{"id":"https://openalex.org/W2298427740","doi":"https://doi.org/10.1145/2892208.2892210","title":"Automatic data layout generation and kernel mapping for CPU+GPU architectures","display_name":"Automatic data layout generation and kernel mapping for CPU+GPU architectures","publication_year":2016,"publication_date":"2016-03-14","ids":{"openalex":"https://openalex.org/W2298427740","doi":"https://doi.org/10.1145/2892208.2892210","mag":"2298427740"},"language":"en","primary_location":{"id":"doi:10.1145/2892208.2892210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2892208.2892210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on Compiler Construction","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/A5005326647","display_name":"Deepak Majeti","orcid":"https://orcid.org/0000-0003-3031-5778"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Deepak Majeti","raw_affiliation_strings":["Rice University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041528950","display_name":"Kuldeep S. Meel","orcid":"https://orcid.org/0000-0001-9423-5270"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuldeep S. Meel","raw_affiliation_strings":["Rice University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102819808","display_name":"Rajkishore Barik","orcid":"https://orcid.org/0000-0003-4779-1391"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajkishore Barik","raw_affiliation_strings":["Intel, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043513001","display_name":"Vivek Sarkar","orcid":"https://orcid.org/0000-0002-3433-8830"},"institutions":[{"id":"https://openalex.org/I74775410","display_name":"Rice University","ror":"https://ror.org/008zs3103","country_code":"US","type":"education","lineage":["https://openalex.org/I74775410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Sarkar","raw_affiliation_strings":["Rice University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rice University, USA","institution_ids":["https://openalex.org/I74775410"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005326647"],"corresponding_institution_ids":["https://openalex.org/I74775410"],"apc_list":null,"apc_paid":null,"fwci":4.1628,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93934979,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"240","last_page":"250"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9984999895095825,"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":0.9983999729156494,"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":0.8414455652236938},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7079379558563232},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5946105718612671},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.46123194694519043},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4260503649711609},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09319230914115906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414455652236938},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7079379558563232},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5946105718612671},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.46123194694519043},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4260503649711609},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09319230914115906},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2892208.2892210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2892208.2892210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on Compiler Construction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W57462620","https://openalex.org/W1518474679","https://openalex.org/W1540418512","https://openalex.org/W1608128325","https://openalex.org/W1968797199","https://openalex.org/W1982020565","https://openalex.org/W2007644437","https://openalex.org/W2016352575","https://openalex.org/W2017239768","https://openalex.org/W2025317174","https://openalex.org/W2054625910","https://openalex.org/W2056304566","https://openalex.org/W2063255488","https://openalex.org/W2068810256","https://openalex.org/W2070922326","https://openalex.org/W2072680607","https://openalex.org/W2080592089","https://openalex.org/W2091589449","https://openalex.org/W2105937753","https://openalex.org/W2111309482","https://openalex.org/W2129305676","https://openalex.org/W2147218728","https://openalex.org/W2150476673","https://openalex.org/W2158950986","https://openalex.org/W2160875256","https://openalex.org/W2167334577","https://openalex.org/W2171392117","https://openalex.org/W2273440736","https://openalex.org/W3009206924","https://openalex.org/W4239437589","https://openalex.org/W6947821152"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758","https://openalex.org/W2074886298"],"abstract_inverted_index":{"The":[0,112,149],"ubiquity":[1],"of":[2,56,77,100,235,255,264,280,295],"hybrid":[3],"CPU+GPU":[4,62,245],"architectures":[5],"has":[6],"led":[7],"to":[8,17,48,53,86,145,215,237,247,282,298],"renewed":[9],"interest":[10],"in":[11,191,202],"automatic":[12,57],"data":[13,21,32,58,69,72,102,119,154,179,199,218,228],"layout":[14,59,70,103,120,200,219,229],"generation":[15,60],"owing":[16],"the":[18,35,54,65,101,118,160,178,182,192,203,217,223,248,289,293],"fact":[19],"that":[20,30,140,176],"layouts":[22,33,155,180,251],"have":[23],"a":[24,83,95,123,128,137,167,171,187,243,253,260],"large":[25],"impact":[26,220],"on":[27,38,127,221,242,259,287],"performance,":[28],"and":[29,75,104,134,156,211,225,269,301],"different":[31],"yield":[34],"best":[36],"performance":[37,213,233,278],"CPUs":[39],"vs.":[40],"GPUs.":[41],"Unfortunately,":[42],"current":[43,87],"programming":[44,88,209],"models":[45,214],"still":[46],"fail":[47],"provide":[49,136,166],"an":[50,142,265,270],"effective":[51],"solution":[52,169],"problem":[55,107,121],"for":[61,108,122,159,163,181,186,252],"processors.":[63],"Specifically,":[64],"interaction":[66],"among":[67],"wholeprogram":[68],"optimizations,":[71,74],"movement":[73],"mapping":[76,106,158],"kernels":[78],"across":[79],"heterogeneous":[80,110,261,300],"cores":[81],"pose":[82],"major":[84],"challenge":[85],"systems.":[89],"In":[90],"this":[91,198],"paper,":[92],"we":[93,135,165],"introduce":[94],"novel":[96],"two-level":[97],"hierarchical":[98],"formulation":[99,115,152],"kernel":[105,157],"modern":[109],"architectures.":[111],"bottom":[113,193],"level":[114,151,194],"deals":[116],"with":[117],"parallel":[124,208,256],"code":[125,183],"region":[126],"given":[129,188],"processor,":[130],"which":[131,164],"is":[132],"NPHard,":[133],"greedy":[138],"algorithm":[139,175],"uses":[141,177],"affinity":[143],"graph":[144],"obtain":[146],"approximate":[147],"solutions.":[148],"top":[150],"targets":[153],"entire":[161],"program":[162],"polynomial-time":[168],"using":[170],"graph-based":[172],"shortest":[173],"path":[174],"regions":[184],"(sections)":[185],"processor":[189],"computed":[190],"formulation.":[195],"We":[196],"implement":[197],"transformation":[201],"new":[204],"Heterogeneous":[205],"Habanero-C":[206],"(H2C)":[207],"framework":[210,230,275],"propose":[212],"characterize":[216],"both":[222,299],"CPU":[224,268],"GPU.":[226,272],"Our":[227],"shows":[231,277],"significant":[232],"improvements":[234,279],"up":[236,281],"2.9x":[238],"(geometric":[239,284],"mean":[240,285],"1.5x)":[241],"multicore":[244,290],"compared":[246],"manually":[249],"specified":[250],"set":[254],"programs":[257],"running":[258],"platform":[262],"consisting":[263],"Intel":[266],"Xeon":[267],"NVIDIA":[271],"Further,":[273],"our":[274,296],"also":[276],"2.7x":[283],"1.6x)":[286],"just":[288],"CPU,":[291],"demonstrating":[292],"applicability":[294],"approach":[297],"homogeneous":[302],"hardware":[303],"platforms.":[304]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}