[703],"simulaciones,":[717],"exploramos":[718],"dise\u00f1o":[723],"tendencias":[726],"actuales":[727],"sobre":[730,738],"amplio":[732],"rango":[733],"aplicaciones.":[735,757],"Extraemos":[736],"mejora":[740],"energ\u00e9tico":[744],"analizando":[745],"contrapartidas":[747],"configuraciones":[750],"\u00f3ptimas":[751],"cada":[753],"Describimos":[758],"detalle":[760],"proceso":[762],"optimizaci\u00f3n":[764],"dos":[766],"vectoriales,":[770],"obteniendo":[771],"extraordinario":[774],"nivel":[776,793],"operaciones":[778],"completa":[780],"utilizaci\u00f3n":[781],"memoria":[785],"disponible.":[786],"Con":[787],"todo,":[788],"ofrecemos":[789],"recomendaciones":[790],"emp\u00edricas":[791],"programaci\u00f3n":[797],"servir\u00e1n":[799],"instrucciones":[801],"dise\u00f1ar":[803],"mejor":[804],"especializados.":[816]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2023-07-21T00:00:00"}
