{"id":"https://openalex.org/W4386763881","doi":"https://doi.org/10.1109/dac56929.2023.10247943","title":"Orchestrated Scheduling and Partitioning for Improved Address Translation in GPUs","display_name":"Orchestrated Scheduling and Partitioning for Improved Address Translation in GPUs","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4386763881","doi":"https://doi.org/10.1109/dac56929.2023.10247943"},"language":"en","primary_location":{"id":"doi:10.1109/dac56929.2023.10247943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","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/A5102707987","display_name":"Bingyao Li","orcid":"https://orcid.org/0000-0002-6281-6799"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingyao Li","raw_affiliation_strings":["University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","Department of Computer Science, University of Pittsburgh, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102748318","display_name":"Yueqi Wang","orcid":"https://orcid.org/0009-0009-4540-2146"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yueqi Wang","raw_affiliation_strings":["University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","Department of Computer Science, University of Pittsburgh, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087859795","display_name":"Xulong Tang","orcid":"https://orcid.org/0000-0002-3385-2053"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xulong Tang","raw_affiliation_strings":["University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","Department of Computer Science, University of Pittsburgh, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Department of Computer Science,Pittsburgh,USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":1.4615,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86546463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9998000264167786,"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":0.9990000128746033,"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":0.8770332336425781},{"id":"https://openalex.org/keywords/translation-lookaside-buffer","display_name":"Translation lookaside buffer","score":0.7991369366645813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6665569543838501},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5278891324996948},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.45299622416496277},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.4515482783317566},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4459552764892578},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33349496126174927},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3227490186691284},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.2548425793647766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8770332336425781},{"id":"https://openalex.org/C116007543","wikidata":"https://www.wikidata.org/wiki/Q1071403","display_name":"Translation lookaside buffer","level":4,"score":0.7991369366645813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6665569543838501},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5278891324996948},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.45299622416496277},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.4515482783317566},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4459552764892578},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33349496126174927},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3227490186691284},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.2548425793647766},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac56929.2023.10247943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","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":24,"referenced_works":["https://openalex.org/W2004807638","https://openalex.org/W2020733012","https://openalex.org/W2021211271","https://openalex.org/W2047390994","https://openalex.org/W2048441570","https://openalex.org/W2062430565","https://openalex.org/W2080592089","https://openalex.org/W2106562406","https://openalex.org/W2128120785","https://openalex.org/W2146241244","https://openalex.org/W2238595726","https://openalex.org/W2626757163","https://openalex.org/W2764065518","https://openalex.org/W2792929085","https://openalex.org/W2793599434","https://openalex.org/W2884735227","https://openalex.org/W2905658624","https://openalex.org/W2953357877","https://openalex.org/W3089681336","https://openalex.org/W3090784541","https://openalex.org/W3137551601","https://openalex.org/W3205535571","https://openalex.org/W4239171680","https://openalex.org/W6753477299"],"related_works":["https://openalex.org/W2170268965","https://openalex.org/W2157802602","https://openalex.org/W1549901675","https://openalex.org/W1579918296","https://openalex.org/W3033052750","https://openalex.org/W2133693067","https://openalex.org/W2097165944","https://openalex.org/W2127306778","https://openalex.org/W1764185321","https://openalex.org/W199247992"],"abstract_inverted_index":{"Unified":[0],"Virtual":[1],"Memory":[2],"(UVM)":[3],"is":[4,52],"a":[5,76,124,159],"promising":[6],"feature":[7],"in":[8],"CPU-GPU":[9],"heterogeneous":[10],"systems":[11],"that":[12,95,142],"allows":[13],"data":[14,29],"structures":[15],"to":[16,134],"be":[17],"accessed":[18],"by":[19],"both":[20],"CPU":[21],"and":[22,59,83,128,152],"GPUs":[23],"through":[24],"unified":[25],"pointers":[26],"without":[27],"explicit":[28],"copying.":[30],"However,":[31],"the":[32,40,56,62,85,89,106,109,114,137,147],"delivered":[33],"performance":[34],"of":[35,42,55,79],"UVM":[36],"significantly":[37,112],"relies":[38],"on":[39,157],"efficiency":[41],"address":[43],"translation.":[44],"The":[45],"current":[46],"GPU":[47,81,130],"thread":[48,90],"block":[49],"(TB)":[50],"management":[51],"not":[53],"aware":[54],"translation":[57,86,99,116],"process":[58],"heavily":[60],"thrashes":[61],"per-streaming":[63],"multiprocessor":[64],"(SM)":[65],"private":[66],"Translation":[67],"Look-ahead":[68],"Buffers":[69],"(TLBs).":[70],"In":[71],"this":[72,120,153],"paper,":[73],"we":[74,122],"conduct":[75],"comprehensive":[77],"characterization":[78],"10":[80],"benchmarks":[82],"quantify":[84],"reuses":[87],"among":[88],"blocks.":[91],"Our":[92],"observation":[93],"reveals":[94],"there":[96],"exists":[97],"substantial":[98],"reuse":[100,117],"within":[101],"TBs":[102],"rather":[103],"than":[104],"across":[105],"TBs.":[107],"Moreover,":[108],"inter-TB":[110],"interference":[111],"enlarges":[113],"intra-TB":[115],"distances.":[118],"To":[119],"end,":[121],"propose":[123],"translation-aware":[125],"TB":[126],"scheduling":[127],"lightweight":[129],"L1":[131,148],"TLB":[132,149],"partitioning":[133],"effectively":[135],"mitigate":[136],"contention.":[138],"Experimental":[139],"results":[140],"show":[141],"our":[143],"proposed":[144],"approach":[145],"improves":[146],"hit":[150],"rate,":[151],"improvement":[154],"translates":[155],"to,":[156],"average,":[158],"12.5%":[160],"execution":[161],"time":[162],"reduction.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}