{"id":"https://openalex.org/W2767203761","doi":"https://doi.org/10.1109/pact.2017.39","title":"POSTER: Design Space Exploration for Performance Optimization of Deep Neural Networks on Shared Memory Accelerators","display_name":"POSTER: Design Space Exploration for Performance Optimization of Deep Neural Networks on Shared Memory Accelerators","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2767203761","doi":"https://doi.org/10.1109/pact.2017.39","mag":"2767203761"},"language":"en","primary_location":{"id":"doi:10.1109/pact.2017.39","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2017.39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 26th International Conference on Parallel Architectures and Compilation Techniques (PACT)","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/A5010094713","display_name":"Swagath Venkataramani","orcid":"https://orcid.org/0000-0002-0470-6364"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Swagath Venkataramani","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078440061","display_name":"Jungwook Choi","orcid":"https://orcid.org/0000-0002-3075-8694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungwook Choi","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784876","display_name":"Vijayalakshmi Srinivasan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vijayalakshmi Srinivasan","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101429456","display_name":"Kailash Gopalakrishnan","orcid":"https://orcid.org/0000-0002-8952-0875"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kailash Gopalakrishnan","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109942953","display_name":"Leland Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leland Chang","raw_affiliation_strings":["IBM T.J. Watson Research Center, NY"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010094713"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0923,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86498829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"147"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9990000128746033,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868685722351074},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6744809150695801},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6394412517547607},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6327623128890991},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6074175834655762},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5725684762001038},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5517282485961914},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5400067567825317},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5218062400817871},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5204660892486572},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5204063653945923},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4931170642375946},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.46801459789276123},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45894256234169006},{"id":"https://openalex.org/keywords/memory-architecture","display_name":"Memory architecture","score":0.43526729941368103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3603166937828064},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2626253366470337},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.23675191402435303},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1275216042995453},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10346230864524841},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1015719473361969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868685722351074},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6744809150695801},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6394412517547607},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6327623128890991},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6074175834655762},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5725684762001038},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5517282485961914},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5400067567825317},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5218062400817871},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5204660892486572},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5204063653945923},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4931170642375946},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.46801459789276123},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45894256234169006},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.43526729941368103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3603166937828064},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2626253366470337},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.23675191402435303},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1275216042995453},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10346230864524841},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1015719473361969},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pact.2017.39","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pact.2017.39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 26th International Conference on Parallel Architectures and Compilation Techniques (PACT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"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":7,"referenced_works":["https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W2442974303","https://openalex.org/W2626991402","https://openalex.org/W2962835968","https://openalex.org/W6635810480","https://openalex.org/W6637373629"],"related_works":["https://openalex.org/W4282568311","https://openalex.org/W4313484792","https://openalex.org/W2951473296","https://openalex.org/W2883928845","https://openalex.org/W4288420200","https://openalex.org/W2543610639","https://openalex.org/W3145095675","https://openalex.org/W4285818394","https://openalex.org/W4285346947","https://openalex.org/W2128337014"],"abstract_inverted_index":{"The":[0],"growing":[1],"prominence":[2],"and":[3,20,46,79,109,125,164],"computational":[4],"challenges":[5],"imposed":[6,142],"by":[7,143],"Deep":[8],"Neural":[9],"Networks":[10],"(DNNs)":[11],"has":[12],"fueled":[13],"the":[14,37,67,116,119,129,133,140,144,157,162],"design":[15,68],"of":[16,29,49,91,106,118,166],"specialized":[17],"accelerator":[18],"architectures":[19],"associated":[21],"dataflows":[22],"to":[23,58,64,72,123,128],"improve":[24],"their":[25],"implementation":[26],"efficiency.":[27],"Each":[28],"these":[30],"solutions":[31],"serve":[32],"as":[33,71],"a":[34,43,47,74,89,99,104,107,110],"datapoint":[35],"on":[36,82,127,169],"throughput":[38],"vs.":[39],"energy":[40],"trade-offs":[41,163],"for":[42,156],"given":[44,75,103],"DNN":[45,108,159],"set":[48,56],"architectural":[50],"constraints.":[51,172],"In":[52],"this":[53,94],"paper,":[54],"we":[55,96],"out":[57],"explore":[59,66],"whether":[60],"it":[61],"is":[62,136],"possible":[63],"systematically":[65],"space":[69],"so":[70],"estimate":[73],"DNN's":[76,120],"(both":[77],"inference":[78],"training)":[80],"performance":[81,135],"an":[83],"shared":[84],"memory":[85,148],"architecture":[86,130,171],"specification":[87],"using":[88],"variety":[90],"data-flows.":[92],"To":[93],"end,":[95],"have":[97],"developed":[98],"framework,":[100],"DEEPMATRIX,":[101],"which":[102],"description":[105],"hardware":[111,145],"architecture,":[112],"automatically":[113],"identifies":[114],"how":[115],"computations":[117],"layers":[121],"need":[122],"partitioned":[124],"mapped":[126],"such":[131],"that":[132],"overall":[134],"maximized,":[137],"while":[138],"meeting":[139],"constraints":[141],"(processing":[146],"power,":[147],"capacity,":[149],"bandwidth":[150],"etc.)":[151],"We":[152],"demonstrate":[153],"DEEPMATRIX's":[154],"effectiveness":[155],"VGG":[158],"benchmark,":[160],"showing":[161],"sensitivity":[165],"utilization":[167],"based":[168],"different":[170]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}