{"id":"https://openalex.org/W4232718373","doi":"https://doi.org/10.1109/cgo.2019.8661188","title":"Kernel Fusion/Decomposition for Automatic GPU-Offloading","display_name":"Kernel Fusion/Decomposition for Automatic GPU-Offloading","publication_year":2019,"publication_date":"2019-02-01","ids":{"openalex":"https://openalex.org/W4232718373","doi":"https://doi.org/10.1109/cgo.2019.8661188"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2019.8661188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5100660168","display_name":"Alok Mishra","orcid":"https://orcid.org/0000-0003-1275-2050"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alok Mishra","raw_affiliation_strings":["Stony Brook University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048530008","display_name":"Martin Kong","orcid":"https://orcid.org/0000-0001-8008-0220"},"institutions":[{"id":"https://openalex.org/I200870766","display_name":"Brookhaven National Laboratory","ror":"https://ror.org/02ex6cf31","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I200870766","https://openalex.org/I39565521","https://openalex.org/I4210142672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Kong","raw_affiliation_strings":["Brookhaven National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brookhaven National Laboratory, USA","institution_ids":["https://openalex.org/I200870766"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Stony Brook University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":null,"first_page":"283","last_page":"284"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9962999820709229,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8044681549072266},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6471660733222961},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.6208934783935547},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.48513659834861755},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47172442078590393},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42748308181762695},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.406390517950058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36480897665023804},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3113299608230591},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.131290465593338},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.079530268907547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06043681502342224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8044681549072266},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6471660733222961},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.6208934783935547},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.48513659834861755},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47172442078590393},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42748308181762695},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.406390517950058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36480897665023804},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3113299608230591},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.131290465593338},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.079530268907547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06043681502342224},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo.2019.8661188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2019.8661188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1598202309","https://openalex.org/W2032391783","https://openalex.org/W2606963276","https://openalex.org/W2788413446","https://openalex.org/W2964258936","https://openalex.org/W4250047567","https://openalex.org/W6687325977","https://openalex.org/W6736295056"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"The":[0,156,243],"massively":[1],"parallel":[2],"architecture":[3],"of":[4,27,106,151,159,187,194,222,245,254,290,300],"GPU":[5,120,302,310,339],"accelerators":[6],"are":[7,205,237,258,324],"being":[8],"harnessed":[9],"to":[10,61,86,117,137,183,294,316],"expedite":[11],"computational":[12,115],"workloads":[13],"in":[14,124,163],"cutting":[15],"edge":[16],"scientific":[17],"research.":[18],"Unfortunately":[19],"writing":[20],"applications":[21,104],"for":[22,53],"GPUs":[23],"requires":[24],"extensive":[25],"knowledge":[26],"the":[28,31,34,107,125,132,179,185,192,220,223,227,231,252,255,288,297,317,320],"underlying":[29],"architecture,":[30],"application":[32,54],"and":[33,48,98,139,147,190,279,312,332],"interfacing":[35],"programming":[36,43,64],"model.":[37,242,318],"Moreover,":[38],"(re-)writing":[39],"kernels":[40],"using":[41],"lower-level":[42],"models":[44,264],"such":[45,203],"as":[46],"CUDA":[47],"OpenCL":[49],"is":[50,60,82,95,218],"a":[51,63,96,119,141,213,272,280,301,334],"burden":[52],"scientists.":[55],"A":[56],"more":[57],"appealing":[58],"strategy":[59],"leverage":[62],"model":[65,248,269,278,285],"layered":[66],"on":[67],"directive-based":[68],"optimization:":[69],"OpenMP,":[70],"whose":[71,216],"recent":[72,281],"specification":[73],"significantly":[74],"extends":[75],"its":[76],"accelerator":[77],"functionalities.":[78],"Despite":[79],"this,":[80],"it":[81],"still":[83],"quite":[84],"challenging":[85],"optimize":[87],"large":[88,102],"scale":[89,103],"applications,":[90],"since":[91],"\u201cpragmatizing\u201d":[92],"each":[93],"kernel":[94,166,188,233,292,322],"repetitive":[97],"complex":[99],"task.":[100],"In":[101],"most":[105],"operations":[108],"could":[109],"be":[110],"small,":[111],"don't":[112],"have":[113],"enough":[114],"work":[116,161,273],"justify":[118],"execution,":[121],"deeply":[122],"buried":[123],"library":[126],"specification,":[127],"or":[128,199],"evenly":[129],"spread":[130],"throughout":[131],"application.":[133],"Thus,":[134],"we":[135,207,236,308,326],"seek":[136],"design":[138],"build":[140],"compiler":[142],"framework":[143],"that":[144,168],"can":[145],"automatically":[146,327],"profitably":[148],"offload":[149],"regions":[150],"code":[152,337],"with":[153,306],"these":[154,307],"characteristics.":[155],"driving":[157],"principle":[158],"our":[160],"resides":[162],"generating":[164],"numerous":[165],"variants":[167,234,323],"result":[169],"from":[170],"fusing":[171],"and/or":[172],"decomposing":[173],"existing":[174,262],"function":[175],"bodies.":[176],"We":[177,257],"analyze":[178],"program's":[180],"call":[181],"graph":[182,275],"determine":[184],"\u201cproximity\u201d":[186],"calls":[189],"evaluate":[191],"degree":[193],"data":[195,313],"reuse":[196],"among":[197,230],"adjacent":[198],"\u201cclose-enough\u201d":[200],"calls.":[201],"When":[202],"patterns":[204],"detected":[206],"generate":[208],"several":[209],"scenarios,":[210],"until":[211],"producing":[212],"single":[214],"variant":[215],"footprint":[217],"near":[219],"capacity":[221],"GPU.":[224],"To":[225],"compare":[226],"potential":[228],"performance":[229,298],"various":[232],"generated,":[235],"designing":[238],"an":[239],"adaptive":[240],"cost":[241,247,263,315],"precision":[244],"this":[246],"will":[249],"depend":[250],"upon":[251,261],"analyzability":[253],"program.":[256],"also":[259],"building":[260],"like":[265],"Baghsorkhi":[266],"et":[267,283],"al.'s":[268,284],"which":[270,286],"proposed":[271],"flow":[274],"based":[276],"analytical":[277],"Hong":[282],"propose":[287],"use":[289],"abstract":[291],"emulations":[293],"help":[295],"identify":[296],"bottlenecks":[299],"program":[303],"execution.":[304],"Along":[305],"introduce":[309],"initialization":[311],"transfer":[314],"Once":[319],"profitable":[321],"detected,":[325],"insert":[328],"pertinent":[329],"OpenMP":[330],"directives":[331],"provide":[333],"newly":[335],"generated":[336],"supporting":[338],"offloading.":[340]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}