{"id":"https://openalex.org/W3089469538","doi":"https://doi.org/10.1145/3410463.3414623","title":"Analyzing and Leveraging Shared L1 Caches in GPUs","display_name":"Analyzing and Leveraging Shared L1 Caches in GPUs","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3089469538","doi":"https://doi.org/10.1145/3410463.3414623","mag":"3089469538"},"language":"en","primary_location":{"id":"doi:10.1145/3410463.3414623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","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/A5066580088","display_name":"Mohamed Assem Ibrahim","orcid":"https://orcid.org/0000-0002-4129-0310"},"institutions":[{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]},{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohamed Assem Ibrahim","raw_affiliation_strings":["William &amp; Mary, Williamsburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"William &amp; Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064126781","display_name":"Onur Kay\u0131ran","orcid":"https://orcid.org/0009-0006-4482-3115"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Onur Kayiran","raw_affiliation_strings":["Advanced Micro Devices, Inc., Fairport, NY, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Fairport, NY, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087189119","display_name":"Yasuko Eckert","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yasuko Eckert","raw_affiliation_strings":["Advanced Micro Devices, Inc., Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102835155","display_name":"Gabriel H. Loh","orcid":"https://orcid.org/0000-0002-4616-0144"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabriel H. Loh","raw_affiliation_strings":["Advanced Micro Devices, Inc., Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050350124","display_name":"Adwait Jog","orcid":"https://orcid.org/0000-0002-5525-7204"},"institutions":[{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]},{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adwait Jog","raw_affiliation_strings":["William &amp; Mary, Williamsburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"William &amp; Mary, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066580088"],"corresponding_institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"],"apc_list":null,"apc_paid":null,"fwci":1.8711,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85866477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"173"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"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":0.9970999956130981,"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":0.8683605194091797},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.8010063767433167},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7689415216445923},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.6093078255653381},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.5728858709335327},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5600146055221558},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5565866827964783},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5543535947799683},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.5041753053665161},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.5019090175628662},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4905818998813629},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.48009708523750305},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.43203461170196533},{"id":"https://openalex.org/keywords/bus-sniffing","display_name":"Bus sniffing","score":0.4163365662097931},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32978641986846924},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3291887044906616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8683605194091797},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8010063767433167},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7689415216445923},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.6093078255653381},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.5728858709335327},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5600146055221558},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5565866827964783},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5543535947799683},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.5041753053665161},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.5019090175628662},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4905818998813629},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.48009708523750305},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.43203461170196533},{"id":"https://openalex.org/C51185590","wikidata":"https://www.wikidata.org/wiki/Q1017228","display_name":"Bus sniffing","level":5,"score":0.4163365662097931},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32978641986846924},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3291887044906616},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3410463.3414623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1968775993","https://openalex.org/W1983096721","https://openalex.org/W1984993578","https://openalex.org/W1989061323","https://openalex.org/W1997352364","https://openalex.org/W2018337509","https://openalex.org/W2029969950","https://openalex.org/W2043135347","https://openalex.org/W2064373756","https://openalex.org/W2079184143","https://openalex.org/W2093043622","https://openalex.org/W2103633747","https://openalex.org/W2105102111","https://openalex.org/W2130820665","https://openalex.org/W2140354616","https://openalex.org/W2151233837","https://openalex.org/W2161364792","https://openalex.org/W2161511909","https://openalex.org/W2164988937","https://openalex.org/W2171164959","https://openalex.org/W2441593292","https://openalex.org/W2521924282","https://openalex.org/W2605251767","https://openalex.org/W2625200202","https://openalex.org/W2626312854","https://openalex.org/W2730499906","https://openalex.org/W2765227358","https://openalex.org/W2795081729","https://openalex.org/W2795326697","https://openalex.org/W2903932107","https://openalex.org/W2904107204","https://openalex.org/W2937249639","https://openalex.org/W2952269378","https://openalex.org/W2984139344","https://openalex.org/W3125984961","https://openalex.org/W4248800093","https://openalex.org/W4255387252","https://openalex.org/W4292169167"],"related_works":["https://openalex.org/W2161101294","https://openalex.org/W2026179701","https://openalex.org/W2148571123","https://openalex.org/W4312759433","https://openalex.org/W2108638805","https://openalex.org/W4380881125","https://openalex.org/W2152423944","https://openalex.org/W2184371594","https://openalex.org/W273173017","https://openalex.org/W2113875634"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"concurrently":[4],"execute":[5],"thousands":[6],"of":[7,21,62,100,106,112],"threads,":[8],"which":[9,50],"makes":[10],"them":[11],"effective":[12],"for":[13,17,56],"achieving":[14],"high":[15],"throughput":[16,55],"a":[18,67,76],"wide":[19],"range":[20],"applications.":[22,58],"However,":[23,59],"the":[24,63,85,103,113],"memory":[25],"wall":[26],"often":[27],"limits":[28],"peak":[29],"throughput.":[30],"GPUs":[31],"use":[32],"caches":[33,101,108],"to":[34,117],"address":[35],"this":[36,92],"limitation,":[37],"and":[38,81],"hence":[39],"several":[40],"prior":[41,64],"works":[42,65],"have":[43],"focused":[44],"on":[45],"improving":[46],"cache":[47,69,80,115],"hit":[48],"rates,":[49],"in":[51],"turn":[52],"can":[53],"improve":[54],"memory-intensive":[57],"almost":[60],"all":[61,82],"assume":[66],"conventional":[68],"hierarchy":[70],"where":[71],"each":[72],"GPU":[73],"core":[74],"has":[75],"private":[77,104],"local":[78],"L1":[79,107],"cores":[83],"share":[84],"L2":[86],"cache.":[87],"Our":[88],"analysis":[89],"shows":[90],"that":[91],"canonical":[93],"organization":[94],"does":[95],"not":[96],"allow":[97],"optimal":[98],"utilization":[99],"because":[102],"nature":[105],"allows":[109],"multiple":[110],"copies":[111],"same":[114],"line":[116],"get":[118],"replicated":[119],"across":[120],"cores.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
