{"id":"https://openalex.org/W1989746230","doi":"https://doi.org/10.1145/1274971.1274991","title":"Tradeoff between data-, instruction-, and thread-level parallelism in stream processors","display_name":"Tradeoff between data-, instruction-, and thread-level parallelism in stream processors","publication_year":2007,"publication_date":"2007-06-17","ids":{"openalex":"https://openalex.org/W1989746230","doi":"https://doi.org/10.1145/1274971.1274991","mag":"1989746230"},"language":"en","primary_location":{"id":"doi:10.1145/1274971.1274991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1274991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual 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/A5078262826","display_name":"Jung Ho Ahn","orcid":"https://orcid.org/0000-0003-1733-1394"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jung Ho Ahn","raw_affiliation_strings":["Hewlett-Packard Laboratories, Palo Alto, California"],"affiliations":[{"raw_affiliation_string":"Hewlett-Packard Laboratories, Palo Alto, California","institution_ids":["https://openalex.org/I1324840837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013680653","display_name":"Mattan Erez","orcid":"https://orcid.org/0000-0002-1567-4097"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mattan Erez","raw_affiliation_strings":["University of Texas at Austin, Austin, Texas"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, Texas","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084342236","display_name":"William J. Dally","orcid":"https://orcid.org/0000-0003-4632-2876"},"institutions":[{"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":false,"raw_author_name":"William J. Dally","raw_affiliation_strings":["Stanford University, Stanford, California"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078262826"],"corresponding_institution_ids":["https://openalex.org/I1324840837"],"apc_list":null,"apc_paid":null,"fwci":1.2707,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80275229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"137"},"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/T10829","display_name":"Interconnection Networks and Systems","score":1.0,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8180143237113953},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.772430419921875},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6586424708366394},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.6510351300239563},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.6363903880119324},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5783607363700867},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5679763555526733},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4503806233406067},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35442325472831726},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22667863965034485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8180143237113953},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.772430419921875},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6586424708366394},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.6510351300239563},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.6363903880119324},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5783607363700867},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5679763555526733},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4503806233406067},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35442325472831726},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22667863965034485}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1274971.1274991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1274991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.95.5616","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.95.5616","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.ece.utexas.edu/~merez/ics07_aspect.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1568192366","https://openalex.org/W1575732703","https://openalex.org/W1603895355","https://openalex.org/W1966691503","https://openalex.org/W2005343162","https://openalex.org/W2012252449","https://openalex.org/W2029171059","https://openalex.org/W2032309817","https://openalex.org/W2034147186","https://openalex.org/W2080285119","https://openalex.org/W2083868341","https://openalex.org/W2086485856","https://openalex.org/W2111880608","https://openalex.org/W2114421447","https://openalex.org/W2120230074","https://openalex.org/W2120431055","https://openalex.org/W2122060420","https://openalex.org/W2130836267","https://openalex.org/W2131825507","https://openalex.org/W2133361919","https://openalex.org/W2137653322","https://openalex.org/W2148051985","https://openalex.org/W2152484003","https://openalex.org/W2152687294","https://openalex.org/W2157373341","https://openalex.org/W2161864047","https://openalex.org/W2165964351","https://openalex.org/W2172307690","https://openalex.org/W2179825846","https://openalex.org/W2294451725","https://openalex.org/W2296006986","https://openalex.org/W2296445158","https://openalex.org/W2318915797","https://openalex.org/W2335790294","https://openalex.org/W2416752666","https://openalex.org/W2488097972","https://openalex.org/W2534060050","https://openalex.org/W4253240009","https://openalex.org/W6633991270","https://openalex.org/W6653239367","https://openalex.org/W6682005402","https://openalex.org/W6697333706"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1229628","https://openalex.org/W2468095077","https://openalex.org/W2105992728","https://openalex.org/W1991844655","https://openalex.org/W2009213655","https://openalex.org/W2494130044","https://openalex.org/W2593878938"],"abstract_inverted_index":{"This":[0],"paper":[1],"explores":[2],"the":[3,6,11,32,44,52,74,99,106,120,128,134,137],"scalability":[4],"of":[5,40,47,55,60,79,86,114,125,136],"Stream":[7,28],"Processor":[8,29],"architecture":[9],"along":[10,127],"instruction-,":[12],"data-,":[13],"and":[14,22,30,37,132,140],"thread-level":[15],"parallelism":[16,130],"dimensions.":[17],"We":[18,49,70,89,118],"develop":[19],"detailed":[20],"VLSI-cost":[21],"processor-performance":[23],"models":[24],"for":[25,83,92],"a":[26,80,84,111],"multi-threaded":[27],"evaluate":[31,119],"tradeoffs,":[33],"in":[34],"both":[35],"functionality":[36],"hardware":[38,53,142],"costs,":[39],"mechanisms":[41],"that":[42,51,73,91],"exploit":[43],"different":[45,129],"types":[46],"parallelism.":[48],"show":[50],"overhead":[54],"supporting":[56],"coarse-grained":[57],"independent":[58],"threads":[59],"control":[61,107],"is":[62,101],"15":[63],"--":[64],"86%":[65],"depending":[66],"on":[67,123],"machine":[68],"parameters.":[69],"also":[71],"demonstrate":[72],"performance":[75,100,124],"gains":[76],"provided":[77],"are":[78],"smaller":[81],"magnitude":[82],"set":[85],"numerical":[87],"applications.":[88],"argue":[90],"stream":[93],"applications":[94],"with":[95],"scalable":[96],"parallel":[97],"algorithms":[98],"not":[102],"very":[103],"sensitive":[104],"to":[105],"structures":[108],"used":[109],"within":[110],"large":[112],"range":[113],"area-efficient":[115],"architectural":[116],"choices.":[117],"specific":[121],"effects":[122],"scaling":[126],"dimensions":[131],"explain":[133],"limitations":[135],"ILP,":[138],"DLP,":[139],"TLP":[141],"mechanisms.":[143]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}