{"id":"https://openalex.org/W1993385165","doi":"https://doi.org/10.1109/sasp.2009.5226334","title":"A memory optimization technique for software-managed scratchpad memory in GPUs","display_name":"A memory optimization technique for software-managed scratchpad memory in GPUs","publication_year":2009,"publication_date":"2009-07-01","ids":{"openalex":"https://openalex.org/W1993385165","doi":"https://doi.org/10.1109/sasp.2009.5226334","mag":"1993385165"},"language":"en","primary_location":{"id":"doi:10.1109/sasp.2009.5226334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2009.5226334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 7th Symposium on Application Specific Processors","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/A5109752527","display_name":"Maryam Moazeni","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maryam Moazeni","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, USA","[Computer Science Department, University of California, Los Angeles, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"[Computer Science Department, University of California, Los Angeles, USA]","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056478657","display_name":"Alex Bui","orcid":"https://orcid.org/0000-0002-4702-1373"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Bui","raw_affiliation_strings":["Department of Radiological Sciences, University of California, Los Angeles, USA","Department of Radiological Sciences, University of California Los Angeles, USA"],"affiliations":[{"raw_affiliation_string":"Department of Radiological Sciences, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Department of Radiological Sciences, University of California Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078132977","display_name":"Majid Sarrafzadeh","orcid":"https://orcid.org/0000-0001-8407-8689"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Majid Sarrafzadeh","raw_affiliation_strings":["Computer Science Department, University of California, Los Angeles, USA","[Computer Science Department, University of California, Los Angeles, USA]"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of California, Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"[Computer Science Department, University of California, Los Angeles, USA]","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109752527"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":3.2159,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9206815,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"68","issue":null,"first_page":"43","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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":0.9983999729156494,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.885325014591217},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6946883201599121},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.6373570561408997},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5290614366531372},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4707881808280945},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4368104338645935},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3982307016849518},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3801853060722351},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3725707530975342},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2042648196220398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.885325014591217},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6946883201599121},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.6373570561408997},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5290614366531372},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4707881808280945},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4368104338645935},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3982307016849518},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3801853060722351},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3725707530975342},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2042648196220398},{"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":2,"locations":[{"id":"doi:10.1109/sasp.2009.5226334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sasp.2009.5226334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE 7th Symposium on Application Specific Processors","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.6650","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.6650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.ucla.edu/~mmoazeni/papers/SASP-moazeni.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W603342411","https://openalex.org/W1482334991","https://openalex.org/W1533758240","https://openalex.org/W1558000309","https://openalex.org/W1589918049","https://openalex.org/W1969289728","https://openalex.org/W1982825626","https://openalex.org/W1990800384","https://openalex.org/W1992851788","https://openalex.org/W2011078763","https://openalex.org/W2034397885","https://openalex.org/W2044636417","https://openalex.org/W2052286413","https://openalex.org/W2060773902","https://openalex.org/W2084984944","https://openalex.org/W2098511965","https://openalex.org/W2104441030","https://openalex.org/W2108792719","https://openalex.org/W2121758805","https://openalex.org/W2128022558","https://openalex.org/W2134693673","https://openalex.org/W2140953138","https://openalex.org/W2149474590","https://openalex.org/W2153492376","https://openalex.org/W2157828735","https://openalex.org/W2169150396","https://openalex.org/W2231791608","https://openalex.org/W2611804663","https://openalex.org/W3009214340","https://openalex.org/W4237977381","https://openalex.org/W4255599643","https://openalex.org/W6681978706"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2384715785","https://openalex.org/W2349624418","https://openalex.org/W2064459023","https://openalex.org/W2384611437","https://openalex.org/W2347873412"],"abstract_inverted_index":{"With":[0],"the":[1,11,42,50,77,82,87,91,102,109,115,119],"appearance":[2],"of":[3,14,44,89,104,111,117,138],"massively":[4],"parallel":[5],"and":[6,59,155],"inexpensive":[7],"platforms":[8,55],"such":[9],"as":[10],"G80":[12,83],"generation":[13],"NVIDIA":[15,151],"GPUs,":[16],"more":[17],"real-life":[18],"applications":[19,61],"will":[20,62],"be":[21],"designed":[22],"or":[23],"ported":[24],"to":[25,85,167,174],"these":[26,39,54],"platforms.":[27,40],"This":[28],"requires":[29],"structured":[30],"transformation":[31],"methods":[32],"that":[33,100],"remove":[34],"existing":[35],"application":[36,51,120],"bottlenecks":[37],"in":[38,53,81,146,170],"Balancing":[41],"usage":[43,103],"on-chip":[45],"resources,":[46],"used":[47],"for":[48,76],"improving":[49],"performance,":[52],"is":[56,124],"often":[57],"non-intuitive":[58],"some":[60],"run":[63],"into":[64],"resource":[65],"limits.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70],"present":[71],"a":[72,96,136],"memory":[73,80,97,105,112,132,162],"optimization":[74,98,133,163],"technique":[75],"software-managed":[78],"scratchpad":[79,92],"architecture":[84],"alleviate":[86],"constraints":[88],"using":[90,150],"memory.":[93],"We":[94,129],"propose":[95],"scheme":[99,134,164],"minimizes":[101],"space":[106],"by":[107,135],"discovering":[108],"chances":[110],"reuse":[113],"with":[114],"goal":[116],"maximizing":[118],"performance.":[121],"Our":[122],"solution":[123],"based":[125,158],"on":[126,140,159],"graph":[127],"coloring.":[128],"evaluated":[130],"our":[131,160],"set":[137],"experiments":[139],"an":[141],"image":[142],"processing":[143],"benchmark":[144],"suite":[145],"medical":[147],"imaging":[148],"domain":[149],"Quadro":[152],"FX":[153],"5600":[154],"CUDA.":[156],"Implementations":[157],"proposed":[161],"showed":[165],"up":[166],"37%":[168],"decrease":[169],"execution":[171],"time":[172],"comparing":[173],"their":[175],"naive":[176],"GPU":[177],"implementations.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
