{"id":"https://openalex.org/W2557691017","doi":"https://doi.org/10.1109/hpec.2016.7761602","title":"Computational and memory analysis of Tegra SoCs","display_name":"Computational and memory analysis of Tegra SoCs","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2557691017","doi":"https://doi.org/10.1109/hpec.2016.7761602","mag":"2557691017"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2016.7761602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2016.7761602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5069616484","display_name":"Andrew Milluzzi","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Andrew Milluzzi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082898376","display_name":"Alan D. George","orcid":"https://orcid.org/0000-0001-9665-2879"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan George","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020976710","display_name":"Herman Lam","orcid":"https://orcid.org/0000-0002-2388-0819"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herman Lam","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, Florida","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069616484"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.3153,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59685913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9997000098228455,"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/flops","display_name":"FLOPS","score":0.788372278213501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7829763889312744},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6941925287246704},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.6219800710678101},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5600883960723877},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5533362627029419},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5240935683250427},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4313570261001587},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4279968738555908},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.4216250777244568},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35266387462615967}],"concepts":[{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.788372278213501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829763889312744},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6941925287246704},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.6219800710678101},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5600883960723877},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5533362627029419},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5240935683250427},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4313570261001587},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4279968738555908},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.4216250777244568},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35266387462615967},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2016.7761602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2016.7761602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1503498281","https://openalex.org/W2001718517","https://openalex.org/W2018353373","https://openalex.org/W2042859117","https://openalex.org/W2048959408","https://openalex.org/W2063750261","https://openalex.org/W2076186064","https://openalex.org/W2125746594"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1855765675","https://openalex.org/W3046859795","https://openalex.org/W1505902692","https://openalex.org/W111037196","https://openalex.org/W2887888236","https://openalex.org/W1555620806"],"abstract_inverted_index":{"Low-power,":[0],"embedded,":[1],"GPU":[2],"System-on-Chip":[3],"(SoC)":[4],"devices":[5,63,197],"provide":[6,65,120],"outstanding":[7],"computational":[8,27,159],"performance,":[9],"especially":[10],"for":[11,18,185,208],"compute-intensive":[12],"tasks.":[13],"While":[14],"clusters":[15],"of":[16,29,37,48,70,76,86,137,171,212],"SoCs":[17],"High-Performance":[19,41],"Embedded":[20],"Computing":[21,42],"(HPEC)":[22],"are":[23,154],"not":[24],"new,":[25],"the":[26,35,46,49,54,83,127,145,191],"power":[28,95],"these":[30],"supercomputers":[31],"has":[32],"long":[33],"lacked":[34],"efficiency":[36,55],"their":[38,92],"more":[39,59],"traditional,":[40],"(HPC)":[43],"counterparts.":[44],"With":[45],"advent":[47],"Tegra":[50,173,196],"K1":[51],"and":[52,90,94,114,124],"X1,":[53],"debate":[56],"is":[57,134],"significantly":[58],"complex.":[60],"These":[61],"new":[62],"can":[64],"up":[66],"to":[67,97,103,119,144,156],"500":[68],"GFLOPS":[69],"Float32":[71],"performance":[72,93,166,193],"with":[73,129],"a":[74,121,135,200,209],"TDP":[75],"just":[77],"10":[78],"Watts.":[79],"This":[80],"paper":[81],"investigates":[82],"current":[84],"state":[85],"NVIDIA":[87,99,172],"SoCs,":[88],"comparing":[89,140],"contrasting":[91],"characteristics":[96],"high-end":[98],"accelerators.":[100],"In":[101],"order":[102],"perform":[104],"this":[105,151],"analysis,":[106,152],"we":[107,153],"leverage":[108],"two":[109],"metrics,":[110],"Computational":[111],"Density":[112],"(CD)":[113],"External":[115],"Memory":[116],"Bandwidth":[117],"(EMB),":[118],"first-order":[122],"estimate":[123],"then":[125],"normalize":[126],"results":[128,143],"Realizable":[130],"Utilization":[131],"(RU).":[132],"RU":[133],"measurement":[136],"device":[138],"efficiency,":[139],"observed":[141,192],"benchmarking":[142],"theoretical":[146],"CD":[147],"or":[148,164],"EMB.":[149],"From":[150],"able":[155],"uncover":[157],"which":[158],"kernels":[160],"might":[161],"show":[162],"similar":[163],"improved":[165],"on":[167,176],"an":[168,179,206],"HPEC":[169],"cluster":[170,181,203],"SoCs.":[174],"Based":[175],"our":[177],"observations,":[178],"SoC":[180],"would":[182],"be":[183,205],"plausible":[184],"some":[186],"power-constrained":[187],"HPC":[188],"applications.":[189,213],"Furthermore,":[190],"improvement":[194],"in":[195],"suggests":[198],"that":[199],"future":[201],"GPU-SoC":[202],"could":[204],"option":[207],"wide":[210],"range":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}