{"id":"https://openalex.org/W3207117390","doi":"https://doi.org/10.1145/3466752.3480104","title":"Fat Loads: Exploiting Locality Amongst Contemporaneous Load Operations to Optimize Cache Accesses","display_name":"Fat Loads: Exploiting Locality Amongst Contemporaneous Load Operations to Optimize Cache Accesses","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3207117390","doi":"https://doi.org/10.1145/3466752.3480104","mag":"3207117390"},"language":"en","primary_location":{"id":"doi:10.1145/3466752.3480104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM 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/A5013518097","display_name":"Vanshika Baoni","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vanshika Baoni","raw_affiliation_strings":["University of Wisconsin-Madison, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051056318","display_name":"Adarsh Mittal","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adarsh Mittal","raw_affiliation_strings":["University of Wisconsin-Madison, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108260478","display_name":"Gurindar S. Sohi","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gurindar S. Sohi","raw_affiliation_strings":["University of Wisconsin-Madison, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, United States of America","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013518097"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.6908,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67686967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"379"},"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8242433071136475},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7843982577323914},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6507202386856079},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.638008177280426},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6006221771240234},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5641700029373169},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5633497834205627},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.5478371381759644},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.5173206329345703},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.4458746910095215},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4342588782310486},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27902352809906006},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0811612606048584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242433071136475},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7843982577323914},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6507202386856079},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.638008177280426},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6006221771240234},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5641700029373169},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5633497834205627},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.5478371381759644},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.5173206329345703},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.4458746910095215},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4342588782310486},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27902352809906006},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0811612606048584},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3466752.3480104","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3466752.3480104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9100000262260437,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1579293304","https://openalex.org/W1857802258","https://openalex.org/W1970454100","https://openalex.org/W1974232202","https://openalex.org/W1993467135","https://openalex.org/W2000544790","https://openalex.org/W2007395720","https://openalex.org/W2036853599","https://openalex.org/W2050203255","https://openalex.org/W2072730350","https://openalex.org/W2077172685","https://openalex.org/W2078040714","https://openalex.org/W2098005539","https://openalex.org/W2102388010","https://openalex.org/W2111740117","https://openalex.org/W2119786518","https://openalex.org/W2121539621","https://openalex.org/W2129454457","https://openalex.org/W2130124967","https://openalex.org/W2130558352","https://openalex.org/W2135885084","https://openalex.org/W2147520174","https://openalex.org/W2147657366","https://openalex.org/W2148177330","https://openalex.org/W2152922910","https://openalex.org/W2153099552","https://openalex.org/W2167540744","https://openalex.org/W2215868337","https://openalex.org/W2464177207","https://openalex.org/W2612889458","https://openalex.org/W2767584030","https://openalex.org/W2885022288","https://openalex.org/W2891529120","https://openalex.org/W2951701122","https://openalex.org/W3086320248","https://openalex.org/W3137284226","https://openalex.org/W4231070018","https://openalex.org/W4238346090","https://openalex.org/W4248046587","https://openalex.org/W4249342118"],"related_works":["https://openalex.org/W2363769136","https://openalex.org/W3085471909","https://openalex.org/W2031173804","https://openalex.org/W2098406302","https://openalex.org/W2734782074","https://openalex.org/W2369103246","https://openalex.org/W2133489088","https://openalex.org/W2114386333","https://openalex.org/W2020176098","https://openalex.org/W4312759433"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"locality":[3],"among":[4],"load":[5,49],"instructions":[6],"that":[7,85],"are":[8],"in":[9,60,114,124,137,148],"processing":[10],"contemporaneously":[11],"within":[12],"a":[13,40,46,51,54,134,146],"processor":[14],"to":[15,21,30,39],"optimize":[16],"the":[17,22,34,79,102,119,127,149],"number":[18,35,103,150],"of":[19,36,42,104,141,151],"accesses":[20,38,107],"memory":[23,43],"hierarchy.":[24],"A":[25],"simple":[26],"technique":[27],"is":[28],"used":[29],"learn":[31],"and":[32,44,145],"predict":[33],"contemporaneous":[37,72],"region":[41],"classify":[45],"particular":[47],"dynamic":[48],"into":[50,63],"normal":[52],"or":[53,92,99],"fat":[55,87],"load.":[56],"Fat":[57],"loads":[58,73,131],"bring":[59],"additional":[61],"data":[62],"Contemporaneous":[64],"Load":[65],"Access":[66],"Registers":[67],"(CLARs),":[68],"from":[69,133],"where":[70],"other":[71],"could":[74,108],"be":[75,109],"serviced":[76,132],"without":[77],"accessing":[78],"L1":[80,105,120],"cache.":[81],"Experimental":[82],"results":[83,136],"indicate":[84],"with":[86,90],"loads,":[88],"along":[89],"4":[91],"8":[93],"cache":[94,106,121],"line":[95],"size":[96],"CLARs":[97],"(256":[98],"512":[100],"bytes),":[101],"reduced":[110,128],"by":[111],"50-60%,":[112],"resulting":[113],"significant":[115],"energy":[116],"savings":[117],"for":[118,130],"operations.":[122],"Further,":[123],"several":[125],"cases":[126],"latency":[129],"CLAR":[135],"an":[138],"earlier":[139],"resolution":[140],"some":[142],"mispredicted":[143],"branches,":[144],"reduction":[147],"wrong-path":[152],"instructions,":[153],"especially":[154],"loads.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
