{"id":"https://openalex.org/W7131087481","doi":"https://doi.org/10.1109/cgo68049.2026.11395210","title":"FRUGAL: Pushing GPU Applications beyond Memory Limits","display_name":"FRUGAL: Pushing GPU Applications beyond Memory Limits","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7131087481","doi":"https://doi.org/10.1109/cgo68049.2026.11395210"},"language":null,"primary_location":{"id":"doi:10.1109/cgo68049.2026.11395210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5078250463","display_name":"Lingqi Zhang","orcid":"https://orcid.org/0000-0002-2452-1551"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Lingqi Zhang","raw_affiliation_strings":["RIKEN Center for Computational Science,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science,Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416150","display_name":"Tengfei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tengfei Wang","raw_affiliation_strings":["Google Cloud Japan,Japan"],"affiliations":[{"raw_affiliation_string":"Google Cloud Japan,Japan","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126658889","display_name":"Jiajun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Huang","raw_affiliation_strings":["University of South Florida,USA"],"affiliations":[{"raw_affiliation_string":"University of South Florida,USA","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126586098","display_name":"Chen Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chen Zhuang","raw_affiliation_strings":["RIKEN Center for Computational Science,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science,Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080497888","display_name":"Ivan R. Ivanov","orcid":"https://orcid.org/0000-0003-0356-3768"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ivan R. Ivanov","raw_affiliation_strings":["RIKEN Center for Computational Science,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science,Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053998645","display_name":"Chen Peng","orcid":"https://orcid.org/0000-0003-3641-2309"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Chen","raw_affiliation_strings":["RIKEN Center for Computational Science,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science,Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126650343","display_name":"Toshio Endo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshio Endo","raw_affiliation_strings":["Institute of Science Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Institute of Science Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123852860","display_name":"Mohamed Wahib","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mohamed Wahib","raw_affiliation_strings":["RIKEN Center for Computational Science,Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science,Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5078250463"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87693562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"188","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.534500002861023,"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":0.534500002861023,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.041200000792741776,"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":0.02889999933540821,"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/memory-footprint","display_name":"Memory footprint","score":0.786899983882904},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.771399974822998},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7145000100135803},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6007999777793884},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.49570000171661377},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4327000081539154},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.3926999866962433},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.3831000030040741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413000106811523},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.786899983882904},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.771399974822998},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7145000100135803},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6007999777793884},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5947999954223633},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.49570000171661377},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3926999866962433},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C18766215","wikidata":"https://www.wikidata.org/wiki/Q7708532","display_name":"Texture memory","level":5,"score":0.2818000018596649},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C76399640","wikidata":"https://www.wikidata.org/wiki/Q189401","display_name":"Virtual memory","level":4,"score":0.260699987411499},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo68049.2026.11395210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo68049.2026.11395210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7625782489776611,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2011963492","https://openalex.org/W2040466547","https://openalex.org/W2144344516","https://openalex.org/W2159959523","https://openalex.org/W2171268876","https://openalex.org/W2489529491","https://openalex.org/W2613580061","https://openalex.org/W2621795851","https://openalex.org/W2758320287","https://openalex.org/W2789114820","https://openalex.org/W2901994046","https://openalex.org/W2951436624","https://openalex.org/W2953358830","https://openalex.org/W2963153849","https://openalex.org/W2999629458","https://openalex.org/W3003229632","https://openalex.org/W3021182071","https://openalex.org/W3037443854","https://openalex.org/W3041850557","https://openalex.org/W3082198846","https://openalex.org/W3129831491","https://openalex.org/W3130911940","https://openalex.org/W3131379896","https://openalex.org/W3170905359","https://openalex.org/W3196320218","https://openalex.org/W3209568355","https://openalex.org/W4214549129","https://openalex.org/W4220703317","https://openalex.org/W4246166885","https://openalex.org/W4282974849","https://openalex.org/W4318541614","https://openalex.org/W4321446282","https://openalex.org/W4321617925","https://openalex.org/W4321636636","https://openalex.org/W4327930439","https://openalex.org/W4367684987","https://openalex.org/W4376632753","https://openalex.org/W4387321091","https://openalex.org/W4387321556","https://openalex.org/W4388662126","https://openalex.org/W4394871786","https://openalex.org/W4395106434","https://openalex.org/W4396913021","https://openalex.org/W4400409913","https://openalex.org/W4400410574","https://openalex.org/W4400877433","https://openalex.org/W4408903016"],"related_works":[],"abstract_inverted_index":{"GPUs":[0,15],"power":[1],"modern":[2],"scientific":[3],"and":[4,22,57,84,89,96,114,129,146],"AI":[5],"applications,":[6],"but":[7,49],"their":[8],"limited":[9],"memory":[10,62,70,123,154],"capacity":[11],"restricts":[12],"scalability.":[13],"Buying":[14],"with":[16,131],"larger":[17],"HBM":[18],"is":[19,47],"prohibitively":[20],"expensive":[21],"still":[23],"bounded":[24],"by":[25,125],"market":[26],"limits.":[27],"Existing":[28],"solutions":[29],"either":[30],"exploit":[31],"application-specific":[32],"knowledge":[33],"through":[34],"out-of-core":[35],"techniques,":[36],"which":[37,46],"lack":[38],"generality,":[39],"or":[40],"rely":[41],"on":[42,106],"system-level":[43],"page":[44],"faulting,":[45],"transparent":[48],"inefficient.":[50],"We":[51],"propose":[52],"FRUGAL,":[53],"an":[54,73,76,100],"application-agnostic":[55],"framework":[56],"methodology":[58],"that":[59,117],"reduces":[60,120],"GPU":[61,122,153],"footprint":[63],"while":[64],"sustaining":[65],"high":[66],"performance.":[67],"FRUGAL":[68,91,118,139],"formulates":[69],"management":[71],"as":[72],"optimization":[74,103],"over":[75],"application\u2019s":[77],"execution":[78],"graph,":[79],"encompassing":[80],"prefetching,":[81],"kernel":[82],"execution,":[83],"offloading.":[85],"Using":[86],"static":[87],"analysis":[88],"profiling,":[90],"applies":[92],"a":[93,133],"two-phase":[94],"scheduling":[95],"migration":[97],"strategy,":[98],"solving":[99],"otherwise":[101],"intractable":[102],"efficiently.":[104],"Evaluations":[105],"Tiled":[107,110],"Cholesky":[108],"Decomposition,":[109,112],"LU":[111],"Tiny-CUDA-NN,":[113],"QuEST":[115],"show":[116],"significantly":[119],"maximum":[121],"usage":[124],"80.21%,":[126],"80.20%,":[127],"64.75%":[128],"60.86%":[130],"only":[132],"geometric":[134],"mean":[135],"of":[136],"28.31%":[137],"slowdown.":[138],"allows":[140],"applications":[141],"to":[142],"exceed":[143],"hardware-imposed":[144],"limits,":[145],"maintains":[147],"strong":[148],"performance":[149],"scalability":[150],"beyond":[151],"existing":[152],"constraints,":[155],"without":[156],"additional":[157],"hardware":[158],"cost.":[159]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}