{"id":"https://openalex.org/W4284960562","doi":"https://doi.org/10.1109/compsac54236.2022.00019","title":"LIBNVCD: An Extendable and User-friendly Multi-GPU Performance Measurement Tool","display_name":"LIBNVCD: An Extendable and User-friendly Multi-GPU Performance Measurement Tool","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4284960562","doi":"https://doi.org/10.1109/compsac54236.2022.00019"},"language":"en","primary_location":{"id":"doi:10.1109/compsac54236.2022.00019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsac54236.2022.00019","pdf_url":null,"source":{"id":"https://openalex.org/S4363607883","display_name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1874871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109864509","display_name":"Holland Schutte","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159485","display_name":"Museum of Modern Art","ror":"https://ror.org/05d6hsa78","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210159485"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Holland Schutte","raw_affiliation_strings":["Modern Mirror, Inc.,New York City,USA","Modern Mirror, Inc., New York City, USA"],"affiliations":[{"raw_affiliation_string":"Modern Mirror, Inc.,New York City,USA","institution_ids":["https://openalex.org/I4210159485"]},{"raw_affiliation_string":"Modern Mirror, Inc., New York City, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005889420","display_name":"Chase Phelps","orcid":"https://orcid.org/0000-0003-1480-0917"},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chase Phelps","raw_affiliation_strings":["Texas State University,San Marcos,USA","Texas State University, San Marcos, USA"],"affiliations":[{"raw_affiliation_string":"Texas State University,San Marcos,USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Texas State University, San Marcos, USA","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070686608","display_name":"Aniruddha Marathe","orcid":"https://orcid.org/0000-0003-0546-4472"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aniruddha Marathe","raw_affiliation_strings":["Lawrence Livermore National Laboratory,Livermore,USA","Lawrence Livermore National Laboratory, Livermore, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory,Livermore,USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002465410","display_name":"Tanzima Islam","orcid":"https://orcid.org/0000-0003-2877-5871"},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanzima Islam","raw_affiliation_strings":["Texas State University,San Marcos,USA","Texas State University, San Marcos, USA"],"affiliations":[{"raw_affiliation_string":"Texas State University,San Marcos,USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Texas State University, San Marcos, USA","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109864509"],"corresponding_institution_ids":["https://openalex.org/I4210159485"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06526104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":null,"first_page":"73","last_page":"82"},"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/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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.836669921875},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.7876726388931274},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5967144966125488},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5820289850234985},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.51947420835495},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4324093163013458},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3797260522842407},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3744533360004425},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.31821197271347046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836669921875},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7876726388931274},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5967144966125488},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5820289850234985},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.51947420835495},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4324093163013458},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3797260522842407},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3744533360004425},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.31821197271347046},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/compsac54236.2022.00019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/compsac54236.2022.00019","pdf_url":null,"source":{"id":"https://openalex.org/S4363607883","display_name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1874871","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1874871","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1874871","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1874871","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310830","display_name":"Texas State University","ror":"https://ror.org/009ey6w22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W77419049","https://openalex.org/W83535271","https://openalex.org/W114182254","https://openalex.org/W135467536","https://openalex.org/W1515668834","https://openalex.org/W1540325530","https://openalex.org/W1545880915","https://openalex.org/W1585237817","https://openalex.org/W1817277597","https://openalex.org/W1977263182","https://openalex.org/W1984222112","https://openalex.org/W2025768430","https://openalex.org/W2101778912","https://openalex.org/W2136434791","https://openalex.org/W2163398148","https://openalex.org/W2163922914","https://openalex.org/W2340816002","https://openalex.org/W2415594836","https://openalex.org/W2482121505","https://openalex.org/W2580107250","https://openalex.org/W2739664450","https://openalex.org/W2796649226","https://openalex.org/W2885585355","https://openalex.org/W2907701003","https://openalex.org/W2949081621","https://openalex.org/W2977118937","https://openalex.org/W2983717258","https://openalex.org/W2999813256","https://openalex.org/W3020739840","https://openalex.org/W4238147959","https://openalex.org/W4239537162","https://openalex.org/W4245072421","https://openalex.org/W4252521241","https://openalex.org/W4252637763","https://openalex.org/W6603139806","https://openalex.org/W6604617307","https://openalex.org/W6637493141","https://openalex.org/W6750448596","https://openalex.org/W6757794950","https://openalex.org/W6761146046"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W2327638088","https://openalex.org/W2068975988"],"abstract_inverted_index":{"Cost":[0],"and":[1,22,46,102,116,136,181],"power":[2],"efficiency":[3],"considerations":[4],"have":[5],"driven":[6],"High":[7],"Performance":[8],"Computing":[9],"(HPC)":[10],"system":[11],"design":[12],"inno-vations":[13],"in":[14,131],"accelerator-based":[15],"heterogeneous":[16,23],"computing.":[17],"Complex":[18],"interactions":[19],"between":[20],"applications":[21],"hardware":[24],"make":[25],"it":[26,88],"difficult":[27],"for":[28,49,58],"users":[29],"to":[30,71,112,179],"extract":[31],"maximum":[32],"performance":[33,44,74,94,114,143,166],"out":[34],"of":[35,43,93,110,118,138,173],"these":[36],"systems.":[37],"While":[38,76],"there":[39],"is":[40,54],"a":[41,99,170],"plethora":[42],"measurement":[45,115,167],"analysis":[47,117],"tools":[48,61],"CPU":[50],"s,":[51],"the":[52,56],"same":[53],"not":[55,90],"case":[57],"GPUs.":[59,120],"Existing":[60],"either":[62],"provide":[63,91],"too":[64],"high-level":[65],"information":[66],"or":[67],"are":[68],"overly":[69],"complicated":[70],"setup,":[72],"impeding":[73],"profiling.":[75],"NVIDIA's":[77,86],"CUPTI":[78,111],"profiling":[79],"library":[80],"enables":[81],"basic":[82],"kernel-level":[83],"measurements":[84],"on":[85,108],"GPUs,":[87],"does":[89],"root-causes":[92],"slowdown.":[95],"This":[96,163],"paper":[97],"presents":[98],"low-overhead,":[100],"flexible,":[101],"user-friendly":[103,164],"tool,":[104],"LIBNV":[105,146],"CD,":[106],"built":[107],"top":[109],"simplify":[113],"NVIDIA":[119],"LIBNVCD":[121],"simplifies":[122],"obtaining":[123],"fine-grained":[124],"measurements,":[125],"requiring":[126],"only":[127],"three":[128],"function":[129],"calls":[130],"source,":[132],"while":[133],"masking":[134],"changes":[135],"complexities":[137],"CUPTI.":[139],"By":[140],"automatically":[141],"discovering":[142],"event":[144],"groups,":[145],"CD":[147],"reduces":[148],"data":[149],"collection":[150],"overhead":[151,172],"significantly":[152],"as":[153,177],"many":[154],"events":[155],"(not":[156],"all)":[157],"can":[158],"be":[159],"measured":[160],"at":[161],"once.":[162],"multi-GPU":[165],"tool":[168],"incurs":[169],"mean":[171],"less":[174],"than":[175],"1%":[176],"compared":[178],"CUPTI,":[180],"has":[182],"been":[183],"released":[184],"publicly.":[185]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}