{"id":"https://openalex.org/W3041537833","doi":"https://doi.org/10.1109/isqed48828.2020.9136967","title":"Alleviating Bottlenecks for DNN Execution on GPUs via Opportunistic Computing","display_name":"Alleviating Bottlenecks for DNN Execution on GPUs via Opportunistic Computing","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3041537833","doi":"https://doi.org/10.1109/isqed48828.2020.9136967","mag":"3041537833"},"language":"en","primary_location":{"id":"doi:10.1109/isqed48828.2020.9136967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed48828.2020.9136967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 21st International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"},"type":"preprint","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/A5003848547","display_name":"Xianwei Cheng","orcid":"https://orcid.org/0009-0001-3550-2647"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xianwei Cheng","raw_affiliation_strings":["Department of Computer Science and Engineering, University of North Texas"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058413620","display_name":"Hui Zhao","orcid":"https://orcid.org/0000-0003-3683-4077"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, University of North Texas"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmut Kandemir","raw_affiliation_strings":["Department of Computer Science and Engineering, Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070359867","display_name":"Saraju P. Mohanty","orcid":"https://orcid.org/0000-0003-2959-6541"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saraju Mohanty","raw_affiliation_strings":["Department of Computer Science and Engineering, University of North Texas"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090623049","display_name":"Beilei Jiang","orcid":"https://orcid.org/0009-0001-3985-333X"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Beilei Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of North Texas"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of North Texas","institution_ids":["https://openalex.org/I123534392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003848547"],"corresponding_institution_ids":["https://openalex.org/I123534392"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08826087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"267"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9923999905586243,"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/T13553","display_name":"Age of Information Optimization","score":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.85135817527771},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5830020904541016},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40039145946502686},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32065677642822266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85135817527771},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5830020904541016},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40039145946502686},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32065677642822266}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isqed48828.2020.9136967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed48828.2020.9136967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 21st International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1598866093","https://openalex.org/W1667652561","https://openalex.org/W1789336918","https://openalex.org/W1979527452","https://openalex.org/W2010069327","https://openalex.org/W2112796928","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2587527900","https://openalex.org/W2624696420","https://openalex.org/W2741546454","https://openalex.org/W2765315405","https://openalex.org/W2769815320","https://openalex.org/W2798371872","https://openalex.org/W2804777790","https://openalex.org/W2946525618","https://openalex.org/W2951091066","https://openalex.org/W2963367891","https://openalex.org/W2963873559","https://openalex.org/W3101558675","https://openalex.org/W4256268103","https://openalex.org/W4302296459","https://openalex.org/W6622239757","https://openalex.org/W6635810480","https://openalex.org/W6652670974","https://openalex.org/W6684191040","https://openalex.org/W6752390237","https://openalex.org/W6752686181","https://openalex.org/W6763412433"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Edge":[0],"computing":[1,94],"and":[2,124],"IoT":[3],"applications":[4],"are":[5,31,117],"severely":[6],"constrained":[7],"by":[8,72],"limited":[9],"hardware":[10],"resource.":[11],"This":[12,57],"makes":[13],"memory-consuming":[14],"DNN":[15,48,62,127,140],"(Deep":[16],"Neural":[17],"Network)":[18],"frameworks":[19],"not":[20],"applicable":[21],"to":[22,96,113,119],"edge":[23],"computing.":[24,78],"Simple":[25],"algorithms":[26],"such":[27],"as":[28,143,145],"direct":[29],"convolution":[30],"finding":[32],"their":[33],"way":[34],"in":[35,85],"embedded":[36],"machine":[37],"learning.":[38],"As":[39],"one":[40],"of":[41,54,107],"the":[42,52,68,86,105,126,135],"most":[43],"widely":[44],"used":[45],"platforms":[46],"for":[47],"acceleration,":[49],"GPUs":[50],"face":[51],"bottleneck":[53,71],"on-chip":[55,69],"bandwidth.":[56],"work":[58],"introduces":[59],"a":[60],"GPU":[61],"execution":[63,128],"architecture":[64],"that":[65,134],"can":[66,138],"relieve":[67,125],"bandwidth":[70],"reducing":[73],"data":[74,82,101,122],"movement":[75,123],"through":[76],"opportunistic":[77,93],"We":[79],"first":[80],"investigate":[81],"access":[83],"patterns":[84],"hardware's":[87],"view.":[88],"Then":[89],"we":[90],"propose":[91],"two":[92],"techniques":[95,116],"predictably":[97],"perform":[98],"computation":[99,112],"when":[100],"is":[102],"available":[103],"with":[104],"help":[106],"assistant":[108],"warps.":[109],"By":[110],"moving":[111],"data,":[114],"our":[115],"able":[118],"significantly":[120],"reduce":[121],"bottleneck.":[129],"Our":[130],"evaluation":[131],"results":[132],"show":[133],"proposed":[136],"technique":[137],"improve":[139],"application":[141],"performance":[142],"much":[144],"55%.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}