{"id":"https://openalex.org/W2989919840","doi":"https://doi.org/10.1109/hpec.2019.8916330","title":"Overcoming Limitations of GPGPU-Computing in Scientific Applications","display_name":"Overcoming Limitations of GPGPU-Computing in Scientific Applications","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2989919840","doi":"https://doi.org/10.1109/hpec.2019.8916330","mag":"2989919840"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2019.8916330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5062475683","display_name":"Connor Kenyon","orcid":null},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Connor Kenyon","raw_affiliation_strings":["Department of Physics & Center for Scientific Computing, University of Massachusetts Dartmouth, Dartmouth, MA"],"affiliations":[{"raw_affiliation_string":"Department of Physics & Center for Scientific Computing, University of Massachusetts Dartmouth, Dartmouth, MA","institution_ids":["https://openalex.org/I100633361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039977911","display_name":"Glenn Volkema","orcid":null},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Glenn Volkema","raw_affiliation_strings":["Department of Physics & Center for Scientific Computing, University of Massachusetts Dartmouth, Dartmouth, MA"],"affiliations":[{"raw_affiliation_string":"Department of Physics & Center for Scientific Computing, University of Massachusetts Dartmouth, Dartmouth, MA","institution_ids":["https://openalex.org/I100633361"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050881945","display_name":"Gaurav Khanna","orcid":"https://orcid.org/0000-0002-2565-8170"},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Khanna","raw_affiliation_strings":["Department of Physics & Center for Scientific Computing, University of Massachusetts Dartmouth, Dartmouth, MA"],"affiliations":[{"raw_affiliation_string":"Department of Physics & Center for Scientific Computing, University of Massachusetts Dartmouth, Dartmouth, MA","institution_ids":["https://openalex.org/I100633361"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062475683"],"corresponding_institution_ids":["https://openalex.org/I100633361"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5183929,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9972000122070312,"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":0.9972000122070312,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9925000071525574,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9828000068664551,"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/pci-express","display_name":"PCI Express","score":0.9532560706138611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.869364857673645},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5337010025978088},{"id":"https://openalex.org/keywords/downtime","display_name":"Downtime","score":0.5230432748794556},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5158600211143494},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.5146509408950806},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5000801086425781},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.469906747341156},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44612637162208557},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4433019757270813},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4260701835155487},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4092911183834076},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.18296849727630615}],"concepts":[{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.9532560706138611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.869364857673645},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5337010025978088},{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.5230432748794556},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5158600211143494},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5146509408950806},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5000801086425781},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.469906747341156},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44612637162208557},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4433019757270813},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4260701835155487},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4092911183834076},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.18296849727630615},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2019.8916330","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2019.8916330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2128022558","https://openalex.org/W2766711359","https://openalex.org/W2835452357"],"related_works":["https://openalex.org/W2046276983","https://openalex.org/W2954002293","https://openalex.org/W2892741875","https://openalex.org/W2164372000","https://openalex.org/W2078264086","https://openalex.org/W2109143577","https://openalex.org/W1985537075","https://openalex.org/W2736680668","https://openalex.org/W2573457208","https://openalex.org/W2566887379"],"abstract_inverted_index":{"The":[0,17,80],"performance":[1,43,90],"of":[2,24,91],"discrete":[3],"general":[4],"purpose":[5],"graphics":[6],"processing":[7],"units":[8],"(GPGPUs)":[9],"has":[10,34],"been":[11],"improving":[12],"at":[13],"a":[14,40],"rapid":[15],"pace.":[16],"PCIe":[18,51,64],"interconnect":[19],"that":[20],"controls":[21],"the":[22,27,32,62,89],"communication":[23],"data":[25,52],"between":[26],"system":[28],"host":[29],"memory":[30,74],"and":[31,69],"GPU":[33,46],"not":[35],"improved":[36],"as":[37],"quickly,":[38],"leaving":[39],"gap":[41],"in":[42],"due":[44],"to":[45,61,87],"downtime":[47],"while":[48],"waiting":[49],"for":[50,72],"transfer.":[53],"In":[54],"this":[55],"article,":[56],"we":[57],"explore":[58],"two":[59],"alternatives":[60],"limited":[63],"bandwidth,":[65],"NVIDIA":[66],"NVLink":[67],"interconnect,":[68],"zero-copy":[70],"algorithms":[71],"shared":[73],"Heterogeneous":[75],"System":[76],"Architecture":[77],"(HSA)":[78],"devices.":[79],"OpenCL":[81],"SHOC":[82],"benchmark":[83],"suite":[84],"is":[85],"used":[86],"measure":[88],"each":[92],"device":[93],"on":[94],"various":[95],"scientific":[96],"application":[97],"kernels.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}