{"id":"https://openalex.org/W2944027133","doi":"https://doi.org/10.1109/hpec.2019.8916463","title":"Deep-Learning Inferencing with High-Performance Hardware Accelerators","display_name":"Deep-Learning Inferencing with High-Performance Hardware Accelerators","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2944027133","doi":"https://doi.org/10.1109/hpec.2019.8916463","mag":"2944027133"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5050164067","display_name":"Luke Kljucaric","orcid":"https://orcid.org/0000-0001-6793-3524"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luke Kljucaric","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Pittsburgh NSF Center for Space, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Pittsburgh NSF Center for Space, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082898376","display_name":"Alan D. George","orcid":"https://orcid.org/0000-0001-9665-2879"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan D. George","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Pittsburgh NSF Center for Space, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Pittsburgh NSF Center for Space, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5050164067"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":0.4089,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.64494159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9968000054359436,"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":0.8295544385910034},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8217195272445679},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5336198806762695},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5011270046234131},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4813278913497925},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4242097735404968},{"id":"https://openalex.org/keywords/pascal","display_name":"Pascal (unit)","score":0.41821327805519104},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41063281893730164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4046618342399597},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3602595627307892},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.27324455976486206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295544385910034},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8217195272445679},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5336198806762695},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5011270046234131},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4813278913497925},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4242097735404968},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.41821327805519104},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41063281893730164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4046618342399597},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3602595627307892},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.27324455976486206},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec.2019.8916463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:d-scholarship.pitt.edu:35658","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402372","display_name":"D-Scholarship@Pitt (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1555915743","https://openalex.org/W1968422655","https://openalex.org/W1990315422","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2119305530","https://openalex.org/W2150341604","https://openalex.org/W2154991996","https://openalex.org/W2155893237","https://openalex.org/W2156387975","https://openalex.org/W2161663128","https://openalex.org/W2163605009","https://openalex.org/W2170866695","https://openalex.org/W2272300165","https://openalex.org/W2587969154","https://openalex.org/W2962987932","https://openalex.org/W3016900429","https://openalex.org/W4205947740","https://openalex.org/W6682889407","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2493838176","https://openalex.org/W4297686120","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W4225949190","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W1967938402"],"abstract_inverted_index":{"In":[0],"order":[1,31],"to":[2,14,32,94,102,167,187,229,255],"improve":[3],"their":[4],"performance-per-watt":[5],"capabilities":[6],"over":[7,69,172,201],"general-purpose":[8],"architectures,":[9],"FPGAs":[10,43,68,133,185],"are":[11,86],"commonly":[12,112],"employed":[13],"accelerate":[15],"applications.":[16],"With":[17],"the":[18,61,104,148,169,202,210,214,221,224,231,253],"exponential":[19],"growth":[20],"of":[21,63,106,150,261],"available":[22,47,182,205],"data,":[23],"machine-learning":[24,65,90],"apps":[25,66],"have":[26,92,165,168,188,252],"generated":[27],"greater":[28,218],"interest":[29],"in":[30,88,176,259],"more":[33,45],"comprehensively":[34],"understand":[35],"that":[36],"data":[37],"and":[38,75,116,131,134,139,157,193,197,237,242,250,263],"increase":[39],"autonomous":[40],"processing.":[41],"As":[42],"become":[44],"readily":[46],"on":[48,67,110,129,143,213],"cloud":[49],"services":[50],"like":[51,73],"Amazon":[52],"Web":[53],"Services":[54],"F1":[55],"platform,":[56,147],"it":[57],"is":[58,123],"worth":[59],"studying":[60],"performance":[62,105,171,196,262],"accelerating":[64,80],"traditional":[70],"fixed-logic":[71],"devices,":[72],"CPUs":[74],"GPUs.":[76],"FPGA":[77,127,248],"frameworks":[78,109,128,249],"for":[79,96,153,183,206,240],"convolutional":[81],"neural":[82],"networks":[83],"(CNN),":[84],"which":[85],"used":[87,113],"many":[89],"apps,":[91],"begun":[93],"emerge":[95],"accelerated-application":[97],"development.":[98],"This":[99],"research":[100],"aims":[101],"compare":[103],"these":[107],"forthcoming":[108],"two":[111],"CNNs,":[114],"GoogLeNet":[115],"AlexNet.":[117],"Specifically,":[118],"handwritten":[119],"Chinese":[120],"character":[121],"recognition":[122],"benchmarked":[124],"across":[125],"multiple":[126,137],"Xilinx":[130,184,215],"Intel":[132,207],"compared":[135],"against":[136],"CPU":[138],"GPU":[140],"architectures":[141],"featured":[142],"AWS,":[144],"Google's":[145],"Cloud":[146],"University":[149],"Pittsburgh's":[151],"Center":[152],"Research":[154],"Computing":[155],"(CRC),":[156],"Intel's":[158],"vLab":[159],"Academic":[160],"Cluster.":[161],"All":[162],"NVIDIA":[163,225],"GPUs":[164,258],"proven":[166],"best":[170],"every":[173],"other":[174],"device":[175,234],"this":[177],"study.":[178],"The":[179],"Zebra":[180,211],"framework":[181,204,212],"showed":[186,217],"an":[189],"average":[190],"8.3":[191],"times":[192,195],"9.3":[194],"efficiency":[198,219],"improvement,":[199],"respectively,":[200],"OpenVINO":[203],"FPGAs.":[208],"Although":[209,245],"VU9P":[216],"than":[220],"Pascal-based":[222],"GPUs,":[223],"Tesla":[226],"V100":[227],"proved":[228],"be":[230],"most":[232],"efficient":[233],"at":[235],"125.9":[236],"47.2":[238],"images-per-second-per-Watt":[239],"AlexNet":[241],"GoogLeNet,":[243],"respectively.":[244],"currently":[246],"lacking,":[247],"devices":[251],"potential":[254],"compete":[256],"with":[257],"terms":[260],"efficiency.":[264]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}