{"id":"https://openalex.org/W3173358825","doi":"https://doi.org/10.1145/3453483.3454038","title":"DeepCuts: a deep learning optimization framework for versatile GPU workloads","display_name":"DeepCuts: a deep learning optimization framework for versatile GPU workloads","publication_year":2021,"publication_date":"2021-06-18","ids":{"openalex":"https://openalex.org/W3173358825","doi":"https://doi.org/10.1145/3453483.3454038","mag":"3173358825"},"language":"en","primary_location":{"id":"doi:10.1145/3453483.3454038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453483.3454038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation","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/A5102939095","display_name":"Wookeun Jung","orcid":"https://orcid.org/0000-0001-6750-6979"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wookeun Jung","raw_affiliation_strings":["Seoul National University, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006235505","display_name":"Thanh Tuan Dao","orcid":"https://orcid.org/0000-0002-9897-2769"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thanh Tuan Dao","raw_affiliation_strings":["Seoul National University, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100767182","display_name":"Jaejin Lee","orcid":"https://orcid.org/0000-0003-4638-8170"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaejin Lee","raw_affiliation_strings":["Seoul National University, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102939095"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.6332,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.8575817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9979000091552734,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8784171342849731},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7768746614456177},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6205971240997314},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5886284112930298},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5768665075302124},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5625489950180054},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5551537871360779},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5116448998451233},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4642069935798645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590728282928467},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.449621319770813},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3550526201725006},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3340643644332886},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15817967057228088},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15623822808265686},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.0992453396320343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8784171342849731},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7768746614456177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6205971240997314},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5886284112930298},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5768665075302124},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5625489950180054},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5551537871360779},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5116448998451233},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4642069935798645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590728282928467},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.449621319770813},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3550526201725006},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3340643644332886},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15817967057228088},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15623822808265686},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0992453396320343},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3453483.3454038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3453483.3454038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W645173616","https://openalex.org/W1686810756","https://openalex.org/W2002555321","https://openalex.org/W2100218206","https://openalex.org/W2108598243","https://openalex.org/W2135653967","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2402144811","https://openalex.org/W2565305208","https://openalex.org/W2804032941","https://openalex.org/W2811130204","https://openalex.org/W2887327791","https://openalex.org/W2933138175","https://openalex.org/W2951815798","https://openalex.org/W2963446712","https://openalex.org/W2963844898","https://openalex.org/W2981758446","https://openalex.org/W2988396473","https://openalex.org/W3136479147","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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Widely":[0],"used":[1],"Deep":[2],"Learning":[3],"(DL)":[4],"frameworks,":[5,147],"such":[6,148],"as":[7,149],"TensorFlow,":[8],"PyTorch,":[9],"and":[10,45,95,112,121,134,142,153],"MXNet,":[11],"heavily":[12],"rely":[13],"on":[14],"the":[15,27,100,143],"NVIDIA":[16],"cuDNN":[17,22,60],"for":[18,83,132],"performance.":[19,29,73],"However,":[20],"using":[21],"does":[23],"not":[24],"always":[25],"give":[26],"best":[28],"One":[30],"reason":[31,57],"is":[32,35,58],"that":[33,51,59,65,137],"it":[34],"hard":[36],"to":[37,71],"handle":[38],"every":[39],"case":[40],"of":[41,69],"versatile":[42,84],"DNN":[43],"models":[44],"GPU":[46,85,96,110,115,122],"architectures":[47],"with":[48,128],"a":[49,53,67,79,108],"library":[50],"has":[52],"fixed":[54],"implementation.":[55],"Another":[56],"lacks":[61],"kernel":[62,92,118],"fusion":[63],"functionality":[64],"gives":[66],"lot":[68],"chances":[70],"improve":[72],"In":[74],"this":[75],"paper,":[76],"we":[77],"propose":[78],"DL":[80,101,105,130,145],"optimization":[81,146],"framework":[82],"workloads,":[86],"called":[87],"DeepCuts.":[88],"It":[89,98],"considers":[90],"both":[91],"implementation":[93,119],"parameters":[94,120],"architectures.":[97],"analyzes":[99],"workload,":[102],"groups":[103],"multiple":[104],"operations":[106],"into":[107],"single":[109],"kernel,":[111],"generates":[113],"optimized":[114],"kernels":[116],"considering":[117],"architecture":[123],"parameters.":[124],"The":[125],"evaluation":[126],"result":[127],"various":[129],"workloads":[131],"inference":[133],"training":[135],"indicates":[136],"DeepCuts":[138],"outperforms":[139],"cuDNN/cuBLAS-based":[140],"implementations":[141],"state-of-the-art":[144],"TVM,":[150],"TensorFlow":[151],"XLA,":[152],"TensorRT.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}