{"id":"https://openalex.org/W2152695949","doi":"https://doi.org/10.1145/264107.264158","title":"The interaction of software prefetching with ILP processors in shared-memory systems","display_name":"The interaction of software prefetching with ILP processors in shared-memory systems","publication_year":1997,"publication_date":"1997-05-01","ids":{"openalex":"https://openalex.org/W2152695949","doi":"https://doi.org/10.1145/264107.264158","mag":"2152695949"},"language":"en","primary_location":{"id":"doi:10.1145/264107.264158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/264107.264158","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/264107.264158","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th annual international symposium on Computer architecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/264107.264158","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011491987","display_name":"Parthasarathy Ranganathan","orcid":"https://orcid.org/0000-0002-9751-5902"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Parthasarathy Ranganathan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110871804","display_name":"Vijay S. Pai","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay S. Pai","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073752172","display_name":"Hazim Abdel-Shafi","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hazim Abdel-Shafi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086111967","display_name":"Sarita V. Adve","orcid":"https://orcid.org/0000-0002-3403-5119"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarita V. Adve","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Rice University, Houston, Texas"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rice University, Houston, Texas","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011491987"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":4.8715,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.9514393,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.8380378484725952},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7831186056137085},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5486689805984497},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5468279719352722},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.5330449938774109},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.480714350938797},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.4639996886253357},{"id":"https://openalex.org/keywords/consistency-model","display_name":"Consistency model","score":0.4581846296787262},{"id":"https://openalex.org/keywords/worst-case-execution-time","display_name":"Worst-case execution time","score":0.44945329427719116},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.44190043210983276},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43643930554389954},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.3107103109359741},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2860545516014099},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.26154470443725586},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2593606114387512},{"id":"https://openalex.org/keywords/data-consistency","display_name":"Data consistency","score":0.19359052181243896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8380378484725952},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7831186056137085},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5486689805984497},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5468279719352722},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.5330449938774109},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.480714350938797},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.4639996886253357},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.4581846296787262},{"id":"https://openalex.org/C200130814","wikidata":"https://www.wikidata.org/wiki/Q362858","display_name":"Worst-case execution time","level":3,"score":0.44945329427719116},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.44190043210983276},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43643930554389954},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3107103109359741},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2860545516014099},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26154470443725586},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2593606114387512},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.19359052181243896},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1145/264107.264158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/264107.264158","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/264107.264158","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th annual international symposium on Computer architecture","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.40.1618","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.1618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rsim.cs.uiuc.edu/~sadve/Publications/isca97.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.50.5542","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.50.5542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-brazos.rice.edu/brazos/papers/hazim_isca97.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.52.4883","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.52.4883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-ece.rice.edu/~parthas/publications/isca97.ps.Z","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.250","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.250","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hpl.hp.com/personal/Partha_Ranganathan/papers/1997/1997_isca_prefetching.pdf","raw_type":"text"},{"id":"pmh:oai:scholarship.rice.edu:1911/20242","is_oa":false,"landing_page_url":"http://hdl.handle.net/1911/20242","pdf_url":null,"source":{"id":"https://openalex.org/S4306401268","display_name":"Rice Digital Scholarship Archive (Rice University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74775410","host_organization_name":"Rice University","host_organization_lineage":["https://openalex.org/I74775410"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/264107.264158","is_oa":true,"landing_page_url":"https://doi.org/10.1145/264107.264158","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/264107.264158","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th annual international symposium on Computer architecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G193062771","display_name":"CISE Research Infrastructure: Multi-processor Cluster       Computing, (A Research Infrastructure Proposal)","funder_award_id":"9502791","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G405364817","display_name":"CAREER:  An Integrated Approach for Improving the           Performance, Programmability, and Portability of Shared     Memory Multiprocessors","funder_award_id":"9502500","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8143822676","display_name":"RESEARCH INITIATION AWARD: Wear Mechanisms and New Methods  of Wear Prevention in Artificial Joints","funder_award_id":"9410467","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2152695949.pdf","grobid_xml":"https://content.openalex.org/works/W2152695949.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W156825290","https://openalex.org/W1490296398","https://openalex.org/W1509928333","https://openalex.org/W1544033533","https://openalex.org/W1638164693","https://openalex.org/W1885534640","https://openalex.org/W1966285605","https://openalex.org/W1991582153","https://openalex.org/W2054739713","https://openalex.org/W2077790567","https://openalex.org/W2078081736","https://openalex.org/W2081644593","https://openalex.org/W2095679548","https://openalex.org/W2096956970","https://openalex.org/W2099958604","https://openalex.org/W2101377877","https://openalex.org/W2104932676","https://openalex.org/W2107354725","https://openalex.org/W2119410522","https://openalex.org/W2129094586","https://openalex.org/W2129269323","https://openalex.org/W2135393198","https://openalex.org/W2136348740","https://openalex.org/W2136501088","https://openalex.org/W2145021036","https://openalex.org/W2145908511","https://openalex.org/W2148740960","https://openalex.org/W2163196718","https://openalex.org/W2163820265","https://openalex.org/W2171564459","https://openalex.org/W2176864362","https://openalex.org/W2295099251","https://openalex.org/W2913305800","https://openalex.org/W4230333905","https://openalex.org/W4285719527","https://openalex.org/W6632581215"],"related_works":["https://openalex.org/W2462936459","https://openalex.org/W1569389315","https://openalex.org/W2790478050","https://openalex.org/W3001388538","https://openalex.org/W3174582865","https://openalex.org/W2503642292","https://openalex.org/W9649600","https://openalex.org/W2129094586","https://openalex.org/W2152695949","https://openalex.org/W4235872354"],"abstract_inverted_index":{"Current":[0],"microprocessors":[1],"aggressively":[2],"exploit":[3],"instruction-level":[4],"parallelism":[5],"(ILP)":[6],"through":[7],"techniques":[8],"such":[9,36],"as":[10],"multiple":[11],"issue,":[12],"dynamic":[13],"scheduling,":[14],"and":[15,168],"non-blocking":[16],"reads.":[17],"Recent":[18],"work":[19],"has":[20],"shown":[21],"that":[22,61,174],"memory":[23,52,98,114,145],"latency":[24],"remains":[25],"a":[26,187],"significant":[27,66,188],"performance":[28,163],"bottleneck":[29],"for":[30,74,118,179],"shared-memory":[31],"multiprocessor":[32],"systems":[33],"built":[34,54],"of":[35,43,46,55,77,101,121,129,141,164,182],"processors.This":[37],"paper":[38,136],"provides":[39,186],"the":[40,44,97,122,139,162],"first":[41],"study":[42],"effectiveness":[45],"software-controlled":[47],"non-binding":[48],"prefetching":[49,63,90,143,159],"in":[50,65,68,95,126,190],"shared":[51],"multiprocessors":[53],"state-of-the-art":[56],"ILP-based":[57,149],"processors.":[58],"We":[59,172],"find":[60,173],"software":[62,89,112,142,158,177],"results":[64],"reductions":[67],"execution":[69,102,124,191],"time":[70,103,116,125,192],"(12%":[71],"to":[72,86,155,194,197],"31%)":[73],"three":[75,180],"out":[76,128,181],"five":[78,130,183],"applications":[79,131],"on":[80,104,132,148],"an":[81,105],"ILP":[82,106,134],"system.":[83,107],"However,":[84],"compared":[85,196],"previous-generation":[87],"system,":[88],"is":[91],"significantly":[92],"less":[93],"effective":[94],"reducing":[96],"stall":[99,115],"component":[100],"Consequently,":[108],"even":[109,175],"after":[110],"adding":[111],"prefetching,":[113,178],"accounts":[117],"over":[119],"30%":[120],"total":[123],"four":[127],"our":[133],"system.This":[135],"also":[137],"investigates":[138],"interaction":[140],"with":[144,176],"consistency":[146,166,170],"models":[147],"multiprocessors.":[150],"In":[151],"particular,":[152],"we":[153],"seek":[154],"determine":[156],"whether":[157],"can":[160],"equalize":[161],"sequential":[165],"(SC)":[167],"release":[169],"(RC).":[171],"applications,":[184],"RC":[185],"reduction":[189],"(15%":[193],"40%)":[195],"SC.":[198]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}