{"id":"https://openalex.org/W2293114121","doi":"https://doi.org/10.1145/1810085.1810088","title":"Throughput computing","display_name":"Throughput computing","publication_year":2010,"publication_date":"2010-06-02","ids":{"openalex":"https://openalex.org/W2293114121","doi":"https://doi.org/10.1145/1810085.1810088","mag":"2293114121"},"language":"en","primary_location":{"id":"doi:10.1145/1810085.1810088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810085.1810088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International Conference on Supercomputing","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/A5084342236","display_name":"William J. Dally","orcid":"https://orcid.org/0000-0003-4632-2876"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Dally","raw_affiliation_strings":["NVIDIA Corporation / Stanford University"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation / Stanford University","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5084342236"],"corresponding_institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.4994,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69345668,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9922999739646912,"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":0.9786999821662903,"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":0.8415619134902954},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.8129816055297852},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7217906713485718},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6556369066238403},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6089833378791809},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.5892739295959473},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5439060926437378},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.5377130508422852},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5229835510253906},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5080459117889404},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5076488256454468},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.47950416803359985},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4518605172634125},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4384092390537262},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4315924048423767},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.25108614563941956},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17199209332466125},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09853127598762512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415619134902954},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8129816055297852},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7217906713485718},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6556369066238403},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6089833378791809},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.5892739295959473},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5439060926437378},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.5377130508422852},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5229835510253906},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5080459117889404},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5076488256454468},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.47950416803359985},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4518605172634125},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4384092390537262},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4315924048423767},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25108614563941956},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17199209332466125},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09853127598762512},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1810085.1810088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810085.1810088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5199999809265137,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W2468095077","https://openalex.org/W305742777","https://openalex.org/W2121547511"],"abstract_inverted_index":{"A":[0],"qualitative":[1],"change":[2],"in":[3,83,115,135],"the":[4,11,15,23,30,79,84,109,132,159],"scaling":[5,13],"of":[6,14,37,78,88,108,151,171],"semiconductor":[7],"technology":[8],"has":[9,34],"ended":[10],"performance":[12,63,95],"single-thread":[16,71],"processors":[17],"that":[18,58,140],"have":[19],"been":[20],"used":[21],"as":[22],"building":[24],"blocks":[25],"for":[26,29,61,70],"high-performance":[27,47],"computers":[28,36,48],"last":[31],"decade":[32],"and":[33,81,86,99,111,144,153,161,167],"made":[35],"all":[38],"scales":[39],"power":[40,66],"limited.":[41],"In":[42,92],"today's":[43],"power-limited":[44],"regime,":[45],"efficient":[46],"must":[49],"be":[50],"built":[51],"from":[52,97,102,158,164,168],"throughput":[53,90,117],"processors,":[54,55,94],"like":[56],"GPUs,":[57,166],"are":[59],"optimized":[60],"sustained":[62],"per":[64],"unit":[65],"---":[67],"rather":[68],"than":[69],"performance.":[72],"This":[73,146],"talk":[74,147],"will":[75,148],"discuss":[76,149],"some":[77],"challenges":[80],"opportunities":[82],"architecture":[85],"programming":[87,173],"future":[89],"processors.":[91],"these":[93],"derives":[96,101],"parallelism":[98,152],"efficiency":[100],"locality.":[103],"Parallelism":[104],"can":[105],"take":[106],"advantage":[107],"plentiful":[110],"inexpensive":[112],"arithmetic":[113,130],"units":[114],"a":[116,125,136],"processor.":[118],"Without":[119],"locality,":[120],"however,":[121],"bandwidth":[122],"quickly":[123],"becomes":[124],"bottleneck.":[126],"Communication":[127],"bandwidth,":[128],"not":[129],"is":[131],"critical":[133],"resource":[134],"modern":[137],"computing":[138],"system":[139],"dominates":[141],"cost,":[142],"performance,":[143],"power.":[145],"exploitation":[150],"locality":[154],"with":[155],"examples":[156],"drawn":[157],"Imagine":[160],"Merrimac":[162],"projects,":[163],"NVIDIA":[165],"three":[169],"generations":[170],"stream":[172],"systems.":[174]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}