{"id":"https://openalex.org/W7148931474","doi":"https://doi.org/10.1145/3806835","title":"Thoth: Uncovering Data-Dependent Memory Access Patterns via Annotation-Directed Load Sampling","display_name":"Thoth: Uncovering Data-Dependent Memory Access Patterns via Annotation-Directed Load Sampling","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7148931474","doi":"https://doi.org/10.1145/3806835"},"language":"en","primary_location":{"id":"doi:10.1145/3806835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806835","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3806835","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123975535","display_name":"Kanheng Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kanheng Jiang","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University"],"raw_orcid":"https://orcid.org/0009-0006-8220-5238","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132856286","display_name":"Yongxin Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Lyu","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University"],"raw_orcid":"https://orcid.org/0009-0002-2997-5285","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiyuan Zhang","orcid":"https://orcid.org/0009-0007-2072-075X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Zhang","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University"],"raw_orcid":"https://orcid.org/0009-0007-2072-075X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104233809","display_name":"Zengshi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengshi Wang","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University"],"raw_orcid":"https://orcid.org/0009-0007-5575-8440","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132910334","display_name":"Chao Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Fu","raw_affiliation_strings":["Shaoxin Laboratory, Fudan University"],"raw_orcid":"https://orcid.org/0000-0001-9286-0275","affiliations":[{"raw_affiliation_string":"Shaoxin Laboratory, Fudan University","institution_ids":["https://openalex.org/I181877577","https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132863778","display_name":"Jun Han","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Han","raw_affiliation_strings":["State Key Laboratory of Integrated Chips and Systems, Fudan University"],"raw_orcid":"https://orcid.org/0000-0002-5245-0754","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Integrated Chips and Systems, Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36055755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.45320001244544983,"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"}},"topics":[{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.45320001244544983,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10930000245571136,"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":0.07919999957084656,"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/cache","display_name":"Cache","score":0.6359999775886536},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5336999893188477},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5236999988555908},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5217999815940857},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4251999855041504},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.40369999408721924},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.39809998869895935},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.383899986743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9063000082969666},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6359999775886536},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5336999893188477},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5217999815940857},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47929999232292175},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4251999855041504},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.383899986743927},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.3659000098705292},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.3174999952316284},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806835","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3806835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806835","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1973262089","https://openalex.org/W1983545421","https://openalex.org/W2000041758","https://openalex.org/W2009196736","https://openalex.org/W2013062050","https://openalex.org/W2036853599","https://openalex.org/W2046526098","https://openalex.org/W2095679548","https://openalex.org/W2115022330","https://openalex.org/W2153515302","https://openalex.org/W2165836188","https://openalex.org/W2170382128","https://openalex.org/W2234355962","https://openalex.org/W2329976284","https://openalex.org/W2416944327","https://openalex.org/W2796645376","https://openalex.org/W2941917372","https://openalex.org/W2949727479","https://openalex.org/W2979729542","https://openalex.org/W2979935562","https://openalex.org/W3013103997","https://openalex.org/W3013773906","https://openalex.org/W3043167609","https://openalex.org/W3126960560","https://openalex.org/W3136230959","https://openalex.org/W4241590855","https://openalex.org/W4244058688","https://openalex.org/W4248803982","https://openalex.org/W4249382013","https://openalex.org/W4308083752","https://openalex.org/W4389491899","https://openalex.org/W4391103886","https://openalex.org/W4391547476","https://openalex.org/W4404101738","https://openalex.org/W4411486321"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"data":[1,57],"structures":[2,17],"are":[3,100],"ubiquitous":[4],"in":[5,85],"graph":[6],"analytics,":[7],"machine":[8],"learning,":[9],"and":[10,32,58,64,109,125,185,238,246],"high-performance":[11],"computing.":[12],"Algorithms":[13],"operating":[14],"on":[15,38],"these":[16,137,141],"typically":[18],"exhibit":[19],"highly":[20],"irregular":[21],"data-dependent":[22],"memory":[23,34],"access":[24],"(DDMA)":[25],"patterns,":[26],"leading":[27],"to":[28,41,217],"frequent":[29],"cache":[30,61],"misses":[31,44,96],"degraded":[33],"performance.":[35],"Prior":[36],"work":[37],"hardware":[39,147],"prefetching":[40,90],"mitigate":[42],"DDMA-induced":[43],"falls":[45],"into":[46],"two":[47,240],"categories:":[48],"address-based":[49,94],"methods":[50,66],"that":[51,67,149,179],"sample":[52],"correlated":[53],"sequences":[54],"of":[55,132,154,226],"load":[56,118,157,176,183,211],"addresses":[59],"from":[60,97],"miss":[62],"streams,":[63],"instruction-based":[65,121],"record":[68],"instruction-level":[69],"dependency":[70,134,162,170],"chains.":[71,163],"Although":[72],"both":[73],"learn":[74],"single":[75],"relations":[76,83,112],"effectively,":[77],"they":[78],"struggle":[79],"with":[80,103],"multi-level":[81,196],"range":[82,111,197],"prevalent":[84],"DDMA-intensive":[86,227],"workloads,":[87],"leaving":[88],"substantial":[89],"opportunities":[91],"unexploited.":[92],"In":[93,120],"schemes,":[95,122],"deeper-level":[98],"consumers":[99],"often":[101],"miscorrelated":[102],"the":[104,110,130,152],"producer.":[105],"Moreover,":[106],"out-of-order":[107],"execution":[108],"themselves":[113],"perturb":[114],"sampling,":[115],"yielding":[116],"mismatched":[117],"instances.":[119],"chain-structured":[123],"representations":[124],"suboptimal":[126],"learning":[127],"strategies":[128],"prevent":[129],"construction":[131],"complete":[133],"chains":[135],"for":[136],"relations.":[138],"To":[139,201],"overcome":[140],"limitations,":[142],"we":[143],"present":[144],"Thoth,":[145],"a":[146,224,231,235],"prefetcher":[148],"operates":[150],"at":[151],"granularity":[153],"explicit":[155],"producer-consumer":[156,182],"pairs":[158,167],"rather":[159],"than":[160],"constructing":[161],"Thoth":[164,208,229],"detects":[165],"such":[166],"via":[168],"register-level":[169],"tracking.":[171],"It":[172],"adopts":[173],"an":[174],"annotation-directed":[175],"sampling":[177],"strategy":[178],"annotates":[180],"matched":[181],"instances":[184],"samples":[186],"only":[187],"those":[188],"annotated":[189],"instances,":[190],"thereby":[191],"robustly":[192],"uncovering":[193],"DDMA":[194,242],"patterns\u2014including":[195],"relations\u2014while":[198],"avoiding":[199],"mismatches.":[200],"maintain":[202],"annotation":[203,221],"correctness":[204],"across":[205],"pipeline":[206],"flushes,":[207],"employs":[209],"precise":[210],"annotation,":[212],"which":[213],"leverages":[214],"reorder":[215],"identifiers":[216],"resume":[218],"or":[219],"terminate":[220],"precisely.":[222],"On":[223],"suite":[225],"benchmarks,":[228],"delivers":[230],"51.1%":[232],"speedup":[233],"over":[234],"no-prefetching":[236],"baseline":[237],"outperforms":[239],"state-of-the-art":[241],"prefetchers":[243],"by":[244],"14.7%":[245],"8.2%,":[247],"respectively.":[248]},"counts_by_year":[],"updated_date":"2026-06-26T06:17:10.115597","created_date":"2026-04-04T00:00:00"}