{"id":"https://openalex.org/W4221003081","doi":"https://doi.org/10.1145/3497776.3517766","title":"Training of deep learning pipelines on memory-constrained GPUs via segmented fused-tiled execution","display_name":"Training of deep learning pipelines on memory-constrained GPUs via segmented fused-tiled execution","publication_year":2022,"publication_date":"2022-03-18","ids":{"openalex":"https://openalex.org/W4221003081","doi":"https://doi.org/10.1145/3497776.3517766","pmid":"https://pubmed.ncbi.nlm.nih.gov/35876769"},"language":"en","primary_location":{"id":"doi:10.1145/3497776.3517766","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3497776.3517766","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3497776.3517766","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3497776.3517766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015151039","display_name":"Yufan Xu","orcid":"https://orcid.org/0000-0002-7787-6460"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufan Xu","raw_affiliation_strings":["University of Utah, USA"],"raw_orcid":"https://orcid.org/0000-0002-7787-6460","affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055962929","display_name":"Saurabh Raje","orcid":"https://orcid.org/0000-0003-3294-1481"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurabh Raje","raw_affiliation_strings":["University of Utah, USA"],"raw_orcid":"https://orcid.org/0000-0003-3294-1481","affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039624297","display_name":"Atanas Rountev","orcid":"https://orcid.org/0000-0003-4556-4937"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanas Rountev","raw_affiliation_strings":["Ohio State University, USA"],"raw_orcid":"https://orcid.org/0000-0003-4556-4937","affiliations":[{"raw_affiliation_string":"Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082770727","display_name":"Gerald Sabin","orcid":"https://orcid.org/0000-0002-8672-4071"},"institutions":[{"id":"https://openalex.org/I4210092039","display_name":"RNET Technologies (United States)","ror":"https://ror.org/00mh27630","country_code":"US","type":"company","lineage":["https://openalex.org/I4210092039"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Sabin","raw_affiliation_strings":["RNET Technologies, USA"],"raw_orcid":"https://orcid.org/0000-0002-8672-4071","affiliations":[{"raw_affiliation_string":"RNET Technologies, USA","institution_ids":["https://openalex.org/I4210092039"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["Washington State University, USA"],"raw_orcid":"https://orcid.org/0000-0002-4062-0293","affiliations":[{"raw_affiliation_string":"Washington State University, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["University of Utah, USA"],"raw_orcid":"https://orcid.org/0000-0002-4737-2034","affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1015,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3510489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2022","issue":null,"first_page":"104","last_page":"116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8483936786651611},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7660462260246277},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7490619421005249},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6812705397605896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6458871960639954},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6009762287139893},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5616661310195923},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5396831631660461},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.503025233745575},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4805048704147339},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4800373315811157},{"id":"https://openalex.org/keywords/graphics-pipeline","display_name":"Graphics pipeline","score":0.45803263783454895},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.437261164188385},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4359052777290344},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.39756011962890625},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.382602721452713},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics","score":0.3347667455673218},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3312433362007141},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.20133790373802185},{"id":"https://openalex.org/keywords/3d-computer-graphics","display_name":"3D computer graphics","score":0.12429818511009216},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10095781087875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483936786651611},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7660462260246277},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7490619421005249},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6812705397605896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6458871960639954},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6009762287139893},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5616661310195923},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5396831631660461},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.503025233745575},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4805048704147339},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4800373315811157},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.45803263783454895},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.437261164188385},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4359052777290344},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.39756011962890625},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.382602721452713},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.3347667455673218},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312433362007141},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.20133790373802185},{"id":"https://openalex.org/C66629338","wikidata":"https://www.wikidata.org/wiki/Q189177","display_name":"3D computer graphics","level":3,"score":0.12429818511009216},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10095781087875366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3497776.3517766","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3497776.3517766","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3497776.3517766","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"},{"id":"pmid:35876769","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35876769","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Compiler construction : ... International Conference, CC ... : proceedings. CC (Conference)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9302555","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9302555","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Compil Constr","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3497776.3517766","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3497776.3517766","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3497776.3517766","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G447955464","display_name":null,"funder_award_id":"2018016","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6239431463","display_name":null,"funder_award_id":"2018016, 2119677, 2118737","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8955170022","display_name":null,"funder_award_id":"R41EB032722","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221003081.pdf","grobid_xml":"https://content.openalex.org/works/W4221003081.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1541729506","https://openalex.org/W2294929133","https://openalex.org/W2892942695","https://openalex.org/W2896180420","https://openalex.org/W2964054286","https://openalex.org/W2972073717","https://openalex.org/W3092310353","https://openalex.org/W3132591370","https://openalex.org/W3132977829","https://openalex.org/W3133796368","https://openalex.org/W3174529902","https://openalex.org/W4249932213"],"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/W2032944314"],"abstract_inverted_index":{"Training":[0],"models":[1],"with":[2,148],"massive":[3],"inputs":[4],"is":[5],"a":[6,69,138,167],"significant":[7],"challenge":[8],"in":[9,30,39,50,102,127,146],"the":[10,47,84,88,94,97,103,161,170],"development":[11],"of":[12,35,54,96,130,160,163,172],"Deep":[13,55,107],"Learning":[14,56,108],"pipelines":[15,109],"to":[16,60,63,117,140,155],"process":[17],"very":[18],"large":[19,153],"digital":[20],"image":[21],"datasets":[22],"as":[23],"required":[24],"by":[25,143],"Whole":[26],"Slide":[27],"Imaging":[28],"(WSI)":[29],"computational":[31,40],"pathology":[32],"and":[33,52,79,169],"analysis":[34],"brain":[36],"fMRI":[37],"images":[38,124,154],"neuroscience.":[41],"Graphics":[42],"Processing":[43],"Units":[44],"(GPUs)":[45],"represent":[46],"primary":[48],"workhorse":[49],"training":[51,67],"inference":[53,65],"models.":[57],"In":[58,133],"order":[59],"use":[61,112],"GPUs":[62,89],"run":[64],"or":[66],"on":[68,87,166],"neural":[70],"network":[71],"pipeline,":[72],"state-of-the-art":[73],"machine":[74],"learning":[75],"frameworks":[76],"like":[77],"PyTorch":[78,178],"TensorFlow":[80],"currently":[81],"require":[82],"that":[83],"collective":[85],"memory":[86,165],"must":[90],"be":[91,156],"larger":[92],"than":[93],"size":[95,162],"activations":[98],"at":[99],"any":[100],"stage":[101],"pipeline.":[104],"Therefore,":[105],"existing":[106,183],"for":[110],"these":[111],"cases":[113],"have":[114],"been":[115],"forced":[116],"develop":[118],"sub-optimal":[119],"\"patch-based\"":[120],"modeling":[121],"approaches,":[122],"where":[123],"are":[125],"processed":[126],"small":[128],"segments":[129],"an":[131],"image.":[132],"this":[134,141],"paper,":[135],"we":[136],"present":[137],"solution":[139],"problem":[142],"employing":[144],"tiling":[145],"conjunction":[147],"check-pointing,":[149],"thereby":[150],"enabling":[151],"arbitrarily":[152],"directly":[157],"processed,":[158],"irrespective":[159],"global":[164],"GPU":[168],"number":[171],"available":[173],"GPUs.":[174],"Experimental":[175],"results":[176],"using":[177],"demonstrate":[179],"enhanced":[180],"functionality/performance":[181],"over":[182],"frameworks.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}