{"id":"https://openalex.org/W2015228575","doi":"https://doi.org/10.1109/ispass.2015.7095801","title":"On latency in GPU throughput microarchitectures","display_name":"On latency in GPU throughput microarchitectures","publication_year":2015,"publication_date":"2015-03-01","ids":{"openalex":"https://openalex.org/W2015228575","doi":"https://doi.org/10.1109/ispass.2015.7095801","mag":"2015228575"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2015.7095801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2015.7095801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","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/A5008915989","display_name":"Michael Andersch","orcid":"https://orcid.org/0009-0004-5778-4480"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Andersch","raw_affiliation_strings":["Technische Universit\u00e4t, Berlin","Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t, Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110305136","display_name":"Jan Lucas","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Lucas","raw_affiliation_strings":["Technische Universit\u00e4t, Berlin","Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t, Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096779769","display_name":"Mauricio A. LvLvarez-Mesa","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mauricio A. LvLvarez-Mesa","raw_affiliation_strings":["Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112321355","display_name":"Ben Juurlink","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ben Juurlink","raw_affiliation_strings":["Technische Universit\u00e4t, Berlin","Technische Universitat Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t, Berlin","institution_ids":["https://openalex.org/I4577782"]},{"raw_affiliation_string":"Technische Universitat Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":0.8164,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.67721766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9991000294685364,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9979000091552734,"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":0.8231539726257324},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.8119096159934998},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.7547803521156311},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6839163303375244},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.6054234504699707},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.4930214583873749},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4668598473072052},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43470245599746704},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.4185031056404114},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18870535492897034},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09207069873809814},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.07313734292984009},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.06832268834114075},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.058525919914245605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231539726257324},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.8119096159934998},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.7547803521156311},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6839163303375244},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.6054234504699707},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.4930214583873749},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4668598473072052},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43470245599746704},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.4185031056404114},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18870535492897034},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09207069873809814},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.07313734292984009},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.06832268834114075},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.058525919914245605},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ispass.2015.7095801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2015.7095801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.14279/depositonce-6884","is_oa":false,"landing_page_url":"https://depositonce.tu-berlin.de/handle/11303/7706","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2067354926","https://openalex.org/W2110195531"],"related_works":["https://openalex.org/W2161462353","https://openalex.org/W2047588290","https://openalex.org/W4296337698","https://openalex.org/W1997955449","https://openalex.org/W2965967938","https://openalex.org/W2382239615","https://openalex.org/W2170268965","https://openalex.org/W2735291995","https://openalex.org/W4285503988","https://openalex.org/W2015228575"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1,95],"provide":[2],"massive":[3],"processing":[4],"power":[5],"(arithmetic":[6],"throughput)":[7],"as":[8,10,80,82,98,103],"well":[9,19,81],"memory":[11],"throughput.":[12,122],"Presently,":[13],"while":[14],"it":[15,29],"appears":[16],"to":[17,70],"be":[18,24,116],"understood":[20],"how":[21],"performance":[22,42,58],"can":[23],"improved":[25],"by":[26,74],"increasing":[27],"throughput,":[28],"is":[30,50],"less":[31],"clear":[32],"what":[33],"the":[34,41,54,77],"effects":[35],"of":[36,43,60,87],"micro-architectural":[37],"latencies":[38],"are":[39,96],"on":[40,108],"throughput-oriented":[44],"GPU":[45,88,118],"architectures.":[46],"In":[47],"fact,":[48],"little":[49],"publicly":[51],"known":[52],"about":[53],"values,":[55],"behavior,":[56],"and":[57,106],"impact":[59],"microarchitecture":[61],"latency":[62,85,101,113],"components":[63],"in":[64,100],"modern":[65],"GPUs.":[66],"This":[67],"work":[68],"attempts":[69],"fill":[71],"that":[72,94,112],"gap":[73],"analyzing":[75],"both":[76],"idle":[78],"(static)":[79],"loaded":[83],"(dynamic)":[84],"behavior":[86],"microarchitectural":[89],"components.":[90],"Our":[91],"results":[92],"show":[93],"not":[97],"effective":[99],"hiding":[102],"commonly":[104],"thought":[105],"based":[107],"that,":[109],"we":[110],"argue":[111],"should":[114],"also":[115],"a":[117],"design":[119],"consideration":[120],"besides":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}