{"id":"https://openalex.org/W2237666531","doi":"https://doi.org/10.1145/2830772.2830812","title":"Filtered runahead execution with a runahead buffer","display_name":"Filtered runahead execution with a runahead buffer","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2237666531","doi":"https://doi.org/10.1145/2830772.2830812","mag":"2237666531"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830812","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","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":false,"raw_author_name":"Milad Hashemi","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"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":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.9767,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.86605061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"369"},"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":0.9983000159263611,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9970999956130981,"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":0.8633168935775757},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6126754283905029},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.599591851234436},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.59902024269104},{"id":"https://openalex.org/keywords/buffer","display_name":"Buffer (optical fiber)","score":0.5425539612770081},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5097708106040955},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.48409712314605713},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4378890097141266},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.42728516459465027},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41299664974212646},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32750844955444336},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07502424716949463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633168935775757},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6126754283905029},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.599591851234436},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.59902024269104},{"id":"https://openalex.org/C145018004","wikidata":"https://www.wikidata.org/wiki/Q4985944","display_name":"Buffer (optical fiber)","level":2,"score":0.5425539612770081},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5097708106040955},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.48409712314605713},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4378890097141266},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.42728516459465027},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41299664974212646},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32750844955444336},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07502424716949463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830772.2830812","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2830772.2830812","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W56414646","https://openalex.org/W1983051972","https://openalex.org/W1983096721","https://openalex.org/W2019674193","https://openalex.org/W2080136019","https://openalex.org/W2096234108","https://openalex.org/W2097385643","https://openalex.org/W2099089002","https://openalex.org/W2103742924","https://openalex.org/W2105194472","https://openalex.org/W2111905231","https://openalex.org/W2118518065","https://openalex.org/W2120274141","https://openalex.org/W2123608323","https://openalex.org/W2123608497","https://openalex.org/W2126605567","https://openalex.org/W2131498141","https://openalex.org/W2141165425","https://openalex.org/W2143068308","https://openalex.org/W2143285027","https://openalex.org/W2146173591","https://openalex.org/W2146246439","https://openalex.org/W2149379863","https://openalex.org/W2151345470","https://openalex.org/W2152356827","https://openalex.org/W2153456949","https://openalex.org/W2153515302","https://openalex.org/W2158630919","https://openalex.org/W2159767828","https://openalex.org/W2162773908","https://openalex.org/W2166620913","https://openalex.org/W2170382128","https://openalex.org/W2464177207","https://openalex.org/W2537450429","https://openalex.org/W2916411819","https://openalex.org/W3147011727","https://openalex.org/W4232096869","https://openalex.org/W4245851057","https://openalex.org/W4247641071","https://openalex.org/W4255602098","https://openalex.org/W4292169167","https://openalex.org/W6681807825","https://openalex.org/W6759615093"],"related_works":["https://openalex.org/W2097227107","https://openalex.org/W2366025885","https://openalex.org/W4233342643","https://openalex.org/W2007889530","https://openalex.org/W4243779378","https://openalex.org/W1859219301","https://openalex.org/W4200583004","https://openalex.org/W188801065","https://openalex.org/W4200108949","https://openalex.org/W179829755"],"abstract_inverted_index":{"Runahead":[0,47],"execution":[1],"dynamically":[2],"expands":[3],"the":[4,20,29,33,72,77,96,107,120,163],"instruction":[5],"window":[6],"of":[7,10,31,126,132,146,152],"an":[8,129,149],"out":[9],"order":[11],"processor":[12],"to":[13,35,38,82],"generate":[14],"memory":[15],"level":[16],"parallelism":[17],"(MLP)":[18],"while":[19],"core":[21,97],"would":[22],"otherwise":[23],"be":[24,110],"stalled.":[25],"Unfortunately,":[26],"runahead":[27,73,78,92,136,164],"has":[28],"disadvantage":[30],"requiring":[32],"front-end":[34,108],"remain":[36],"active":[37],"supply":[39,83],"instructions.":[40,52,84],"We":[41,53,66],"propose":[42,156],"a":[43,117,123,143,157],"new":[44],"structure":[45],"(the":[46],"Buffer)":[48],"for":[49],"supplying":[50],"these":[51,68],"note":[54],"that":[55,160],"cache":[56],"misses":[57],"are":[58],"often":[59],"caused":[60],"by":[61],"repetitive,":[62],"short":[63],"dependence":[64,69],"chains.":[65],"store":[67],"chains":[70],"in":[71,142],"buffer.":[74],"During":[75],"runahead,":[76,168],"buffer":[79,165],"is":[80,122],"used":[81],"This":[85],"generates":[86],"2x":[87],"more":[88],"MLP":[89],"than":[90],"traditional":[91,167],"on":[93],"average":[94],"because":[95],"can":[98,109],"run":[99],"further":[100],"ahead.":[101],"It":[102],"also":[103],"saves":[104],"energy":[105,114,130,139,150],"since":[106],"clock-gated,":[111],"reducing":[112],"dynamic":[113],"consumption.":[115],"Over":[116],"no-prefetching/prefetching":[118],"baseline,":[119],"result":[121],"performance":[124,144],"benefit":[125,145],"17.2%/7.8%":[127],"and":[128,166],"reduction":[131],"6.7%/4.5%":[133],"respectively.":[134],"Traditional":[135],"with":[137],"additional":[138],"optimizations":[140],"results":[141],"12.1%/5.9%":[147],"but":[148],"increase":[151],"9.5%/5.4%.":[153],"Finally,":[154],"we":[155],"hybrid":[158],"policy":[159],"switches":[161],"between":[162],"maximizing":[169],"performance.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
