{"id":"https://openalex.org/W7162684207","doi":"https://doi.org/10.1145/3818683","title":"Apollo: Accelerating Load Requests via Multi-Level Cache Miss Load Prediction","display_name":"Apollo: Accelerating Load Requests via Multi-Level Cache Miss Load Prediction","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162684207","doi":"https://doi.org/10.1145/3818683"},"language":"en","primary_location":{"id":"doi:10.1145/3818683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3818683","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":null,"license_id":null,"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/10.1145/3818683","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101530836","display_name":"Zhengwei Huang","orcid":"https://orcid.org/0000-0002-6844-9803"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengwei Huang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0002-9914-1254","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704814","display_name":"Wei Guo","orcid":"https://orcid.org/0000-0001-7293-8581"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0002-6704-0966","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongwen Wang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0008-2514-2052","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6672595,"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":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8295000195503235,"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":0.8295000195503235,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.055799998342990875,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.03269999846816063,"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":0.6976000070571899},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5964999794960022},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5099999904632568},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.3776000142097473},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.35120001435279846},{"id":"https://openalex.org/keywords/bus-sniffing","display_name":"Bus sniffing","score":0.33629998564720154},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.3264999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9046000242233276},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6976000070571899},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5099999904632568},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.353300005197525},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34040001034736633},{"id":"https://openalex.org/C51185590","wikidata":"https://www.wikidata.org/wiki/Q1017228","display_name":"Bus sniffing","level":5,"score":0.33629998564720154},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.3264999985694885},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.3167000114917755},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C2779971761","wikidata":"https://www.wikidata.org/wiki/Q629872","display_name":"Arbiter","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C160151201","wikidata":"https://www.wikidata.org/wiki/Q207946","display_name":"Arbitration","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C2777549182","wikidata":"https://www.wikidata.org/wiki/Q15117556","display_name":"Abort","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.2623000144958496},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3818683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3818683","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":null,"license_id":null,"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:10.1145/3818683","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3818683","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":null,"license_id":null,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2025106479","https://openalex.org/W2052647915","https://openalex.org/W2165358233","https://openalex.org/W3124943311"],"related_works":[],"abstract_inverted_index":{"Accelerating":[0],"load":[1,13,28,39,44,97,116,132,157,172,185,202,216,227,234,247,267],"requests":[2,29,40,248],"is":[3,90,125,168,314],"an":[4,238],"effective":[5],"way":[6],"to":[7,25,109,112,119,134,147,159,187,261],"improve":[8],"processor":[9],"performance":[10,285,309],"through":[11],"reducing":[12],"request":[14,98,117,124,133,158,173,186],"latency.":[15],"Currently,":[16],"state-of-the-art":[17],"methods,":[18],"including":[19],"Hermes":[20,294,318],"and":[21,34,41,105,118,127,180,204,207,237,243,254,297,319],"TLP,":[22],"are":[23,31],"limited":[24],"accelerating":[26],"off-chip":[27,38,72],"that":[30,57,278],"correctly":[32,198,212],"predicted":[33,146,199,213],"cannot":[35],"accelerate":[36],"mispredicted":[37],"any":[42],"on-chip":[43],"requests.":[45,217,268],"To":[46,218],"overcome":[47],"this":[48],"limitation,":[49],"we":[50,221],"propose":[51,222],"a":[52,79,96,114,130,223,230,272,281,307],"new":[53],"technique":[54],"called":[55,240],"Apollo":[56,64,89,190,279,305],"integrates":[58],"TLP.":[59,323],"The":[60,86],"key":[61],"innovation":[62],"of":[63,69,88,265,275,287,311],"lies":[65],"in":[66,251],"its":[67],"transformation":[68],"the":[70,101,123,135,149,155,162,166,170,176,183,193,252,263,290,302],"perceptron-based":[71],"prediction":[73,84,167],"paradigm,":[74],"pioneered":[75],"by":[76,295,299],"Hermes,":[77],"into":[78],"comprehensive":[80],"multi-level":[81],"cache":[82,121,137,163],"miss":[83,100,148,201,215,226,233,250],"technique.":[85],"workflow":[87],"as":[91],"follows:":[92],"(1)":[93],"predicting":[94],"whether":[95,111,246],"will":[99,249],"L1D":[102,150,177,194,200,206,225,253],"or":[103,140,151,178],"L2,":[104,152,255],"(2)":[106],"performing":[107],"arbitration":[108,143,260],"decide":[110],"issue":[113],"speculative":[115,131,184,266],"which":[120,313],"level":[122],"issued,":[126],"(3)":[128],"issuing":[129],"lower-level":[136],"(either":[138],"L2":[139,179,208,214,232],"LLC)":[141],"after":[142],"for":[144,182,197,211,289],"those":[145],"while":[153,257],"allowing":[154],"regular":[156,171],"concurrently":[160],"access":[161,195,209],"hierarchy.":[164],"If":[165],"correct,":[169],"eventually":[174],"misses":[175],"waits":[181],"finish.":[188],"Therefore,":[189],"can":[191],"hide":[192],"latency":[196,210],"requests,":[203],"both":[205],"enable":[219],"Apollo,":[220],"lightweight":[224,231],"predictor":[228,235],"(L1MP),":[229],"(L2MP),":[236],"arbiter":[239],"Athena.":[241],"L1MP":[242],"L2MP":[244],"predict":[245],"respectively,":[256],"Athena":[258],"performs":[259],"control":[262],"issuance":[264],"Our":[269],"evaluation":[270],"using":[271],"diverse":[273],"set":[274],"workloads":[276],"shows":[277],"provides":[280,306],"geometric":[282],"mean":[283],"(geomean)":[284],"improvement":[286,310],"15.2%":[288],"single-core":[291],"processor,":[292,304],"outperforming":[293],"9.6%":[296],"TLP":[298],"6.4%.":[300],"For":[301],"multi-core":[303],"geomean":[308],"18.5%,":[312],"16.8%":[315],"higher":[316,321],"than":[317,322],"5.8%":[320]},"counts_by_year":[],"updated_date":"2026-06-26T06:17:10.115597","created_date":"2026-05-29T00:00:00"}
