{"id":"https://openalex.org/W1965378199","doi":"https://doi.org/10.1109/hpcc.2012.69","title":"DMA-Assisted, Intranode Communication in GPU Accelerated Systems","display_name":"DMA-Assisted, Intranode Communication in GPU Accelerated Systems","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W1965378199","doi":"https://doi.org/10.1109/hpcc.2012.69","mag":"1965378199"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc.2012.69","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc.2012.69","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 14th International Conference on High Performance Computing and Communication &amp; 2012 IEEE 9th International Conference on Embedded Software and Systems","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/A5100999753","display_name":"Feng Ji","orcid":"https://orcid.org/0000-0002-2051-5453"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Feng Ji","raw_affiliation_strings":["Department of Computer Science, North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091417392","display_name":"Ashwin M. Aji","orcid":"https://orcid.org/0000-0002-5467-8357"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin M. Aji","raw_affiliation_strings":["Department of Computer Science, Virginia Tech Antenna Group, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech Antenna Group, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078425310","display_name":"James Dinan","orcid":"https://orcid.org/0000-0002-4840-7737"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Dinan","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034514540","display_name":"Darius Buntinas","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darius Buntinas","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050531633","display_name":"Pavan Balaji","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pavan Balaji","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014920685","display_name":"Rajeev Thakur","orcid":"https://orcid.org/0000-0002-5532-3048"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajeev Thakur","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Department of Computer Science, Virginia Tech Antenna Group, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech Antenna Group, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083800790","display_name":"Xiaosong Ma","orcid":"https://orcid.org/0000-0003-1261-2496"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]},{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaosong Ma","raw_affiliation_strings":["Computer Science and Mathematics Division, Oak Ridge National Laboratory, USA","Department of Computer Science, North Carolina State University, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Mathematics Division, Oak Ridge National Laboratory, USA","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100999753"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":2.3422,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87599493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"4192","issue":null,"first_page":"461","last_page":"468"},"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9902999997138977,"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":0.8652804493904114},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7122095227241516},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6931198835372925},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6243997812271118},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42808395624160767},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4109910726547241},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3521915674209595},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21933960914611816},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.17920154333114624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8652804493904114},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7122095227241516},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6931198835372925},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6243997812271118},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42808395624160767},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4109910726547241},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3521915674209595},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21933960914611816},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.17920154333114624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpcc.2012.69","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc.2012.69","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 14th International Conference on High Performance Computing and Communication &amp; 2012 IEEE 9th International Conference on Embedded Software and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.260.945","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.260.945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/%7Ethakur/papers/ji_hpcc12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320310013","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1500216316","https://openalex.org/W1964479544","https://openalex.org/W1969617278","https://openalex.org/W2040561634","https://openalex.org/W2070940137","https://openalex.org/W2109349370","https://openalex.org/W2109977639","https://openalex.org/W2110813866","https://openalex.org/W2113290275","https://openalex.org/W2121444153","https://openalex.org/W2127533540","https://openalex.org/W2133352850","https://openalex.org/W2149234156","https://openalex.org/W2155779395","https://openalex.org/W6668040661"],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2315600872","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2962978274"],"abstract_inverted_index":{"Accelerator":[0],"awareness":[1],"has":[2],"become":[3],"a":[4,70,85,108],"pressing":[5],"issue":[6],"in":[7],"data":[8,45,61],"movement":[9,62],"models,":[10],"such":[11],"as":[12],"MPI,":[13],"because":[14],"of":[15,19,88],"the":[16,66],"rapid":[17],"deployment":[18],"systems":[20],"that":[21,76],"utilize":[22],"accelerators.":[23],"In":[24,49],"our":[25,89],"previous":[26],"work,":[27],"we":[28,52],"developed":[29],"techniques":[30,57],"to":[31,40,58,92,99],"enhance":[32],"MPI":[33],"with":[34,56],"accelerator":[35,47],"awareness,":[36],"thus":[37],"allowing":[38],"applications":[39],"easily":[41],"and":[42,95,101,107],"efficiently":[43],"communicate":[44],"between":[46,63],"memories.":[48],"this":[50,54],"paper,":[51],"extend":[53],"work":[55],"perform":[59],"efficient":[60],"accelerators":[64],"within":[65],"same":[67],"node":[68],"using":[69,104],"DMA-assisted,":[71],"peer-to-peer":[72],"intranode":[73,93],"communication":[74,94,100],"technique":[75],"was":[77],"recently":[78],"introduced":[79],"for":[80],"NVIDIA":[81],"GPUs.":[82],"We":[83],"present":[84],"detailed":[86],"design":[87],"new":[90],"approach":[91],"evaluate":[96],"its":[97],"improvement":[98],"application":[102,111],"performance":[103],"micro-kernel":[105],"benchmarks":[106],"2D":[109],"stencil":[110],"kernel.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
