{"id":"https://openalex.org/W2531523563","doi":"https://doi.org/10.1109/tpds.2016.2616314","title":"The Unicorn Runtime: Efficient Distributed Shared Memory Programming for Hybrid CPU-GPU Clusters","display_name":"The Unicorn Runtime: Efficient Distributed Shared Memory Programming for Hybrid CPU-GPU Clusters","publication_year":2016,"publication_date":"2016-10-11","ids":{"openalex":"https://openalex.org/W2531523563","doi":"https://doi.org/10.1109/tpds.2016.2616314","mag":"2531523563"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2016.2616314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2616314","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"],"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/A5090605070","display_name":"Tarun Beri","orcid":null},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tarun Beri","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727565","display_name":"Sorav Bansal","orcid":"https://orcid.org/0009-0004-2006-9635"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sorav Bansal","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103024860","display_name":"Subodh Kumar","orcid":"https://orcid.org/0000-0003-3698-9212"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Subodh Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Delhi, India","institution_ids":["https://openalex.org/I68891433"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68891433"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.8838,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.79141312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"28","issue":"5","first_page":"1518","last_page":"1534"},"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/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":0.9991000294685364,"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":0.9001656174659729},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7853062152862549},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5220908522605896},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5220867991447449},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.45162928104400635},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.42793336510658264},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.42161881923675537},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.31267714500427246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9001656174659729},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7853062152862549},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5220908522605896},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5220867991447449},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.45162928104400635},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.42793336510658264},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.42161881923675537},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.31267714500427246},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2016.2616314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2016.2616314","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321026","display_name":"Ministry of Earth Sciences","ror":"https://ror.org/013cf5k59"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1502558273","https://openalex.org/W1555993967","https://openalex.org/W1654511047","https://openalex.org/W1669598709","https://openalex.org/W1825216778","https://openalex.org/W1826603487","https://openalex.org/W1854214752","https://openalex.org/W1955328627","https://openalex.org/W1984222112","https://openalex.org/W1988307172","https://openalex.org/W2012173227","https://openalex.org/W2024437592","https://openalex.org/W2036551003","https://openalex.org/W2038469228","https://openalex.org/W2041327854","https://openalex.org/W2045271686","https://openalex.org/W2051634982","https://openalex.org/W2051975225","https://openalex.org/W2056999868","https://openalex.org/W2079577430","https://openalex.org/W2081612620","https://openalex.org/W2096070062","https://openalex.org/W2098815550","https://openalex.org/W2103071101","https://openalex.org/W2104861744","https://openalex.org/W2118269922","https://openalex.org/W2121893797","https://openalex.org/W2124613228","https://openalex.org/W2137571283","https://openalex.org/W2138212562","https://openalex.org/W2140300123","https://openalex.org/W2146381930","https://openalex.org/W2159952265","https://openalex.org/W2161679325","https://openalex.org/W2171226522","https://openalex.org/W2173213060","https://openalex.org/W2495794616","https://openalex.org/W3138798301","https://openalex.org/W4205190765","https://openalex.org/W4242599275","https://openalex.org/W4248722156","https://openalex.org/W4256158364","https://openalex.org/W6629942619","https://openalex.org/W6637302513","https://openalex.org/W6638601623","https://openalex.org/W6639055396","https://openalex.org/W6675580927","https://openalex.org/W6683813759"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2017587301","https://openalex.org/W2353146130","https://openalex.org/W2030707850","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1967597631"],"abstract_inverted_index":{"Programming":[0],"hybrid":[1,24,79],"CPU-GPU":[2,25],"clusters":[3],"is":[4,39,82,170,189],"hard.":[5],"This":[6,81,175],"paper":[7,30],"addresses":[8],"this":[9,29,63,243],"difficulty":[10],"and":[11,15,41,49,101,104,115,119,132,228,272],"presents":[12],"the":[13,55,74,85,110,162,167,177,249],"design":[14],"runtime":[16],"implementation":[17,286],"of":[18,57,73,76,87,139,156,166,179,198,208,216,280],"Unicorn-a":[19],"parallel":[20,181],"programming":[21,251],"model":[22,252],"for":[23],"clusters.":[26],"In":[27,242],"particular,":[28],"proves":[31],"that":[32,137,248],"efficient":[33,190],"distributed":[34,185],"shared":[35,91],"memory":[36],"style":[37],"programing":[38],"possible":[40],"its":[42,121,274],"simplicity":[43],"can":[44,64,253],"be":[45,65,254],"retained":[46],"across":[47],"CPUs":[48],"GPUs":[50,227],"in":[51,292],"a":[52,68,124,184,205,214,238,277,288,299],"cluster,":[53],"minus":[54],"frustration":[56],"dealing":[58,77],"with":[59,67,78,84,219,223],"race":[60],"conditions.":[61],"Further,":[62],"done":[66],"unified":[69],"abstraction,":[70,112],"avoiding":[71],"much":[72],"complication":[75],"architectures.":[80],"achieved":[83],"help":[86],"transactional":[88],"semantics":[89],"(on":[90,296],"global":[92],"address":[93],"spaces),":[94],"deferred":[95],"bulk":[96],"data":[97],"synchronization,":[98],"workload":[99],"pipelining":[100],"various":[102],"communication":[103,116],"computation":[105,114],"scheduling":[106,117],"optimizations.":[107],"We":[108,135,264],"describe":[109],"said":[111],"our":[113,149,285],"system":[118,150],"report":[120,273],"performance":[122,207],"on":[123,298],"few":[125],"benchmarks":[126],"like":[127,142,262],"Matrix":[128],"Multiplication,":[129],"LU":[130],"Decomposition":[131],"2D":[133,146],"FFT.":[134],"find":[136],"parallelization":[138],"coarse-grained":[140],"applications":[141],"matrix":[143],"multiplication":[144],"or":[145],"FFT":[147],"using":[148],"requires":[151],"only":[152],"about":[153,293],"30":[154],"lines":[155],"C":[157],"code":[158,169,182],"to":[159,183,257,269],"set":[160],"up":[161],"runtime.":[163],"The":[164,187],"rest":[165],"application":[168],"regular":[171],"single":[172],"CPU/GPU":[173],"implementation.":[174],"indicates":[176],"ease":[178],"extending":[180],"environment.":[186],"execution":[188],"as":[191],"well.":[192],"When":[193],"multiplying":[194],"two":[195,224,229],"square":[196],"matrices":[197],"size":[199],"65,":[200],"536":[201],"\u03c7":[202],"65,536,":[203],"Unicornachieves":[204],"peak":[206],"7.88":[209],"TFlop/s":[210],"when":[211],"run":[212],"over":[213,237],"cluster":[215],"14":[217],"nodes":[218],"each":[220],"node":[221],"equipped":[222],"Tesla":[225],"M2070":[226],"6-core":[230],"Intel":[231],"Xeon":[232],"2.67":[233],"GHz":[234],"CPUs,":[235],"connected":[236],"32Gbps":[239],"Infiniband":[240],"network.":[241],"paper,":[244],"we":[245],"also":[246],"demonstrate":[247],"Unicorn":[250],"efficiently":[255],"used":[256],"implement":[258,270],"high":[259],"level":[260],"abstractions":[261],"MapReduce.":[263],"use":[265],"such":[266],"an":[267],"extension":[268],"PageRank":[271],"performance.":[275],"For":[276],"sample":[278],"web":[279,283],"500":[281],"million":[282],"pages,":[284],"completes":[287],"page":[289],"rank":[290],"iteration":[291],"18":[294],"seconds":[295],"average)":[297],"14-node":[300],"cluster.":[301]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}