{"id":"https://openalex.org/W3037865181","doi":"https://doi.org/10.1145/3369583.3393611","title":"High Performance is All about Minimizing Data Movement","display_name":"High Performance is All about Minimizing Data Movement","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3037865181","doi":"https://doi.org/10.1145/3369583.3393611","mag":"3037865181"},"language":"en","primary_location":{"id":"doi:10.1145/3369583.3393611","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3369583.3393611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing","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/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, Salt Lake City, UT, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5030152493"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.08173635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"4"},"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8504925966262817},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8338252305984497},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7327283620834351},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5420220494270325},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.5233741998672485},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.47025051712989807},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4657837748527527},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4373303949832916},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4169892966747284},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.33108067512512207},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.23450776934623718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504925966262817},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8338252305984497},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7327283620834351},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5420220494270325},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.5233741998672485},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.47025051712989807},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4657837748527527},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4373303949832916},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4169892966747284},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33108067512512207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.23450776934623718},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3369583.3393611","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3369583.3393611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2049487370","https://openalex.org/W2903775786","https://openalex.org/W2984920043"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W4388155270","https://openalex.org/W1872724644","https://openalex.org/W2111416043","https://openalex.org/W4243399827","https://openalex.org/W1975522091","https://openalex.org/W575672070","https://openalex.org/W2147358386","https://openalex.org/W3195293013"],"abstract_inverted_index":{"High-performance":[0],"applications":[1],"running":[2],"on":[3,71],"current":[4],"and":[5,29,31,57,59,76,84,88,99,106],"future":[6],"architectures":[7,55,123],"are":[8],"mostly":[9],"performance-limited":[10],"by":[11],"the":[12,19,40,94,119,126],"cost":[13],"of":[14,22,42,53,74,96,121],"data":[15,44,48,75,86,103],"movement,":[16,87],"vertically":[17],"through":[18],"memory":[20,60],"hierarchy":[21],"a":[23,51,63,72],"node":[24],"or":[25],"between":[26],"CPU":[27],"host":[28],"accelerator,":[30],"horizontally":[32],"across":[33,50,118],"nodes.":[34],"In":[35],"this":[36],"talk,":[37],"we":[38],"discuss":[39],"role":[41],"packed":[43],"layout":[45,104],"in":[46,125],"optimizing":[47],"movement":[49],"variety":[52],"different":[54],"(CPU":[56],"GPU)":[58],"systems.":[61],"Conceptually,":[62],"high":[64],"performance":[65,116],"application":[66,98],"is":[67,79],"defined":[68],"as":[69],"operations":[70],"unit":[73],"parallelism":[77],"that":[78],"designed":[80],"for":[81,114],"efficient":[82],"vertical":[83],"horizontal":[85],"can":[89],"be":[90],"tailored":[91],"to":[92],"match":[93],"requirements":[95],"an":[97],"target":[100],"architecture.":[101],"Integrating":[102],"abstractions":[105],"optimizations":[107],"into":[108],"programming":[109],"systems":[110],"provides":[111],"critical":[112],"technology":[113],"achieving":[115],"portability":[117],"diversity":[120],"high-performance":[122],"arising":[124],"exascale":[127],"era.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}