{"id":"https://openalex.org/W2052742013","doi":"https://doi.org/10.1109/hipc.2013.6799140","title":"A hybrid shared memory heterogeneous execution platform for PCIe-based GPGPUs","display_name":"A hybrid shared memory heterogeneous execution platform for PCIe-based GPGPUs","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2052742013","doi":"https://doi.org/10.1109/hipc.2013.6799140","mag":"2052742013"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2013.6799140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2013.6799140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th Annual International Conference on High Performance Computing","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/A5083023059","display_name":"Sambit K. Shukla","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sambit K. Shukla","raw_affiliation_strings":["Computer Science and Engineering, UC Riverside, Riverside, CA","Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, UC Riverside, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048949780","display_name":"Laxmi N. Bhuyan","orcid":"https://orcid.org/0000-0002-8759-0458"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laxmi N. Bhuyan","raw_affiliation_strings":["Computer Science and Engineering, UC Riverside, Riverside, CA","Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, UC Riverside, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Comput. Sci. & Eng., UC Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.1793,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.38484727,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"343","last_page":"352"},"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":0.9994000196456909,"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":0.9991999864578247,"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":0.894163966178894},{"id":"https://openalex.org/keywords/pci-express","display_name":"PCI Express","score":0.7940964698791504},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6994044184684753},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5558249354362488},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5303051471710205},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5117185115814209},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47561126947402954},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4509234130382538},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36028218269348145},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.29363110661506653},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.28315436840057373},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1120789647102356},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.10542252659797668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.894163966178894},{"id":"https://openalex.org/C64270927","wikidata":"https://www.wikidata.org/wiki/Q206924","display_name":"PCI Express","level":3,"score":0.7940964698791504},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6994044184684753},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5558249354362488},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5303051471710205},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5117185115814209},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47561126947402954},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4509234130382538},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36028218269348145},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29363110661506653},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.28315436840057373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1120789647102356},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.10542252659797668},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2013.6799140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2013.6799140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th Annual International Conference on High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1552041766","https://openalex.org/W1651324627","https://openalex.org/W1992720840","https://openalex.org/W2007432529","https://openalex.org/W2058144256","https://openalex.org/W2095894588","https://openalex.org/W2098278566","https://openalex.org/W2104677829","https://openalex.org/W2109426995","https://openalex.org/W2121758805","https://openalex.org/W2135518093","https://openalex.org/W2147900461","https://openalex.org/W2149340725","https://openalex.org/W2149950425","https://openalex.org/W4232145753","https://openalex.org/W4240262711","https://openalex.org/W4252178669","https://openalex.org/W6633102822","https://openalex.org/W6636916521"],"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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"The":[0,21],"disparity":[1],"between":[2,70],"the":[3,10,15,52,55,71,97,114],"CPU":[4,36],"and":[5,35,74,86,125],"GPU":[6,18,63,78,92,98,116],"domains":[7],"has":[8],"forced":[9],"programmers":[11],"to":[12,14,50,88],"adhere":[13],"traditional":[16,75,115],"driver-based":[17],"programming":[19,79,117],"approach.":[20,80],"negative":[22],"implications":[23],"of":[24,54],"this":[25,39],"approach":[26,49,69],"are":[27],"inter-domain":[28],"data":[29],"transfer":[30],"overhead,":[31],"host":[32],"memory":[33,73,77,102],"pressure":[34],"underutilization.":[37],"In":[38],"paper,":[40],"we":[41,65],"propose":[42],"a":[43,67,100],"novel":[44],"hybrid":[45],"shared":[46,72,101],"memory-based":[47],"execution":[48,103,122],"enhance":[51],"throughput":[53],"General":[56],"Purpose":[57],"GPU(GPGPU)":[58],"applications.":[59],"To":[60],"achive":[61],"optimal":[62],"execution,":[64],"adopted":[66],"midway":[68],"disjoint":[76],"Our":[81,105],"design":[82,106],"involves":[83],"OS":[84],"enhancements":[85],"extensions":[87],"an":[89],"OS-integrated":[90],"open-source":[91],"driver(GDev)":[93],"which":[94],"together":[95],"provide":[96],"application":[99],"platform.":[104],"not":[107],"only":[108],"eliminates":[109],"several":[110],"drawbacks":[111],"associated":[112],"with":[113],"approach,":[118],"but":[119],"allows":[120],"data-parallel":[121],"across":[123],"CPUs":[124],"GPU.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}