{"id":"https://openalex.org/W4395959100","doi":"https://doi.org/10.1145/3649411.3649415","title":"Cache Cohort GPU Scheduling","display_name":"Cache Cohort GPU Scheduling","publication_year":2024,"publication_date":"2024-03-02","ids":{"openalex":"https://openalex.org/W4395959100","doi":"https://doi.org/10.1145/3649411.3649415"},"language":"en","primary_location":{"id":"doi:10.1145/3649411.3649415","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649411.3649415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"16th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"type":"conference-paper","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/A5057211298","display_name":"Vinay Ramakrishnaiah","orcid":"https://orcid.org/0000-0002-2925-4798"},"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":"Vinay Ramakrishnaiah","raw_affiliation_strings":["Research and Advanced Development, Advanced Micro Devices, United States"],"raw_orcid":"https://orcid.org/0000-0002-2925-4798","affiliations":[{"raw_affiliation_string":"Research and Advanced Development, Advanced Micro Devices, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077056823","display_name":"Bradford M. Beckmann","orcid":"https://orcid.org/0000-0002-5444-6521"},"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":"Bradford Beckmann","raw_affiliation_strings":["Research and Advanced Development, Advanced Micro Devices, United States"],"raw_orcid":"https://orcid.org/0000-0002-5444-6521","affiliations":[{"raw_affiliation_string":"Research and Advanced Development, Advanced Micro Devices, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029473578","display_name":"Pete Ehrett","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":"Pete Ehrett","raw_affiliation_strings":["Research and Advanced Development, Advanced Micro Devices, United States"],"raw_orcid":"https://orcid.org/0000-0002-4587-3716","affiliations":[{"raw_affiliation_string":"Research and Advanced Development, Advanced Micro Devices, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000419856","display_name":"Ren\u00e9 van Oostrum","orcid":"https://orcid.org/0009-0006-5734-4201"},"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":"Rene Van Oostrum","raw_affiliation_strings":["Research and Advanced Development, Advanced Micro Devices, United States"],"raw_orcid":"https://orcid.org/0009-0006-5734-4201","affiliations":[{"raw_affiliation_string":"Research and Advanced Development, Advanced Micro Devices, United States","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5095923335","display_name":"Keith Lowery","orcid":"https://orcid.org/0009-0001-0915-7309"},"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":"Keith Lowery","raw_affiliation_strings":["Research and Advanced Development, Advanced Micro Devices, United States"],"raw_orcid":"https://orcid.org/0009-0001-0915-7309","affiliations":[{"raw_affiliation_string":"Research and Advanced Development, Advanced Micro Devices, United States","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210137977"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9882000088691711,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9592000246047974,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7843866348266602},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6919615864753723},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6138371229171753},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4589342772960663},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05676063895225525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843866348266602},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6919615864753723},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6138371229171753},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4589342772960663},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05676063895225525},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649411.3649415","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649411.3649415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"16th Workshop on General Purpose Processing Using GPU","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":25,"referenced_works":["https://openalex.org/W1963958818","https://openalex.org/W2000215628","https://openalex.org/W2022915229","https://openalex.org/W2024165284","https://openalex.org/W2322798958","https://openalex.org/W2582365613","https://openalex.org/W2750586907","https://openalex.org/W2765368488","https://openalex.org/W2766476454","https://openalex.org/W2768445292","https://openalex.org/W2788386530","https://openalex.org/W2885801207","https://openalex.org/W2886162485","https://openalex.org/W3006050796","https://openalex.org/W3057934400","https://openalex.org/W3102869303","https://openalex.org/W3114643644","https://openalex.org/W3170643994","https://openalex.org/W3174786754","https://openalex.org/W3186368531","https://openalex.org/W4236134234","https://openalex.org/W4289533782","https://openalex.org/W4310007390","https://openalex.org/W4379743391","https://openalex.org/W4385585396"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"With":[0],"the":[1,18,58,64,88,98,112,119,122,128,138,143,148,159,177],"ever-improving":[2],"computation":[3],"capability":[4],"of":[5,66,90,94,121,127],"GPUs,":[6],"there":[7,132],"is":[8,30,51,133],"an":[9],"increasing":[10],"demand":[11],"for":[12],"higher":[13],"memory":[14,28],"bandwidth":[15,29],"to":[16,25,52,117,157,170],"supply":[17],"GPU":[19,38,113,145],"cores":[20],"with":[21,31],"data.":[22],"One":[23],"way":[24],"improve":[26],"effective":[27],"larger":[32],"caches,":[33],"and":[34,56,102,124,152],"we":[35,86,141],"have":[36],"seen":[37],"vendors":[39],"recently":[40],"invest":[41],"in":[42,173],"very":[43],"large":[44],"last-level":[45],"caches":[46],"(LLCs).":[47],"The":[48],"key":[49],"challenge":[50],"maximize":[53],"cache":[54,80,91,178],"utilization":[55],"keep":[57],"active":[59],"working":[60,100],"set":[61,101],"on-chip":[62],"during":[63],"lifetime":[65],"a":[67],"kernel.":[68],"Software":[69],"tiling":[70],"optimizations":[71],"can":[72,104],"help,":[73],"but":[74],"programmers":[75],"alone":[76],"cannot":[77],"anticipate":[78],"dynamic":[79],"capacity":[81],"contention.":[82],"To":[83,136],"this":[84],"end,":[85],"introduce":[87],"concept":[89],"cohorts:":[92],"groups":[93],"kernels":[95],"that":[96],"share":[97],"same":[99],"thus":[103],"be":[105],"efficiently":[106],"scheduled":[107],"together.":[108],"Our":[109,165],"approach":[110],"uses":[111],"command":[114],"processor":[115],"(CP)":[116],"track":[118],"occupancy":[120],"LLC":[123],"throttles":[125],"scheduling":[126,160,180],"next":[129],"cohort":[130],"if":[131],"no":[134],"room.":[135],"evaluate":[137],"design":[139],"space,":[140],"modify":[142],"existing":[144],"firmware":[146],"on":[147,182],"AMD":[149],"RX":[150,153,183],"7600":[151],"7900":[154,184],"XTX":[155],"GPUs":[156],"prototype":[158],"scheme":[161],"using":[162,176],"real":[163],"hardware.":[164],"preliminary":[166],"results":[167],"show":[168],"up":[169],"27%":[171],"reduction":[172],"execution":[174],"time":[175],"optimized":[179],"technique":[181],"XTX.":[185]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
