{"id":"https://openalex.org/W4394586852","doi":"https://doi.org/10.1145/3631882.3631902","title":"An Empirical Evaluation of PTE Coalescing","display_name":"An Empirical Evaluation of PTE Coalescing","publication_year":2023,"publication_date":"2023-10-02","ids":{"openalex":"https://openalex.org/W4394586852","doi":"https://doi.org/10.1145/3631882.3631902"},"language":"en","primary_location":{"id":"doi:10.1145/3631882.3631902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3631882.3631902","pdf_url":null,"source":{"id":"https://openalex.org/S4306524191","display_name":"Proceedings of the International Symposium on Memory Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Symposium on Memory Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5095044702","display_name":"Eliot H. Solomon","orcid":"https://orcid.org/0009-0001-0570-183X"},"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":"Eliot H. Solomon","raw_affiliation_strings":["Rice University, USA"],"raw_orcid":"https://orcid.org/0009-0001-0570-183X","affiliations":[{"raw_affiliation_string":"Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yufeng Zhou","orcid":"https://orcid.org/0000-0002-8626-2145"},"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":"Yufeng Zhou","raw_affiliation_strings":["Rice University, USA"],"raw_orcid":"https://orcid.org/0000-0002-8626-2145","affiliations":[{"raw_affiliation_string":"Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034020280","display_name":"Alan L. Cox","orcid":"https://orcid.org/0009-0005-4904-9600"},"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":"Alan L. Cox","raw_affiliation_strings":["Rice University, USA"],"raw_orcid":"https://orcid.org/0009-0005-4904-9600","affiliations":[{"raw_affiliation_string":"Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991000294685364,"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":0.9991000294685364,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9835000038146973,"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":0.4736919403076172}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4736919403076172}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3631882.3631902","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3631882.3631902","pdf_url":null,"source":{"id":"https://openalex.org/S4306524191","display_name":"Proceedings of the International Symposium on Memory Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Symposium on Memory Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2004807638","https://openalex.org/W2036250095","https://openalex.org/W2047390994","https://openalex.org/W2089336473","https://openalex.org/W2101196063","https://openalex.org/W2135384752","https://openalex.org/W2146068631","https://openalex.org/W2169875292","https://openalex.org/W2508029432","https://openalex.org/W2576312950","https://openalex.org/W2626757163","https://openalex.org/W2734941459","https://openalex.org/W2794228535","https://openalex.org/W2914209329","https://openalex.org/W2953357877","https://openalex.org/W3042851732","https://openalex.org/W4378710497"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829"],"abstract_inverted_index":{"Superpages":[0],"(also":[1],"known":[2],"as":[3,66],"huge":[4],"pages)":[5],"are":[6,162],"an":[7,211,225],"effective":[8],"technique":[9],"for":[10],"reducing":[11,274],"the":[12,22,26,43,51,72,98,108,123,136,139,147,151,166,170,256,266,275],"latency":[13],"of":[14,25,58,74,181,190,206,258,268,299],"virtual-to-physical":[15],"address":[16],"translation":[17],"on":[18,265],"modern":[19],"processors.":[20],"However,":[21],"large":[23],"size":[24],"2":[27,78],"MB":[28,79],"and":[29,55,80,111,117,158,176,193,199],"1":[30],"GB":[31],"superpages":[32,65,76,82],"supported":[33],"by":[34,70,221],"x86-64":[35],"processors":[36,95],"continues":[37],"to":[38,42,47,91,132,146,224,281,285],"present":[39],"a":[40,59,67,103,232,236,286,296],"challenge":[41],"operating":[44,148,167,197,212,226,238],"system\u2019s":[45],"ability":[46],"form":[48],"superpages,":[49],"given":[50],"mandatory":[52],"contiguity,":[53],"alignment,":[54],"attribute":[56],"requirements":[57],"superpage.":[60],"Recent":[61],"work":[62],"proposes":[63],"medium-sized":[64],"potential":[68],"solution,":[69],"allowing":[71],"creation":[73],"smaller":[75],"where":[77,107],"larger":[81],"have":[83,101],"not":[84,88,252],"formed":[85],"or":[86,128,150,169],"will":[87],"be":[89,133,173],"possible":[90],"form.":[92],"Notably,":[93],"AMD":[94],"starting":[96],"with":[97,241],"Zen":[99],"microarchitecture":[100],"offered":[102],"\u201cPTE":[104],"Coalescing\u201d":[105],"feature":[106,142],"hardware":[109],"opportunistically":[110],"transparently":[112],"creates,":[113],"from":[114,278],"underlying":[115],"consecutive":[116],"aligned":[118],"4":[119,290],"KB":[120,127,130,261,280,283,291],"mappings":[121,131],"in":[122,135,289,295],"page":[124],"table,":[125],"16":[126,282],"32":[129,263,279],"cached":[134],"TLB.":[137],"On":[138],"surface,":[140],"this":[141],"requires":[143],"no":[144],"modifications":[145],"system":[149,168,198,213,227,239],"compiler":[152],"toolchain,":[153],"exploiting":[154],"only":[155],"coincidental":[156],"contiguity":[157],"alignment.":[159],"Nonetheless,":[160],"there":[161],"ways":[163],"that":[164,210,214,228,273],"either":[165],"toolchain":[171,200],"can":[172],"made":[174],"coalescing-aware":[175],"hence":[177],"make":[178],"better":[179],"use":[180],"PTE":[182,191,242,269],"Coalescing.":[183,270],"This":[184],"paper":[185],"first":[186],"investigates":[187],"undocumented":[188],"aspects":[189],"Coalescing,":[192],"then":[194],"evaluates":[195],"some":[196],"optimizations":[201],"which":[202],"explicitly":[203],"take":[204],"advantage":[205],"it.":[207],"We":[208,271],"find":[209,272],"is":[215,229],"coalescing-friendly":[216,237],"reduces":[217],"L1":[218],"ITLB":[219,248],"misses":[220,294],"50%-80%":[222],"compared":[223],"coalescing-unaware.":[230],"For":[231],"Clang":[233],"compilation":[234],"workload,":[235],"coupled":[240],"Coalescing":[243],"all":[244],"but":[245,251],"eliminates":[246],"L2":[247,292],"misses.":[249],"Last":[250],"least,":[253],"we":[254],"evaluate":[255],"impact":[257],"granularity":[259,277],"(16":[260],"vs":[262],"KB)":[264],"effectiveness":[267],"coalescing":[276],"leads":[284],"1.3x-20.5x":[287],"reduction":[288],"DTLB":[293],"wide":[297],"variety":[298],"workloads.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}