{"id":"https://openalex.org/W7126242922","doi":"https://doi.org/10.1145/3767110.3767128","title":"Compile Time Prediction of Cache Reuse for Array Applications with Multiple Loop Nests","display_name":"Compile Time Prediction of Cache Reuse for Array Applications with Multiple Loop Nests","publication_year":2025,"publication_date":"2025-10-06","ids":{"openalex":"https://openalex.org/W7126242922","doi":"https://doi.org/10.1145/3767110.3767128"},"language":null,"primary_location":{"id":"doi:10.1145/3767110.3767128","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767110.3767128","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Symposium on Memory Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3767110.3767128","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055033165","display_name":"Abdur Razzak","orcid":"https://orcid.org/0009-0008-7577-5608"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdur Razzak","raw_affiliation_strings":["Computer Science, New Mexico State University, Las Cruces, NM, USA"],"raw_orcid":"https://orcid.org/0009-0008-7577-5608","affiliations":[{"raw_affiliation_string":"Computer Science, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Atanu Barai","orcid":"https://orcid.org/0000-0002-6879-4455"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanu Barai","raw_affiliation_strings":["CCS3, Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":"https://orcid.org/0000-0002-6879-4455","affiliations":[{"raw_affiliation_string":"CCS3, Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nandakishore Santhi","orcid":"https://orcid.org/0000-0002-4755-7821"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nandakishore Santhi","raw_affiliation_strings":["Information Sciences Group (CCS3), Los Alamos National Laboratory, Los Alamos, NM, USA"],"raw_orcid":"https://orcid.org/0000-0002-4755-7821","affiliations":[{"raw_affiliation_string":"Information Sciences Group (CCS3), Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087778749","display_name":"Abdel\u2010Hameed A. Badawy","orcid":"https://orcid.org/0000-0001-8027-1449"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdel-Hameed Badawy","raw_affiliation_strings":["Klipsch School of ECE, New Mexico State University, Las Cruces, NM, USA"],"raw_orcid":"https://orcid.org/0000-0001-8027-1449","affiliations":[{"raw_affiliation_string":"Klipsch School of ECE, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055033165"],"corresponding_institution_ids":["https://openalex.org/I10052268"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73264781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9368000030517578,"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":0.9368000030517578,"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/T12127","display_name":"Software System Performance and Reliability","score":0.015799999237060547,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0071000000461936,"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/reuse","display_name":"Reuse","score":0.6863999962806702},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6468999981880188},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.5767999887466431},{"id":"https://openalex.org/keywords/access-time","display_name":"Access time","score":0.5156999826431274},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5063999891281128},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.42890000343322754},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.41940000653266907},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.39629998803138733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413000106811523},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6863999962806702},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6468999981880188},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6134999990463257},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C194080101","wikidata":"https://www.wikidata.org/wiki/Q46306","display_name":"Access time","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5063999891281128},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.42890000343322754},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.35190001130104065},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.2994999885559082},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2892000079154968},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.2632000148296356},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3767110.3767128","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767110.3767128","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3767110.3767128","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3767110.3767128","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Symposium on Memory Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2018052702","https://openalex.org/W2091250014","https://openalex.org/W2169828639","https://openalex.org/W3129352166","https://openalex.org/W4200525217","https://openalex.org/W4383749541","https://openalex.org/W4394586828","https://openalex.org/W4405348622"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"memory":[1,48,57,63,116],"access":[2,64,117,129,174,187],"patterns":[3,130,175,188],"play":[4],"a":[5,31,88,141,147,208,225,260],"crucial":[6],"role":[7],"in":[8,91,160,176,251],"determining":[9],"the":[10,40,46,84,110,114,128,154,274],"overall":[11],"performance":[12,282],"of":[13,131,157,167],"applications":[14,269],"by":[15,206,214],"exploiting":[16],"temporal":[17,37],"and":[18,56,73,94,180,189,193,211,280],"spatial":[19],"locality,":[20,38],"thus":[21],"maximizing":[22],"cache":[23,95,194],"locality.":[24],"The":[25,237],"Reuse":[26,233],"Distance":[27,234],"Histogram":[28],"(RDH)":[29],"is":[30,69],"widely":[32,226],"used":[33,123],"metric":[34],"to":[35,45,60,263],"quantify":[36],"measuring":[39],"distance":[41],"between":[42],"consecutive":[43],"accesses":[44],"same":[47],"location.":[49],"Traditionally,":[50],"calculating":[51],"RDH":[52,93],"requires":[53],"program":[54,111],"execution":[55,138],"trace":[58,67],"collection":[59,68],"obtain":[61],"dynamic":[62,264],"behavior.":[65],"This":[66,144,200,257],"often":[70,101],"time-consuming,":[71],"resource-intensive,":[72],"unsuitable":[74],"for":[75,152,267,276],"early-stage":[76],"optimization":[77],"or":[78,112],"large-scale":[79],"applications.":[80],"Static":[81],"prediction,":[82],"on":[83],"other":[85],"hand,":[86],"offers":[87],"significant":[89,142],"speedup":[90],"estimating":[92],"hit":[96,195],"rates.":[97],"However,":[98],"these":[99],"approaches":[100],"lack":[102],"accuracy,":[103],"as":[104],"predictions":[105],"are":[106,122],"made":[107],"without":[108,134],"executing":[109],"observing":[113,135],"complete":[115],"pattern.":[118],"Specifically,":[119],"when":[120],"arrays":[121],"inside":[124],"nested":[125,163],"loops,":[126,272],"predicting":[127,153],"array":[132,158,186,268],"references":[133,159],"their":[136],"exact":[137],"sequence":[139],"presents":[140,146,259],"challenge.":[143],"paper":[145,201],"novel":[148],"static":[149,242,281],"analysis":[150,210,252],"framework":[151],"reuse":[155,191,218,265],"profiles":[156],"programs":[161],"with":[162,270],"loop":[164,172],"structures,":[165],"independent":[166],"runtime":[168],"information.":[169],"By":[170],"analyzing":[171],"bounds,":[173],"smaller":[177],"problem":[178],"sizes,":[179],"predictive":[181],"equations,":[182],"our":[183,203,222,241],"method":[184],"predicts":[185],"estimates":[190],"distances":[192],"rates":[196],"at":[197],"compile":[198],"time.":[199,256],"extends":[202],"previous":[204],"study":[205],"incorporating":[207],"deeper":[209],"improving":[212],"prediction":[213],"addressing":[215],"previously":[216],"unhandled":[217],"patterns.":[219],"We":[220],"evaluated":[221],"technique":[223],"against":[224],"accepted":[227],"traditional":[228],"trace-driven":[229],"profiling":[230,266],"tool,":[231],"Parallel":[232],"Analysis":[235],"(PARDA).":[236],"results":[238],"demonstrate":[239],"that":[240],"predictor":[243],"achieves":[244],"comparable":[245],"accuracy":[246],"while":[247],"offering":[248],"orders-of-magnitude":[249],"improvement":[250],"speed,":[253],"excluding":[254],"setup":[255],"work":[258],"practical":[261],"alternative":[262],"multiple":[271],"paving":[273],"way":[275],"integration":[277],"into":[278],"compilers":[279],"modeling":[283],"tools.":[284]},"counts_by_year":[],"updated_date":"2026-02-01T03:38:14.988550","created_date":"2026-02-01T00:00:00"}