{"id":"https://openalex.org/W2748573297","doi":"https://doi.org/10.1109/micro.2016.7783764","title":"Continuous runahead: Transparent hardware acceleration for memory intensive workloads","display_name":"Continuous runahead: Transparent hardware acceleration for memory intensive workloads","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2748573297","doi":"https://doi.org/10.1109/micro.2016.7783764","mag":"2748573297"},"language":"en","primary_location":{"id":"doi:10.1109/micro.2016.7783764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro.2016.7783764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)","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/A5026546407","display_name":"Milad Hashemi","orcid":"https://orcid.org/0009-0008-9345-607X"},"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":true,"raw_author_name":"Milad Hashemi","raw_affiliation_strings":["University of Texas, Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050695684","display_name":"Onur Mutlu","orcid":"https://orcid.org/0000-0002-0075-2312"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Onur Mutlu","raw_affiliation_strings":["ETH Zurich"],"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070360563","display_name":"Yale N. Patt","orcid":"https://orcid.org/0009-0004-8704-8249"},"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":"Yale N. Patt","raw_affiliation_strings":["University of Texas, Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas, Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026546407"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":4.8199,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.95554124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.9994999766349792,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9965999722480774,"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/instruction-prefetch","display_name":"Instruction prefetch","score":0.9679532647132874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8638274669647217},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6671320199966431},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6540350914001465},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.6299106478691101},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.5442493557929993},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5251390933990479},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.44078871607780457},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3561975359916687},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3555349111557007}],"concepts":[{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.9679532647132874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8638274669647217},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6671320199966431},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6540350914001465},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.6299106478691101},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.5442493557929993},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5251390933990479},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.44078871607780457},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3561975359916687},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3555349111557007},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/micro.2016.7783764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro.2016.7783764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W56414646","https://openalex.org/W1993313731","https://openalex.org/W2066503894","https://openalex.org/W2097385643","https://openalex.org/W2103742924","https://openalex.org/W2105194472","https://openalex.org/W2108977887","https://openalex.org/W2111905231","https://openalex.org/W2118518065","https://openalex.org/W2120274141","https://openalex.org/W2123608497","https://openalex.org/W2128633261","https://openalex.org/W2129381159","https://openalex.org/W2146246439","https://openalex.org/W2149379863","https://openalex.org/W2150143212","https://openalex.org/W2152356827","https://openalex.org/W2153456949","https://openalex.org/W2153515302","https://openalex.org/W2157109334","https://openalex.org/W2157274115","https://openalex.org/W2162773908","https://openalex.org/W2166620913","https://openalex.org/W2167100385","https://openalex.org/W2168214303","https://openalex.org/W2169001628","https://openalex.org/W2170382128","https://openalex.org/W2237666531","https://openalex.org/W2464177207","https://openalex.org/W2537450429","https://openalex.org/W2916411819","https://openalex.org/W3007181776","https://openalex.org/W3144376511","https://openalex.org/W3147011727","https://openalex.org/W4231131543","https://openalex.org/W4232096869","https://openalex.org/W4234107648","https://openalex.org/W4236382111","https://openalex.org/W4238816702","https://openalex.org/W4242484660","https://openalex.org/W4245851057","https://openalex.org/W4246178214","https://openalex.org/W4248446132","https://openalex.org/W4255052811","https://openalex.org/W4255602098","https://openalex.org/W4255807648","https://openalex.org/W4297688712","https://openalex.org/W6602309031","https://openalex.org/W6677859296","https://openalex.org/W6678915101","https://openalex.org/W6681807825","https://openalex.org/W6683129041","https://openalex.org/W6719768283","https://openalex.org/W6759615093","https://openalex.org/W6817964639","https://openalex.org/W6819430493"],"related_works":["https://openalex.org/W2167639078","https://openalex.org/W2379283503","https://openalex.org/W2141676084","https://openalex.org/W2170496111","https://openalex.org/W2165284728","https://openalex.org/W2168962644","https://openalex.org/W2153372734","https://openalex.org/W1480691199","https://openalex.org/W4388454812","https://openalex.org/W2748573297"],"abstract_inverted_index":{"Runahead":[0,139,200],"execution":[1],"pre-executes":[2],"the":[3,29,84,96,107,112,118,148,156,199,214],"application's":[4],"own":[5],"code":[6],"to":[7,100,110,120,126,136,162],"generate":[8],"new":[9],"cache":[10,72,166],"misses.":[11,73,167],"This":[12,74,192],"pre-execution":[13],"results":[14],"in":[15,23,60,129,188],"prefetch":[16,63,160],"requests":[17],"that":[18,53,98,116],"are":[19,57,79,124,133],"overwhelmingly":[20],"accurate":[21],"(95%":[22],"a":[24,39,65,130,137,142,171,177,185,194,202,207,223,227],"realistic":[25],"system":[26,189],"configuration":[27],"for":[28],"memory":[30,149,180],"intensive":[31,181],"SPEC":[32],"CPU2006":[33],"benchmarks),":[34],"much":[35],"more":[36],"so":[37],"than":[38],"global":[40],"history":[41],"buffer":[42],"(GHB)":[43],"or":[44],"stream":[45,109],"prefetcher":[46],"(by":[47],"13%/19%).":[48],"However,":[49],"we":[50,93,221],"also":[51],"find":[52],"current":[54],"runahead":[55,77,204],"techniques":[56],"very":[58],"limited":[59,82],"coverage:":[61],"they":[62],"only":[64],"small":[66],"fraction":[67],"(13%)":[68],"of":[69,86,114,164,179],"all":[70],"runahead-reachable":[71,165],"is":[75,170,193,216],"because":[76],"intervals":[78],"short":[80,102],"and":[81,132,184,206],"by":[83],"duration":[85],"each":[87],"full-window":[88],"stall.":[89,121],"In":[90],"this":[91],"work,":[92],"explore":[94],"removing":[95],"constraints":[97],"lead":[99],"these":[101],"intervals.":[103],"We":[104],"dynamically":[105],"filter":[106],"instruction":[108],"identify":[111],"chains":[113],"operations":[115,123],"cause":[117],"pipeline":[119],"These":[122],"renamed":[125],"execute":[127],"speculatively":[128],"loop":[131],"then":[134],"migrated":[135],"Continuous":[138],"Engine":[140],"(CRE),":[141],"shared":[143],"multi-core":[144],"accelerator":[145],"located":[146],"at":[147],"controller.":[150],"The":[151,168],"CRE":[152,215],"runs":[153],"ahead":[154],"with":[155,218,229],"chain":[157],"continuously,":[158],"increasing":[159],"coverage":[161],"70%":[163],"result":[169],"43.3%":[172],"weighted":[173],"speedup":[174],"gain":[175,197,209,225],"on":[176],"set":[178],"quad-core":[182],"workloads":[183],"significant":[186],"reduction":[187],"energy":[190],"consumption.":[191],"21.9%":[195],"performance":[196],"over":[198,210,226],"Buffer,":[201],"state-of-the-art":[203],"proposal":[205],"13.2%/13.5%":[208],"GHB/stream":[211],"prefetching.":[212],"When":[213],"combined":[217],"GHB":[219,230],"prefetching,":[220],"observe":[222],"23.5%":[224],"baseline":[228],"prefetching":[231],"alone.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}