{"id":"https://openalex.org/W2090943890","doi":"https://doi.org/10.1145/2503210.2503299","title":"Effective sampling-driven performance tools for GPU-accelerated supercomputers","display_name":"Effective sampling-driven performance tools for GPU-accelerated supercomputers","publication_year":2013,"publication_date":"2013-10-30","ids":{"openalex":"https://openalex.org/W2090943890","doi":"https://doi.org/10.1145/2503210.2503299","mag":"2090943890"},"language":"en","primary_location":{"id":"doi:10.1145/2503210.2503299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","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/A5055733971","display_name":"Milind Chabbi","orcid":"https://orcid.org/0000-0003-1021-7644"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Milind Chabbi","raw_affiliation_strings":["Rice University Houston,TX","Rice University (Houston, TX)"],"affiliations":[{"raw_affiliation_string":"Rice University Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University (Houston, TX)","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110949807","display_name":"Karthik Murthy","orcid":"https://orcid.org/0000-0002-6063-9653"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Murthy","raw_affiliation_strings":["Rice University Houston,TX","Rice University (Houston, TX)"],"affiliations":[{"raw_affiliation_string":"Rice University Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University (Houston, TX)","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072936498","display_name":"Michael Fagan","orcid":null},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Fagan","raw_affiliation_strings":["Rice University Houston,TX","Rice University (Houston, TX)"],"affiliations":[{"raw_affiliation_string":"Rice University Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University (Houston, TX)","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089709469","display_name":"John Mellor\u2010Crummey","orcid":"https://orcid.org/0000-0002-9026-5453"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Mellor-Crummey","raw_affiliation_strings":["Rice University Houston,TX","Rice University (Houston, TX)"],"affiliations":[{"raw_affiliation_string":"Rice University Houston,TX","institution_ids":["https://openalex.org/I74775410"]},{"raw_affiliation_string":"Rice University (Houston, TX)","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055733971"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":2.24628124,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90130244,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.998199999332428,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8799837827682495},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7284882664680481},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6245874166488647},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5962724685668945},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.595638632774353},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5562898516654968},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5406962633132935},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5043164491653442},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4553118944168091},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4202726483345032},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37113040685653687},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18765023350715637},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11717712879180908},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.10281050205230713},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.08915102481842041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8799837827682495},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7284882664680481},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6245874166488647},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5962724685668945},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.595638632774353},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5562898516654968},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5406962633132935},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5043164491653442},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4553118944168091},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4202726483345032},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37113040685653687},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18765023350715637},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11717712879180908},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.10281050205230713},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.08915102481842041},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2503210.2503299","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2503210.2503299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1948591071","https://openalex.org/W1969617278","https://openalex.org/W1987450723","https://openalex.org/W1988927353","https://openalex.org/W2005807845","https://openalex.org/W2019465613","https://openalex.org/W2024135699","https://openalex.org/W2024639384","https://openalex.org/W2068975988","https://openalex.org/W2099084006","https://openalex.org/W2101778912","https://openalex.org/W2117610793","https://openalex.org/W2122002474","https://openalex.org/W2122570236","https://openalex.org/W2142769604","https://openalex.org/W2148707178","https://openalex.org/W2150476673","https://openalex.org/W2152419477","https://openalex.org/W2153843289","https://openalex.org/W2168363974","https://openalex.org/W2470920449","https://openalex.org/W2521708680"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Performance":[0],"analysis":[1,27],"of":[2,44,76,88,91],"GPU-accelerated":[3,30],"systems":[4],"requires":[5],"a":[6,62,108,117,130],"system-wide":[7],"view":[8],"that":[9,133,140],"considers":[10],"both":[11],"CPU":[12],"and":[13,85,126],"GPU":[14,137],"components.":[15],"In":[16,57],"this":[17],"paper,":[18],"we":[19,59,97,106,115,128],"describe":[20],"how":[21],"to":[22,29,144],"extend":[23],"system-wide,":[24],"sampling-based":[25,52],"performance":[26,46,99,110,131],"methods":[28,53],"systems.":[31,71],"Since":[32],"current":[33],"GPUs":[34,50],"do":[35],"not":[36],"support":[37],"sampling,":[38],"our":[39,77,92],"implementation":[40],"required":[41],"careful":[42],"coordination":[43],"instrumentation-based":[45],"data":[47],"collection":[48],"on":[49,55,83,112],"with":[51,79],"employed":[54],"CPUs.":[56],"addition,":[58],"also":[60],"introduce":[61],"novel":[63],"technique":[64],"for":[65,100],"analyzing":[66],"systemic":[67],"idleness":[68],"in":[69,120],"CPU/GPU":[70],"We":[72],"demonstrate":[73],"the":[74,89],"effectiveness":[75],"techniques":[78],"application":[80],"case":[81,93],"studies":[82,94],"Titan":[84],"Keeneland.":[86],"Some":[87],"highlights":[90],"are:":[95],"1)":[96],"improved":[98],"LULESH":[101],"1.0":[102],"by":[103,136],"30%,":[104],"2)":[105],"identified":[107,116,129],"hardware":[109],"problem":[111,119,132],"Keeneland,":[113],"3)":[114],"scaling":[118],"LAMMPS":[121],"derived":[122],"from":[123],"CUDA":[124],"initialization,":[125],"4)":[127],"is":[134],"caused":[135],"synchronization":[138],"operations":[139],"suffer":[141],"delays":[142],"due":[143],"blocking":[145],"system":[146],"calls.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}