{"id":"https://openalex.org/W3166489582","doi":"https://doi.org/10.1145/3458357","title":"Flynn\u2019s Reconciliation","display_name":"Flynn\u2019s Reconciliation","publication_year":2021,"publication_date":"2021-06-08","ids":{"openalex":"https://openalex.org/W3166489582","doi":"https://doi.org/10.1145/3458357","mag":"3166489582"},"language":"en","primary_location":{"id":"doi:10.1145/3458357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3458357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3458357","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3458357","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053547794","display_name":"Daniel Thuerck","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Daniel Thuerck","raw_affiliation_strings":["NEC Laboratories Europe and TU Darmstadt, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories Europe and TU Darmstadt, Heidelberg, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110023001","display_name":"Nicolas Weber","orcid":"https://orcid.org/0000-0003-0032-9511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Weber","raw_affiliation_strings":["NEC Laboratories Europe, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories Europe, Heidelberg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049867893","display_name":"Roberto Bifulco","orcid":"https://orcid.org/0000-0002-9403-0336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Bifulco","raw_affiliation_strings":["NEC Laboratories Europe, Heidelberg, Germany"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories Europe, Heidelberg, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053547794"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.06942253,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980999827384949,"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":0.9035339951515198},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.748924970626831},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7427305579185486},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.616836667060852},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.606642484664917},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4913236200809479},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46365436911582947},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.45704159140586853},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44221821427345276},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4336888790130615},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4264426529407501},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.4171302616596222},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4028754234313965}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9035339951515198},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.748924970626831},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7427305579185486},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.616836667060852},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.606642484664917},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4913236200809479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46365436911582947},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.45704159140586853},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44221821427345276},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4336888790130615},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4264426529407501},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.4171302616596222},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4028754234313965},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3458357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3458357","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3458357","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3458357","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3458357","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3166489582.pdf","grobid_xml":"https://content.openalex.org/works/W3166489582.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1149960754","https://openalex.org/W1586016561","https://openalex.org/W1984222112","https://openalex.org/W2011357920","https://openalex.org/W2012231377","https://openalex.org/W2045886945","https://openalex.org/W2053375152","https://openalex.org/W2067635581","https://openalex.org/W2069703635","https://openalex.org/W2081373884","https://openalex.org/W2099758780","https://openalex.org/W2107911628","https://openalex.org/W2121176848","https://openalex.org/W2127594310","https://openalex.org/W2137857636","https://openalex.org/W2147654959","https://openalex.org/W2153185479","https://openalex.org/W2171399035","https://openalex.org/W2292182532","https://openalex.org/W2292282166","https://openalex.org/W2476944423","https://openalex.org/W2562674124","https://openalex.org/W2562983784","https://openalex.org/W2570625112","https://openalex.org/W2729851701","https://openalex.org/W2753734581","https://openalex.org/W2766807579","https://openalex.org/W2786704328","https://openalex.org/W2787898679","https://openalex.org/W2788030525","https://openalex.org/W2792649368","https://openalex.org/W2891890103","https://openalex.org/W2899062157","https://openalex.org/W2912012512","https://openalex.org/W2912841518","https://openalex.org/W2944745903","https://openalex.org/W2979365412","https://openalex.org/W2983655274","https://openalex.org/W2984920043","https://openalex.org/W2987684178","https://openalex.org/W2996807164","https://openalex.org/W2997097284","https://openalex.org/W2999857212","https://openalex.org/W3008788679","https://openalex.org/W3017116334","https://openalex.org/W3021837324","https://openalex.org/W3157870174","https://openalex.org/W4230751061","https://openalex.org/W4239598722","https://openalex.org/W4239600432","https://openalex.org/W4240382083","https://openalex.org/W4242314113","https://openalex.org/W4320063484"],"related_works":["https://openalex.org/W2135947393","https://openalex.org/W2014711461","https://openalex.org/W1994316441","https://openalex.org/W4226225561","https://openalex.org/W2180255888","https://openalex.org/W2659654975","https://openalex.org/W2191246539","https://openalex.org/W2033485113","https://openalex.org/W2009392786","https://openalex.org/W3166489582"],"abstract_inverted_index":{"A":[0],"large":[1],"portion":[2],"of":[3,40,68,73,80],"the":[4,9,50,57,66,81,112],"recent":[5],"performance":[6],"increase":[7],"in":[8],"High":[10],"Performance":[11],"Computing":[12],"(HPC)":[13],"and":[14,70,96,105,110,123,137,155],"Machine":[15],"Learning":[16],"(ML)":[17],"domains":[18],"is":[19,156],"fueled":[20],"by":[21,30,142],"accelerator":[22,61],"cards.":[23],"Many":[24],"popular":[25],"ML":[26],"frameworks":[27],"support":[28],"accelerators":[29],"organizing":[31],"computations":[32],"as":[33],"a":[34,38,78,91,97,116],"computational":[35],"graph":[36],"over":[37,103],"set":[39],"highly":[41],"optimized,":[42],"batched":[43,147],"general-purpose":[44],"kernels.":[45,75],"While":[46],"this":[47],"approach":[48],"simplifies":[49],"kernels\u2019":[51],"implementation":[52],"for":[53,63,129,146],"each":[54],"individual":[55],"accelerator,":[56],"increasing":[58],"heterogeneity":[59],"among":[60],"architectures":[62],"HPC":[64],"complicates":[65],"creation":[67],"portable":[69],"extensible":[71],"libraries":[72,154],"such":[74],"Therefore,":[76],"using":[77],"generalization":[79],"CUDA":[82],"community\u2019s":[83],"warp":[84],"register":[85],"cache":[86],"programming":[87,93],"idiom,":[88],"we":[89],"propose":[90],"new":[92],"idiom":[94],"(CoRe)":[95],"virtual":[98],"architecture":[99],"model":[100],"(PIRCH),":[101],"abstracting":[102],"SIMD":[104],"SIMT":[106],"paradigms.":[107],"We":[108],"define":[109],"automate":[111],"mapping":[113],"process":[114],"from":[115],"single":[117],"source":[118],"to":[119,158],"PIRCH\u2019s":[120],"intermediate":[121],"representation":[122],"develop":[124],"backends":[125],"that":[126],"issue":[127],"code":[128],"three":[130],"different":[131],"architectures:":[132],"Intel":[133],"AVX512,":[134],"NVIDIA":[135],"GPUs,":[136],"NEC":[138],"SX-Aurora.":[139],"Code":[140],"generated":[141],"our":[143],"source-to-source":[144],"compiler":[145],"kernels,":[148],"borG,":[149],"competes":[150],"favorably":[151],"with":[152],"vendor-tuned":[153],"up":[157],"2\u00d7":[159],"faster":[160],"than":[161],"hand-tuned":[162],"kernels":[163],"across":[164],"architectures.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}