{"id":"https://openalex.org/W3086484626","doi":"https://doi.org/10.1109/hpcs48598.2019.9188095","title":"Polyhedral Model Guided Automatic GPU Cache Exploitation Framework","display_name":"Polyhedral Model Guided Automatic GPU Cache Exploitation Framework","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W3086484626","doi":"https://doi.org/10.1109/hpcs48598.2019.9188095","mag":"3086484626"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs48598.2019.9188095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","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/A5051171715","display_name":"Abhishek A Patwardhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abhishek A. Patwardhan","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075524478","display_name":"Ramakrishna Upadrasta","orcid":"https://orcid.org/0000-0002-5290-3266"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramakrishna Upadrasta","raw_affiliation_strings":["Scalable Compilers for Heterogeneous Architectures Lab, Indian Institute of Technology Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Scalable Compilers for Heterogeneous Architectures Lab, Indian Institute of Technology Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051171715"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55478737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"496","last_page":"503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9966999888420105,"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":0.9959999918937683,"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":0.8968082666397095},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7969741821289062},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6265743374824524},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5972897410392761},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5696649551391602},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.566935658454895},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5425944328308105},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47825542092323303},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.4502597749233246},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.4158173203468323},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2696104049682617},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16156283020973206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8968082666397095},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7969741821289062},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6265743374824524},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5972897410392761},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5696649551391602},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.566935658454895},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5425944328308105},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47825542092323303},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.4502597749233246},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.4158173203468323},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2696104049682617},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16156283020973206},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcs48598.2019.9188095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1191262899","https://openalex.org/W1547909858","https://openalex.org/W1558370006","https://openalex.org/W1675130169","https://openalex.org/W1782174992","https://openalex.org/W1854214752","https://openalex.org/W1973532523","https://openalex.org/W2034761517","https://openalex.org/W2064675550","https://openalex.org/W2077143534","https://openalex.org/W2083056254","https://openalex.org/W2091553595","https://openalex.org/W2110195531","https://openalex.org/W2110301098","https://openalex.org/W2113190809","https://openalex.org/W2126026097","https://openalex.org/W2147193503","https://openalex.org/W2150953684","https://openalex.org/W2153636750","https://openalex.org/W2154078685","https://openalex.org/W2294413161","https://openalex.org/W2340604309","https://openalex.org/W2346144740","https://openalex.org/W4235662649","https://openalex.org/W6633402081","https://openalex.org/W6643480586"],"related_works":["https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W1999524790","https://openalex.org/W1574397187","https://openalex.org/W4221139464","https://openalex.org/W3106055984","https://openalex.org/W2996929894","https://openalex.org/W4289827464","https://openalex.org/W4223480868","https://openalex.org/W2111914791"],"abstract_inverted_index":{"We":[0,26,49,76,90,115,156],"propose":[1],"a":[2,35,56,63,150],"compiler":[3,67],"driven":[4],"acceleration":[5],"of":[6,17,37,73,83,87,165,176],"parallel":[7],"computations":[8,38],"on":[9,94],"GPUs":[10],"by":[11,54,112],"exploiting":[12],"the":[13,84,106,135],"various":[14],"special":[15,136,177],"varieties":[16,72],"caches":[18,138,179],"(texture,":[19],"surface":[20],"and":[21,98,128,131],"constant":[22],"for":[23,34,80,184],"NVIDIA":[24],"GPUs).":[25],"show":[27,132],"that":[28,44,133,158,180],"our":[29,92,159],"method":[30],"obtains":[31],"better":[32],"performance":[33],"class":[36],"when":[39],"compared":[40],"with":[41],"earlier":[42],"methods":[43],"use":[45,77],"on-chip":[46],"shared":[47,152],"memory.":[48],"provide":[50],"an":[51],"end-to-end":[52],"solution":[53],"developing":[55],"fully":[57],"automatic,":[58],"sound,":[59],"static":[60],"framework":[61],"within":[62],"state-of-art":[64],"source-to-source":[65],"Polyhedral":[66],"(PPCG)":[68],"to":[69,101,145],"exploit":[70],"these":[71,140],"GPU":[74,88,137,166,178],"caches.":[75,89],"polyhedral":[78],"model":[79],"profitability":[81],"modeling":[82],"particular":[85],"variety":[86],"evaluate":[91],"implementation":[93],"PolyBench/C":[95],"benchmark":[96],"kernels":[97],"report":[99],"up":[100,144],"1.":[102],"5x":[103],"speedups":[104],"over":[105,149],"current":[107],"memory":[108,153],"mapping":[109],"strategy":[110],"used":[111],"PPCG":[113],"compiler.":[114],"also":[116],"consider":[117],"sample":[118],"real-world":[119],"representative":[120],"kernels:":[121],"PageRank,":[122],"DNN":[123],"layer":[124],"(LSTM),":[125],"solvers":[126],"(Poisson":[127],"DWE-FDTD":[129],"stencil),":[130],"using":[134],"in":[139,143],"programs":[141],"results":[142],"2.":[146],"6x":[147],"speedup":[148],"standard":[151],"based":[154],"implementation.":[155],"believe":[157],"contribution":[160],"is":[161],"towards":[162],"automatic":[163],"exploitation":[164],"cache/memory":[167],"hierarchy":[168],"as":[169],"it":[170],"shows":[171],"general":[172],"purpose":[173],"computing":[174],"usage":[175],"were":[181],"originally":[182],"designed":[183],"image":[185],"processing":[186],"applications.":[187]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}