{"id":"https://openalex.org/W2417175077","doi":"https://doi.org/10.1109/ispass.2016.7482092","title":"GSI: A GPU Stall Inspector to characterize the sources of memory stalls for tightly coupled GPUs","display_name":"GSI: A GPU Stall Inspector to characterize the sources of memory stalls for tightly coupled GPUs","publication_year":2016,"publication_date":"2016-04-01","ids":{"openalex":"https://openalex.org/W2417175077","doi":"https://doi.org/10.1109/ispass.2016.7482092","mag":"2417175077"},"language":"en","primary_location":{"id":"doi:10.1109/ispass.2016.7482092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ideals.illinois.edu/items/92938/bitstreams/302731/data.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075312447","display_name":"Johnathan Alsop","orcid":"https://orcid.org/0000-0001-5272-2396"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Johnathan Alsop","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047054160","display_name":"Matthew D. Sinclair","orcid":"https://orcid.org/0000-0003-0189-7895"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew D. Sinclair","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002281059","display_name":"Rakesh Komuravelli","orcid":"https://orcid.org/0009-0009-0996-3907"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rakesh Komuravelli","raw_affiliation_strings":["Qualcomm Technologies, Inc"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies, Inc","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086111967","display_name":"Sarita V. Adve","orcid":"https://orcid.org/0000-0002-3403-5119"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarita V. Adve","raw_affiliation_strings":["University of Illinois, Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075312447"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.2799,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.78518114,"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":"172","last_page":"182"},"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":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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":0.8724563121795654},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7141076922416687},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5701550841331482},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5050624012947083},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.47162437438964844},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4614499807357788},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4572365880012512},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.45232635736465454},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.42077741026878357},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39782875776290894},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3332340717315674},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21851283311843872},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.12222272157669067},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.11810794472694397},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.07525530457496643}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8724563121795654},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7141076922416687},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5701550841331482},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5050624012947083},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.47162437438964844},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4614499807357788},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4572365880012512},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45232635736465454},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.42077741026878357},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39782875776290894},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3332340717315674},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21851283311843872},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.12222272157669067},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.11810794472694397},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.07525530457496643},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ispass.2016.7482092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispass.2016.7482092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.ideals.illinois.edu:2142/90587","is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/90587","pdf_url":"https://www.ideals.illinois.edu/items/92938/bitstreams/302731/data.pdf","source":{"id":"https://openalex.org/S4377196349","display_name":"IDEALS (University of Illinois Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157725225","host_organization_name":"University of Illinois Urbana-Champaign","host_organization_lineage":["https://openalex.org/I157725225"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/90587","is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/90587","pdf_url":"https://www.ideals.illinois.edu/items/92938/bitstreams/302731/data.pdf","source":{"id":"https://openalex.org/S4377196349","display_name":"IDEALS (University of Illinois Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157725225","host_organization_name":"University of Illinois Urbana-Champaign","host_organization_lineage":["https://openalex.org/I157725225"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2417175077.pdf","grobid_xml":"https://content.openalex.org/works/W2417175077.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1807294333","https://openalex.org/W1897254069","https://openalex.org/W1966668827","https://openalex.org/W1978155891","https://openalex.org/W1979527452","https://openalex.org/W1985807728","https://openalex.org/W1997162567","https://openalex.org/W1997576530","https://openalex.org/W2021211271","https://openalex.org/W2053776346","https://openalex.org/W2099912705","https://openalex.org/W2106562406","https://openalex.org/W2120635877","https://openalex.org/W2122901568","https://openalex.org/W2134101883","https://openalex.org/W2148032086","https://openalex.org/W2150618958","https://openalex.org/W2152390090","https://openalex.org/W2152956697","https://openalex.org/W2156355519","https://openalex.org/W2157225945","https://openalex.org/W2158551169","https://openalex.org/W2164264749","https://openalex.org/W2236227338","https://openalex.org/W2417350949","https://openalex.org/W4229517165","https://openalex.org/W4241027159","https://openalex.org/W4242019954","https://openalex.org/W6639801777"],"related_works":["https://openalex.org/W2482815832","https://openalex.org/W2294358097","https://openalex.org/W1993191611","https://openalex.org/W2189498595","https://openalex.org/W1999755551","https://openalex.org/W2578331457","https://openalex.org/W4238392246","https://openalex.org/W1594092496","https://openalex.org/W2029518214","https://openalex.org/W3142189107"],"abstract_inverted_index":{"In":[0,145],"recent":[1,190],"years":[2],"the":[3,8,19,47,71,82,104,117,136,160,177,184],"power":[4],"wall":[5],"has":[6,16],"prevented":[7],"continued":[9],"scaling":[10],"of":[11,21,73,85,101,109,120,162,179,186],"single":[12],"core":[13],"performance.":[14],"This":[15],"lead":[17],"to":[18,50,69,93,99],"rise":[20],"dark":[22],"silicon":[23],"and":[24,30,53,158],"motivated":[25],"a":[26,33,154,166,169],"move":[27],"toward":[28],"parallelism":[29,121],"specialization.":[31],"As":[32],"result,":[34],"energy-efficient":[35],"high-throughput":[36],"GPU":[37,124,150,163],"cores":[38,57],"are":[39,88],"increasingly":[40],"favored":[41],"for":[42,80,156,193],"accelerating":[43],"data-parallel":[44],"applications.":[45],"However,":[46],"best":[48],"way":[49],"efficiently":[51],"communicate":[52],"synchronize":[54],"across":[55],"heterogeneous":[56,74,196],"remains":[58],"an":[59],"important":[60],"open":[61],"research":[62],"question.":[63],"Many":[64],"methods":[65,79],"have":[66],"been":[67],"proposed":[68],"improve":[70],"efficiency":[72],"memory":[75,105,138,173],"systems,":[76],"but":[77],"current":[78],"evaluating":[81,183],"performance":[83,143],"effects":[84],"these":[86],"innovations":[87,192],"limited":[89],"in":[90,96,103,123,188],"their":[91],"ability":[92],"attribute":[94],"differences":[95],"execution":[97],"time":[98],"sources":[100,185],"latency":[102],"system.":[106],"Performance":[107],"characterization":[108],"tightly":[110,170,194],"coupled":[111,171],"CPU-GPU":[112,172,197],"systems":[113],"is":[114],"complicated":[115],"by":[116,182],"high":[118],"levels":[119],"present":[122],"codes.":[125],"Existing":[126],"simulation":[127],"tools":[128],"provide":[129],"only":[130],"coarse-grained":[131],"metrics":[132],"which":[133],"can":[134],"obscure":[135],"underlying":[137],"system":[139],"interactions":[140],"that":[141],"cause":[142],"differences.":[144],"this":[146],"work":[147],"we":[148],"introduce":[149],"Stall":[151],"Inspector":[152],"(GSI),":[153],"method":[155],"identifying":[157],"visualizing":[159],"causes":[161],"stalls":[164,187],"with":[165],"focus":[167],"on":[168],"subsystem.":[174],"We":[175],"demonstrate":[176],"utility":[178],"our":[180],"approach":[181],"several":[189],"architectural":[191],"coupled,":[195],"systems.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}