{"id":"https://openalex.org/W2601249265","doi":"https://doi.org/10.1145/3029580.3029582","title":"VectorPU","display_name":"VectorPU","publication_year":2017,"publication_date":"2017-01-25","ids":{"openalex":"https://openalex.org/W2601249265","doi":"https://doi.org/10.1145/3029580.3029582","mag":"2601249265"},"language":"en","primary_location":{"id":"doi:10.1145/3029580.3029582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3029580.3029582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop and 6th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures and Design Tools and Architectures for Multicore Embedded Computing Platforms","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/A5100743673","display_name":"Lu Li","orcid":"https://orcid.org/0000-0002-2633-7942"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Lu Li","raw_affiliation_strings":["IDA, Link\u00f6ping University, Link\u00f6ping, Sweden"],"affiliations":[{"raw_affiliation_string":"IDA, Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059272770","display_name":"Christoph Ke\u00dfler","orcid":"https://orcid.org/0000-0001-5241-0026"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Christoph Kessler","raw_affiliation_strings":["IDA, Link\u00f6ping University, Link\u00f6ping, Sweden"],"affiliations":[{"raw_affiliation_string":"IDA, Link\u00f6ping University, Link\u00f6ping, Sweden","institution_ids":["https://openalex.org/I102134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100743673"],"corresponding_institution_ids":["https://openalex.org/I102134673"],"apc_list":null,"apc_paid":null,"fwci":1.3519,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81247768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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":0.8806557655334473},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6021885871887207},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5886794328689575},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.45414021611213684},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4414272606372833},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4373909533023834},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4314314126968384},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41430261731147766},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39200061559677124},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3170008063316345},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30654412508010864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8806557655334473},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6021885871887207},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5886794328689575},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.45414021611213684},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4414272606372833},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4373909533023834},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4314314126968384},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41430261731147766},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39200061559677124},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3170008063316345},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30654412508010864},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3029580.3029582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3029580.3029582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop and 6th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures and Design Tools and Architectures for Multicore Embedded Computing Platforms","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W844148305","https://openalex.org/W1966124831","https://openalex.org/W1975761710","https://openalex.org/W1981065940","https://openalex.org/W2032039029","https://openalex.org/W2041679393","https://openalex.org/W2050019858","https://openalex.org/W2095894588","https://openalex.org/W2121893797","https://openalex.org/W2126026097","https://openalex.org/W2149950425","https://openalex.org/W2159792012","https://openalex.org/W2185719349","https://openalex.org/W2257796347","https://openalex.org/W2271225246","https://openalex.org/W2472048300","https://openalex.org/W4244034359","https://openalex.org/W4249798784","https://openalex.org/W4252178669"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2983282793","https://openalex.org/W1973046741","https://openalex.org/W1966837078","https://openalex.org/W2460870572","https://openalex.org/W4236300446"],"abstract_inverted_index":{"We":[0,90,134],"present":[1],"VectorPU,":[2,143],"a":[3,25,30,47,60,92],"C++":[4],"based":[5],"programming":[6],"framework":[7],"providing":[8,29],"high-level":[9],"and":[10,46,68,87,100,131,139,144,148],"efficient":[11],"unified":[12,62],"memory":[13,44,63,70,88],"access":[14,55],"on":[15,120],"heterogeneous":[16],"systems,":[17,99],"in":[18],"particular":[19],"GPU-based":[20,98],"systems.":[21],"VectorPU":[22,57,95],"consists":[23],"of":[24,39,80,94,142],"light-weight":[26,48],"runtime":[27],"library":[28],"generic,":[31],"\"smart\"":[32],"data-container":[33],"abstraction":[34],"for":[35,96],"transparent":[36],"software":[37],"caching":[38],"array":[40],"operands":[41],"with":[42,65,83,129],"programmable":[43],"coherence,":[45],"component":[49],"model":[50],"realized":[51],"by":[52,118],"macro-based":[53],"data":[54,66,85],"annotations.":[56],"thereby":[58],"enables":[59],"flexible":[61],"view":[64],"transfer":[67],"device":[69],"management":[71],"abstracted":[72],"away":[73],"from":[74,124],"programmers,":[75],"while":[76],"keeping":[77],"the":[78,137],"efficiency":[79,150],"expert-written":[81,153],"code":[82,113],"manual":[84],"movement":[86],"management.":[89],"provide":[91],"prototype":[93],"(CUDA)":[97],"show":[101,136],"that":[102],"it":[103],"can":[104],"achieve":[105],"1.40\u00d7":[106],"to":[107,126,152],"13.29\u00d7":[108],"speedup":[109],"over":[110],"good":[111],"quality":[112],"using":[114],"Nvidia's":[115],"Unified":[116],"Memory":[117],"experiments":[119],"several":[121],"machines":[122],"ranging":[123],"laptops":[125],"supercomputer":[127],"nodes,":[128],"Kepler":[130],"Maxwell":[132],"GPUs.":[133],"also":[135],"expressiveness":[138],"wide":[140],"applicability":[141],"its":[145],"low":[146],"overhead":[147],"equal":[149],"compared":[151],"code.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2017-04-07T00:00:00"}