{"id":"https://openalex.org/W4405361869","doi":"https://doi.org/10.1109/mascots64422.2024.10786578","title":"Fast and Accurate DNN Performance Estimation across Diverse Hardware Platforms","display_name":"Fast and Accurate DNN Performance Estimation across Diverse Hardware Platforms","publication_year":2024,"publication_date":"2024-10-21","ids":{"openalex":"https://openalex.org/W4405361869","doi":"https://doi.org/10.1109/mascots64422.2024.10786578"},"language":"en","primary_location":{"id":"doi:10.1109/mascots64422.2024.10786578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots64422.2024.10786578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","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/A5115428791","display_name":"Vishwas Vasudeva Kakrannaya","orcid":null},"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":true,"raw_author_name":"Vishwas Vasudeva Kakrannaya","raw_affiliation_strings":["Pennsylvania State University University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047931040","display_name":"Siddhartha Balakrishna","orcid":null},"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":"Siddhartha Balakrishna Rai","raw_affiliation_strings":["Pennsylvania State University University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033253809","display_name":"Anand Sivasubramaniam","orcid":"https://orcid.org/0000-0001-6173-687X"},"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":"Anand Sivasubramaniam","raw_affiliation_strings":["Pennsylvania State University University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024530225","display_name":"Timothy Zhu","orcid":"https://orcid.org/0000-0001-8394-8953"},"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":"Timothy Zhu","raw_affiliation_strings":["Pennsylvania State University University Park,PA,USA"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University University Park,PA,USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5115428791"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20163519,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":0.9735999703407288,"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":0.7672595977783203},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.49546539783477783},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.42012277245521545},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4054126441478729},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3722212612628937},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.357566237449646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3294844329357147},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32190096378326416},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08354359865188599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672595977783203},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.49546539783477783},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42012277245521545},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4054126441478729},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3722212612628937},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.357566237449646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294844329357147},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32190096378326416},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08354359865188599},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mascots64422.2024.10786578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mascots64422.2024.10786578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2155893237","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2612076670","https://openalex.org/W2618530766","https://openalex.org/W2903557836","https://openalex.org/W2904180680","https://openalex.org/W2963037989","https://openalex.org/W2964330541","https://openalex.org/W3015963989","https://openalex.org/W3102175148","https://openalex.org/W3106910749","https://openalex.org/W3135013702","https://openalex.org/W3159576817","https://openalex.org/W3181228931","https://openalex.org/W4252743600","https://openalex.org/W4281644153","https://openalex.org/W4282970339","https://openalex.org/W4383899655","https://openalex.org/W6638020065","https://openalex.org/W6744307745","https://openalex.org/W6758823024","https://openalex.org/W6766978945","https://openalex.org/W6839440523","https://openalex.org/W6845644974"],"related_works":["https://openalex.org/W2576994247","https://openalex.org/W2608353378","https://openalex.org/W4249206767","https://openalex.org/W2563559453","https://openalex.org/W2382330008","https://openalex.org/W1519970947","https://openalex.org/W4243860260","https://openalex.org/W4383503847","https://openalex.org/W2342695897","https://openalex.org/W2216265843"],"abstract_inverted_index":{"Performance":[0],"modeling":[1],"is":[2,64,96,107],"an":[3,72],"important":[4],"tool":[5],"for":[6,29,33],"many":[7,121],"purposes":[8],"such":[9],"as":[10],"designing":[11],"hardware":[12,94,124],"accelerators,":[13],"improving":[14],"scheduling,":[15],"optimizing":[16],"system":[17],"parameters,":[18],"procuring":[19],"new":[20,27],"hardware,":[21,50,62,92],"etc.":[22],"This":[23],"paper":[24],"provides":[25],"a":[26,38,111,130],"methodology":[28],"constructing":[30],"performance":[31,89],"models":[32],"Deep":[34],"Neural":[35],"Networks":[36],"(DNNs),":[37],"popular":[39],"machine":[40],"learning":[41],"workload.":[42],"Prior":[43],"works":[44],"require":[45],"running":[46],"DNNs":[47,122],"on":[48,60,76],"existing":[49],"which":[51,63,84],"may":[52],"not":[53,67],"be":[54],"available,":[55],"or":[56],"simulating":[57],"the":[58,78,98],"computation":[59],"futuristic":[61,131],"slow":[65],"and":[66,109,123,129],"scalable.":[68],"We":[69],"instead":[70],"take":[71],"analytical":[73],"approach":[74,106],"based":[75],"analyzing":[77],"raw":[79],"operations":[80],"within":[81],"DNN":[82],"algorithms,":[83],"allows":[85],"us":[86],"to":[87],"estimate":[88],"across":[90,120],"any":[91],"even":[93],"that":[95],"in":[97],"process":[99],"of":[100],"being":[101],"designed.":[102],"Evaluations":[103],"show":[104],"our":[105],"fast":[108],"gives":[110],"good":[112],"first":[113],"order":[114],"approximation":[115],"($\\pm":[116],"10-15":[117],"\\%$":[118],"accuracy)":[119],"platforms":[125],"including":[126],"GPUs,":[127],"CPUs,":[128],"Processing":[132],"In":[133],"Memory":[134],"(PIM)":[135],"accelerator":[136],"called":[137],"BLIMP.":[138]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}