{"id":"https://openalex.org/W1981230615","doi":"https://doi.org/10.1145/2492408.2492421","title":"Software-level scheduling to exploit non-uniformly shared data cache on GPGPU","display_name":"Software-level scheduling to exploit non-uniformly shared data cache on GPGPU","publication_year":2013,"publication_date":"2013-06-16","ids":{"openalex":"https://openalex.org/W1981230615","doi":"https://doi.org/10.1145/2492408.2492421","mag":"1981230615"},"language":"en","primary_location":{"id":"doi:10.1145/2492408.2492421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2492408.2492421","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 SIGPLAN Workshop on Memory Systems Performance and Correctness","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/A5059368105","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0001-6658-6452"},"institutions":[{"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":"Bo Wu","raw_affiliation_strings":["The College of William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357271","display_name":"Weilin Wang","orcid":"https://orcid.org/0000-0003-4541-180X"},"institutions":[{"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":"Weilin Wang","raw_affiliation_strings":["The College of William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"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":"Xipeng Shen","raw_affiliation_strings":["The College of William and Mary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16285277"],"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":"1","last_page":"2"},"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":0.9991000294685364,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8875555396080017},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7694830894470215},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.732207715511322},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.669096052646637},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6531651616096497},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.587194561958313},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5140215158462524},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46151065826416016},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.45149606466293335},{"id":"https://openalex.org/keywords/cache-coherence","display_name":"Cache coherence","score":0.4116099178791046},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.36821621656417847},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.34671521186828613},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33882302045822144},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08207738399505615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8875555396080017},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7694830894470215},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.732207715511322},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.669096052646637},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6531651616096497},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.587194561958313},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5140215158462524},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46151065826416016},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.45149606466293335},{"id":"https://openalex.org/C141917322","wikidata":"https://www.wikidata.org/wiki/Q1025017","display_name":"Cache coherence","level":5,"score":0.4116099178791046},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.36821621656417847},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.34671521186828613},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33882302045822144},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08207738399505615},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2492408.2492421","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2492408.2492421","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 SIGPLAN Workshop on Memory Systems Performance and Correctness","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2020572638","https://openalex.org/W2072680607","https://openalex.org/W2087725506","https://openalex.org/W2128329055","https://openalex.org/W2168102371"],"related_works":["https://openalex.org/W2290179447","https://openalex.org/W2123859627","https://openalex.org/W3139889547","https://openalex.org/W2057019356","https://openalex.org/W1993010599","https://openalex.org/W2061075966","https://openalex.org/W2147122795","https://openalex.org/W3147501184","https://openalex.org/W2167303720","https://openalex.org/W2046128376"],"abstract_inverted_index":{"Data":[0],"cache":[1,90],"is":[2,45],"introduced":[3],"to":[4,6,19,66,70,87],"GPUs":[5],"mitigate":[7],"the":[8,43,73,76,89],"irregular":[9],"memory":[10],"access":[11],"problem.":[12],"But":[13],"few":[14],"studies":[15],"have":[16],"investigated":[17],"how":[18],"exploit":[20],"its":[21],"full":[22],"potential.":[23],"In":[24],"this":[25],"work,":[26],"we":[27],"consider":[28],"some":[29],"important":[30],"GPU":[31,51],"applications":[32],"that":[33,42],"feature":[34],"data":[35,71,83],"sharing":[36,44,84],"across":[37],"thread":[38,68,79],"blocks.":[39],"We":[40,60],"show":[41,100],"not":[46],"well":[47],"exploited":[48],"because":[49],"current":[50],"runtime":[52],"ignores":[53],"such":[54],"a":[55,92],"factor":[56],"when":[57],"scheduling":[58],"threads.":[59],"then":[61],"present":[62],"an":[63],"application-level":[64],"transformation":[65],"remap":[67],"blocks":[69,80],"on":[72,91,97,103],"fly.":[74],"With":[75],"software-level":[77],"scheduler,":[78],"with":[81],"much":[82],"are":[85],"scheduled":[86],"share":[88],"streaming":[93],"multiprocessor":[94],"(SM).":[95],"Experiments":[96],"four":[98],"benchmarks":[99],"1.23X":[101],"speedup":[102],"average.":[104]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}