{"id":"https://openalex.org/W4396949640","doi":"https://doi.org/10.1109/isqed60706.2024.10528752","title":"Roofline Performance Analysis of DNN Architectures on CPU and GPU Systems","display_name":"Roofline Performance Analysis of DNN Architectures on CPU and GPU Systems","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4396949640","doi":"https://doi.org/10.1109/isqed60706.2024.10528752"},"language":"en","primary_location":{"id":"doi:10.1109/isqed60706.2024.10528752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed60706.2024.10528752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 25th International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5055771008","display_name":"H C Prashanth","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"H C Prashanth","raw_affiliation_strings":["International Institute of Information Technology Bangalore,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore,Bangalore,India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061397479","display_name":"Madhav Rao","orcid":"https://orcid.org/0000-0003-2278-9148"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Madhav Rao","raw_affiliation_strings":["IIIT-Bangalore,Bangalore,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Bangalore,Bangalore,India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":null,"apc_paid":null,"fwci":1.8056,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83618695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9983999729156494,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9944999814033508,"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":0.7623807191848755},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5132243633270264},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43886223435401917},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3805873990058899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623807191848755},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5132243633270264},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43886223435401917},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3805873990058899}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isqed60706.2024.10528752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isqed60706.2024.10528752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 25th International Symposium on Quality Electronic Design (ISQED)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1961751213","https://openalex.org/W2002555321","https://openalex.org/W2529487057","https://openalex.org/W2736230459","https://openalex.org/W2769815320","https://openalex.org/W2891241286","https://openalex.org/W2931743911","https://openalex.org/W3005411327","https://openalex.org/W3023649406","https://openalex.org/W3101558675","https://openalex.org/W3103041597","https://openalex.org/W3109468088","https://openalex.org/W3161088809","https://openalex.org/W3165698711","https://openalex.org/W4200140025","https://openalex.org/W4213312819","https://openalex.org/W4214677181","https://openalex.org/W4236601256","https://openalex.org/W4285203950","https://openalex.org/W4299974909","https://openalex.org/W4312297303","https://openalex.org/W4312383318","https://openalex.org/W4312705522","https://openalex.org/W4313484747","https://openalex.org/W4313496554","https://openalex.org/W4362690361","https://openalex.org/W6780793256"],"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/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"The":[0,32,55,88,116,155],"significance":[1],"of":[2,5,45,78,103,106,120,146,172,176],"prior":[3],"characterizations":[4],"Deep":[6],"Neural":[7],"Network":[8],"(DNN)":[9],"Architectures":[10],"on":[11,35,41,131,139,160],"CPU":[12,46,140],"and":[13,23,30,47,52,82,113],"GPU":[14,161],"is":[15],"likely":[16],"to":[17,74,94,129,182],"benefit":[18],"in":[19,61,101,152,167],"understanding":[20],"the":[21,27,63,68,75,79,86,104],"resources":[22],"timing":[24],"constraints":[25],"for":[26,67,125,150,169,184],"large-scale":[28],"adoption":[29],"deployment.":[31],"paper":[33],"focuses":[34],"43":[36],"popular":[37],"DNN":[38,156],"workloads":[39],"profiling":[40],"two":[42],"different":[43],"segments":[44],"GPUs,":[48],"each,":[49],"including":[50],"Workstation":[51,162],"mobile":[53],"class.":[54],"roof-line":[56],"performance":[57],"analysis":[58],"model":[59,80],"aids":[60],"picking":[62],"optimal":[64],"architectural":[65],"configurations":[66],"real-time":[69],"resource-constrained":[70],"design":[71],"with":[72],"respect":[73],"Arithmetic":[76],"Intensity":[77],"run":[81,130,159],"throughput":[83,118,147,168],"extracted":[84],"from":[85,92],"system.":[87],"selected":[89],"DNNs":[90,126],"ranging":[91],"MobileNet":[93],"VGGNet":[95],"models":[96,157],"showcase":[97],"a":[98],"wide":[99],"characteristics":[100],"terms":[102],"number":[105],"MAC":[107],"operations":[108],"per":[109],"inference,":[110],"data":[111],"movement,":[112],"parameter":[114],"size.":[115,154],"average":[117],"improvement":[119,145,166],"around":[121],"10\u00d7":[122],"was":[123,148],"reported":[124,149],"when":[127,158],"configured":[128],"48":[132],"multiple":[133],"threads":[134],"over":[135,174],"single":[136],"threaded":[137],"execution":[138],"Workstation,":[141],"but":[142],"no":[143],"direct":[144],"changes":[151,183],"batch":[153,170],"showed":[163],"98":[164],"\u00d7":[165],"size":[171,175],"16":[173],"1,":[177],"whereas":[178],"it":[179],"remains":[180],"insensitive":[181],"multi-threaded":[185],"execution.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}