{"id":"https://openalex.org/W2138578542","doi":"https://doi.org/10.1145/2145816.2145838","title":"PARRAY","display_name":"PARRAY","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2138578542","doi":"https://doi.org/10.1145/2145816.2145838","mag":"2138578542"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","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/A5108049213","display_name":"Yifeng Chen","orcid":"https://orcid.org/0000-0001-5219-3543"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yifeng Chen","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102915338","display_name":"Xiang Cui","orcid":"https://orcid.org/0000-0001-9165-3776"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Cui","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100653755","display_name":"Hong Mei","orcid":"https://orcid.org/0000-0002-3938-4692"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Mei","raw_affiliation_strings":["Peking University, Bejing, China","Peking University, Bejing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Bejing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Bejing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108049213"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":3.1906,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.92036725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"180"},"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":0.8811600208282471},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6997702121734619},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6541147232055664},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6136883497238159},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.5135424137115479},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5099846124649048},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.47121113538742065},{"id":"https://openalex.org/keywords/parallel-programming-model","display_name":"Parallel programming model","score":0.41202062368392944},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.40950119495391846},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.15853393077850342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8811600208282471},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6997702121734619},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6541147232055664},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6136883497238159},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.5135424137115479},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5099846124649048},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.47121113538742065},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.41202062368392944},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40950119495391846},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.15853393077850342}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2145816.2145838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1967802285","https://openalex.org/W2053722886","https://openalex.org/W2065413511","https://openalex.org/W2090409324","https://openalex.org/W2091780466","https://openalex.org/W2107483876","https://openalex.org/W2108600626","https://openalex.org/W2109065830","https://openalex.org/W2109982223","https://openalex.org/W2110846749","https://openalex.org/W2114927422","https://openalex.org/W2130179171","https://openalex.org/W2140300123","https://openalex.org/W2159560337","https://openalex.org/W2164106630","https://openalex.org/W2170611190","https://openalex.org/W2315064349","https://openalex.org/W3140353777","https://openalex.org/W3144368627","https://openalex.org/W3145767355","https://openalex.org/W3147878143","https://openalex.org/W4244568863","https://openalex.org/W6676995014"],"related_works":["https://openalex.org/W2769189194","https://openalex.org/W1537323515","https://openalex.org/W2353852602","https://openalex.org/W2120249721","https://openalex.org/W2460870572","https://openalex.org/W1177194838","https://openalex.org/W4236300446","https://openalex.org/W1536319110","https://openalex.org/W2102103803","https://openalex.org/W1582830241"],"abstract_inverted_index":{"This":[0,124],"paper":[1],"introduces":[2],"a":[3,75,114,189],"programming":[4,15,57,112,165],"interface":[5],"called":[6],"PARRAY":[7,53],"(or":[8],"Parallelizing":[9],"ARRAYs)":[10],"that":[11,110,193],"supports":[12],"system-level":[13],"succinct":[14],"for":[16,103,144],"heterogeneous":[17],"parallel":[18,132],"systems":[19],"like":[20,34],"GPU":[21],"clusters.":[22],"The":[23,182],"current":[24],"practice":[25],"of":[26,51,62,68,85,176,180],"software":[27],"development":[28],"requires":[29],"combining":[30],"several":[31],"low-level":[32,156],"libraries":[33,175],"Pthread,":[35],"OpenMP,":[36],"CUDA":[37],"and":[38,42,49,130,166,207],"MPI.":[39],"Achieving":[40],"productivity":[41],"portability":[43],"is":[44],"hard":[45],"with":[46,58,203],"different":[47],"numbers":[48],"models":[50],"GPUs.":[52],"extends":[54],"mainstream":[55],"C":[56],"novel":[59],"array":[60,70,87,94,98],"types":[61,99],"distinct":[63],"features:":[64],"1)":[65],"the":[66,79,83,135,149,161,200],"dimensions":[67],"an":[69,86],"type":[71,88,162],"are":[72,170],"nested":[73],"in":[74,113],"tree,":[76],"conceptually":[77],"reflecting":[78],"memory":[80],"hierarchy;":[81],"2)":[82],"definition":[84],"may":[89],"contain":[90],"references":[91],"to":[92,100,118,126,160],"other":[93],"types,":[95],"allowing":[96],"sophisticated":[97,121],"be":[101],"created":[102],"parallelization;":[104],"3)":[105],"threads":[106],"also":[107],"form":[108],"arrays":[109],"allow":[111],"Single-Program-Multiple-Codeblock":[115],"(SPMC)":[116],"style":[117],"unify":[119],"various":[120],"communication":[122],"patterns.":[123],"leads":[125],"shorter,":[127],"more":[128],"portable":[129],"maintainable":[131],"codes,":[133],"while":[134],"programmer":[136],"still":[137,171],"has":[138],"control":[139],"over":[140],"performance-related":[141],"features":[142],"necessary":[143],"deep":[145],"manual":[146],"optimization.":[147],"Although":[148],"source-to-source":[150],"code":[151,192],"generator":[152],"only":[153],"faithfully":[154],"generates":[155],"library":[157],"calls":[158],"according":[159],"information,":[163],"higher-level":[164],"automatic":[167],"performance":[168],"optimization":[169],"possible":[172],"through":[173],"building":[174],"sub-programs":[177],"on":[178,185,199],"top":[179],"PARRAY.":[181],"case":[183],"study":[184],"cluster":[186],"FFT":[187],"illustrates":[188],"simple":[190],"30-line":[191],"2x":[194],"outperforms":[195],"Intel":[196],"Cluster":[197],"MKL":[198],"Tianhe-1A":[201],"system":[202],"7168":[204],"Fermi":[205],"GPUs":[206],"14336":[208],"CPUs.":[209]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}