{"id":"https://openalex.org/W2398414514","doi":"https://doi.org/10.1145/2897937.2897966","title":"A model-driven approach to warp/thread-block level GPU cache bypassing","display_name":"A model-driven approach to warp/thread-block level GPU cache bypassing","publication_year":2016,"publication_date":"2016-05-25","ids":{"openalex":"https://openalex.org/W2398414514","doi":"https://doi.org/10.1145/2897937.2897966","mag":"2398414514"},"language":"en","primary_location":{"id":"doi:10.1145/2897937.2897966","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2897937.2897966","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2897937.2897966","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2897937.2897966","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037376215","display_name":"Hongwen Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwen Dai","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323120","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-6946-4335"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064269047","display_name":"Saurabh Gupta","orcid":"https://orcid.org/0000-0002-5984-852X"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Gupta","raw_affiliation_strings":["Oak Ridge National Lab, Oak Ridge, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067289169","display_name":"Christos Kartsaklis","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christos Kartsaklis","raw_affiliation_strings":["Oak Ridge National Lab, Oak Ridge, TN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Lab, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085469786","display_name":"Mike Mantor","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":"Mike Mantor","raw_affiliation_strings":["Advanced Micro Devices, Orlando, FL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Orlando, FL","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9983000159263611,"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":0.9968000054359436,"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":0.8699241876602173},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.8120173215866089},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7781519889831543},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6995252966880798},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6804640293121338},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.6729161143302917},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.6595548391342163},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5905396342277527},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5750530362129211},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.4782944321632385},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.4697701632976532},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4607895314693451},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31492725014686584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8699241876602173},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8120173215866089},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7781519889831543},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6995252966880798},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6804640293121338},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.6729161143302917},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.6595548391342163},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5905396342277527},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5750530362129211},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.4782944321632385},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.4697701632976532},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4607895314693451},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31492725014686584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2897937.2897966","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2897937.2897966","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2897937.2897966","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2897937.2897966","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2897937.2897966","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2897937.2897966","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 53rd Annual Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3836870106","display_name":"SHF: Small: CPU-GPU Collaborative Execution in Fusion Architectures","funder_award_id":"1216569","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307757","display_name":"Advanced Micro Devices","ror":"https://ror.org/04kd6c783"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2398414514.pdf","grobid_xml":"https://content.openalex.org/works/W2398414514.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1968775993","https://openalex.org/W1970643910","https://openalex.org/W1979527452","https://openalex.org/W1982996921","https://openalex.org/W1997162567","https://openalex.org/W1997352364","https://openalex.org/W2027806965","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2062527253","https://openalex.org/W2065562952","https://openalex.org/W2067441262","https://openalex.org/W2075183163","https://openalex.org/W2080592089","https://openalex.org/W2081526957","https://openalex.org/W2090283364","https://openalex.org/W2090584832","https://openalex.org/W2091599698","https://openalex.org/W2093043622","https://openalex.org/W2097336080","https://openalex.org/W2109432325","https://openalex.org/W2128120785","https://openalex.org/W2130336316","https://openalex.org/W2143773524","https://openalex.org/W2144264070","https://openalex.org/W2146451305","https://openalex.org/W2150073849","https://openalex.org/W2167334577","https://openalex.org/W2547815835","https://openalex.org/W6682374492"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2363769136","https://openalex.org/W2114386333","https://openalex.org/W2126408955","https://openalex.org/W2539712666","https://openalex.org/W2148571123","https://openalex.org/W2396934146","https://openalex.org/W2369103246","https://openalex.org/W2734782074","https://openalex.org/W2115222420"],"abstract_inverted_index":{"The":[0],"high":[1],"amount":[2],"of":[3,33,42,45,74],"memory":[4],"requests":[5],"from":[6],"massive":[7],"threads":[8],"may":[9],"easily":[10],"cause":[11],"cache":[12,34,62],"contention":[13,35],"and":[14,36,93],"cache-miss-related":[15],"resource":[16,37],"congestion":[17,38],"on":[18,69,71,98],"GPUs.":[19],"This":[20],"paper":[21],"proposes":[22],"a":[23,40,56,72],"simple":[24],"yet":[25],"effective":[26],"performance":[27,88],"model":[28],"to":[29,49,81],"estimate":[30],"the":[31,43,51,78],"impact":[32],"as":[39],"function":[41],"number":[44],"warps/thread":[46],"blocks":[47],"(TBs)":[48],"bypass":[50],"cache.":[52],"Then":[53],"we":[54],"design":[55],"hardware-based":[57],"dynamic":[58],"warp/thread-block":[59],"level":[60],"GPU":[61],"bypassing":[63],"scheme,":[64],"which":[65],"achieves":[66,86],"1.68x":[67],"speedup":[68],"average":[70],"set":[73],"memory-intensive":[75],"benchmarks":[76],"over":[77,90,95],"baseline.":[79],"Compared":[80],"prior":[82],"works,":[83],"our":[84],"scheme":[85],"21.6%":[87],"improvement":[89],"SWL-best":[91],"[29]":[92],"11.9%":[94],"CBWT-best":[96],"[4]":[97],"average.":[99]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}