{"id":"https://openalex.org/W2059816505","doi":"https://doi.org/10.1109/tpds.2014.2316825","title":"Runtime and Architecture Support for Efficient Data Exchange in Multi-Accelerator Applications","display_name":"Runtime and Architecture Support for Efficient Data Exchange in Multi-Accelerator Applications","publication_year":2014,"publication_date":"2014-04-22","ids":{"openalex":"https://openalex.org/W2059816505","doi":"https://doi.org/10.1109/tpds.2014.2316825","mag":"2059816505","pmid":"https://pubmed.ncbi.nlm.nih.gov/26180487"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2316825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2316825","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4500157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077201715","display_name":"Javier Cabezas","orcid":"https://orcid.org/0000-0003-3335-8036"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Cabezas","raw_affiliation_strings":["Department of Computer Science, Barcelona Supercomputing Center and with the Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","Department of Computer Science, Barcelona Supercomputing Center","Department of Computer Architecture, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Barcelona Supercomputing Center and with the Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Department of Computer Science, Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]},{"raw_affiliation_string":"Department of Computer Architecture, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034214277","display_name":"Isaac Gelado","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Gelado","raw_affiliation_strings":["NVIDIA Corporation at Santa Clara, California, United States","Research Department, NVIDIA Corporation at Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation at Santa Clara, California, United States","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"Research Department, NVIDIA Corporation at Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048680880","display_name":"John E. Stone","orcid":"https://orcid.org/0000-0001-7215-762X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John E. Stone","raw_affiliation_strings":["Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL, United States","Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL, United States","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute for Advanced Science and Technology, University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113528111","display_name":"Nacho Navarro","orcid":null},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nacho Navarro","raw_affiliation_strings":["Department of Computer Science, Barcelona Supercomputing Center and with the Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","Department of Computer Architecture, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","Department of Computer Science, Barcelona Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Barcelona Supercomputing Center and with the Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Department of Computer Architecture, Universitat Polit\u00e8cnica de Catalunya, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]},{"raw_affiliation_string":"Department of Computer Science, Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026418735","display_name":"David B. Kirk","orcid":"https://orcid.org/0000-0002-4887-5098"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David B. Kirk","raw_affiliation_strings":["NVIDIA Corporation at Santa Clara, California, United States","Research Department, NVIDIA Corporation at Santa Clara, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation at Santa Clara, California, United States","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"Research Department, NVIDIA Corporation at Santa Clara, CA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-mei Hwu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, United States","Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL, United States","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Urbana, IL","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9241,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75666168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"26","issue":"5","first_page":"1405","last_page":"1418"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998000264167786,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8939031362533569},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5545427799224854},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5167747735977173},{"id":"https://openalex.org/keywords/runtime-system","display_name":"Runtime system","score":0.46591877937316895},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4592125415802002},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42499521374702454},{"id":"https://openalex.org/keywords/maintainability","display_name":"Maintainability","score":0.4174971282482147},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.411064475774765},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4101925194263458},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36621272563934326},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3355996012687683},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2649743854999542},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14806389808654785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8939031362533569},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5545427799224854},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5167747735977173},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.46591877937316895},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4592125415802002},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42499521374702454},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.4174971282482147},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.411064475774765},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4101925194263458},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36621272563934326},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3355996012687683},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2649743854999542},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14806389808654785},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tpds.2014.2316825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2316825","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmid:26180487","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26180487","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on parallel and distributed systems : a publication of the IEEE Computer Society","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:4500157","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4500157","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Parallel Distrib Syst","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:4500157","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4500157","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Parallel Distrib Syst","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1104241873","display_name":null,"funder_award_id":"P41 GM104601","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G2228217462","display_name":null,"funder_award_id":"R01 GM098243","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G3773289342","display_name":null,"funder_award_id":"DE-FC02-10ER26004/DE-SC0005515","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4572022505","display_name":null,"funder_award_id":"2009-SGR-980","funder_id":"https://openalex.org/F4320321505","funder_display_name":"Generalitat de Catalunya"},{"id":"https://openalex.org/G696918205","display_name":null,"funder_award_id":"9P41GM104601","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320307769","display_name":"Astellas Pharma US","ror":"https://ror.org/05pw69n24"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320312065","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991"},{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1483880184","https://openalex.org/W1651324627","https://openalex.org/W1731318279","https://openalex.org/W1764493129","https://openalex.org/W2005818856","https://openalex.org/W2028499920","https://openalex.org/W2080592089","https://openalex.org/W2095894588","https://openalex.org/W2113190809","https://openalex.org/W2121893797","https://openalex.org/W2122960384","https://openalex.org/W2167510195","https://openalex.org/W3138798301","https://openalex.org/W4241790656","https://openalex.org/W6636916521","https://openalex.org/W6637719143","https://openalex.org/W6678379141"],"related_works":["https://openalex.org/W4236300446","https://openalex.org/W2226356789","https://openalex.org/W2143665235","https://openalex.org/W4312069186","https://openalex.org/W2085573357","https://openalex.org/W2031047992","https://openalex.org/W2094133266","https://openalex.org/W2806681060","https://openalex.org/W2165621019","https://openalex.org/W2561033805"],"abstract_inverted_index":{"Heterogeneous":[0],"parallel":[1,34],"computing":[2],"applications":[3,303],"often":[4],"process":[5],"large":[6],"data":[7,46,54,93,229],"sets":[8],"that":[9,125,179,210,293],"require":[10],"multiple":[11,42,56,95],"GPUs":[12,96],"to":[13,39,41,117,186,270,283,304],"jointly":[14],"meet":[15],"their":[16],"needs":[17],"for":[18,91,167,190,243,249,254,301],"physical":[19],"memory":[20],"capacity":[21],"and":[22,49,68,79,106,146,165,170,205,218,222,252],"compute":[23],"throughput.":[24],"However,":[25],"the":[26,75,80,126,161,192,195,227,238,267],"lack":[27],"of":[28,121,152,176,194,287],"high-level":[29],"abstractions":[30],"in":[31,61,110,136,140,149,211,310],"previous":[32],"heterogeneous":[33,214],"programming":[35,89,128,131],"models":[36],"force":[37],"programmers":[38],"resort":[40],"code":[43],"versions,":[44],"complex":[45],"copy":[47],"steps":[48],"synchronization":[50],"schemes":[51],"when":[52],"exchanging":[53,92],"between":[55,94],"GPU":[57,163],"devices,":[58],"which":[59,84],"results":[60,208],"high":[62],"software":[63,223],"development":[64],"cost,":[65],"poor":[66,70],"maintainability,":[67],"even":[69],"performance.":[71],"This":[72],"paper":[73,112,138],"describes":[74],"HPE":[76,153,182,268,298],"runtime":[77,105,154,204,269],"system,":[78,215],"associated":[81],"architecture":[82,107,264],"support,":[83],"enables":[85,266],"a":[86,187,212,244],"simple,":[87],"efficient":[88],"interface":[90,129],"through":[97],"either":[98],"interconnects":[99],"or":[100],"cross-node":[101],"network":[102],"interfaces.":[103],"The":[104,133,174,262],"support":[108,118,180,197,265],"presented":[109,135],"this":[111,137],"can":[113,225,235],"also":[114,236],"be":[115],"used":[116],"other":[119],"types":[120],"accelerators.":[122],"We":[123,290],"show":[124,209],"simplified":[127],"reduces":[130],"complexity.":[132],"research":[134],"started":[139],"2009.":[141],"It":[142],"has":[143],"been":[144],"implemented":[145],"tested":[147],"extensively":[148],"several":[150],"generations":[151],"systems":[155],"as":[156,158,297],"well":[157],"adopted":[159],"into":[160],"NVIDIA":[162],"hardware":[164,178,196,308],"drivers":[166],"CUDA":[168],"4.0":[169],"beyond":[171],"since":[172],"2011.":[173],"availability":[175],"real":[177,203,260],"key":[181],"features":[183,309],"gives":[184],"rise":[185],"rare":[188],"opportunity":[189],"studying":[191],"effectiveness":[193],"by":[198,232,241],"running":[199],"important":[200],"benchmarks":[201],"on":[202,259],"hardware.":[206,261],"Experimental":[207],"exemplar":[213],"peer":[216],"DMA":[217],"double-buffering,":[219],"pinned":[220],"buffers,":[221],"techniques":[224],"improve":[226,237],"inter-accelerator":[228],"communication":[230],"bandwidth":[231],"2\u00d7.":[233],"They":[234],"execution":[239],"speed":[240],"1.6\u00d7":[242,253],"3D":[245],"finite":[246],"difference,":[247],"2.5\u00d7":[248],"1D":[250],"FFT,":[251],"merge":[255],"sort,":[256],"all":[257],"measured":[258],"proposed":[263],"transparently":[271],"deploy":[272],"these":[273],"optimizations":[274],"under":[275],"simple":[276,294],"portable":[277],"user":[278],"code,":[279],"allowing":[280],"system":[281],"designers":[282],"freely":[284],"employ":[285],"devices":[286],"different":[288],"capabilities.":[289],"further":[291],"argue":[292],"interfaces":[295],"such":[296],"are":[299],"needed":[300],"most":[302],"benefit":[305],"from":[306],"advanced":[307],"practice.":[311]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
