{"id":"https://openalex.org/W2671496873","doi":"https://doi.org/10.1145/2578948.2560689","title":"Autotuning Wavefront Applications for Multicore Multi-GPU Hybrid Architectures","display_name":"Autotuning Wavefront Applications for Multicore Multi-GPU Hybrid Architectures","publication_year":2014,"publication_date":"2014-02-07","ids":{"openalex":"https://openalex.org/W2671496873","doi":"https://doi.org/10.1145/2578948.2560689","mag":"2671496873"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/2578948.2560689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/18615208/PMAMpaper.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036672835","display_name":"Siddharth Mohanty","orcid":"https://orcid.org/0009-0002-0663-8673"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Siddharth Mohanty","raw_affiliation_strings":["Institute for Computing Systems Architecture, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Institute for Computing Systems Architecture, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032376930","display_name":"Murray Cole","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Murray Cole","raw_affiliation_strings":["Institute for Computing Systems Architecture, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Institute for Computing Systems Architecture, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.698,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.715601,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":76,"max":79},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9999,"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":0.9999,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9944,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9934,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.85070556},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.62377554},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5958975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86956453},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.85070556},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.62377554},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.61950994},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5958975},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47512466},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43893996},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09453687},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07930371},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/2578948.2560689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/autotuning-wavefront-applications-for-multicore-multigpu-hybrid-architectures(273132ea-3b9d-46fd-b255-c158b459d5ab).html","pdf_url":"https://www.research.ed.ac.uk/files/18615208/PMAMpaper.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.pure.ed.ac.uk/ws/files/18615208/PMAMpaper.pdf","pdf_url":"https://www.pure.ed.ac.uk/ws/files/18615208/PMAMpaper.pdf","source":{"id":"https://openalex.org/S4306400320","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/autotuning-wavefront-applications-for-multicore-multigpu-hybrid-architectures(273132ea-3b9d-46fd-b255-c158b459d5ab).html","pdf_url":"https://www.research.ed.ac.uk/files/18615208/PMAMpaper.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":11,"referenced_works":["https://openalex.org/W1982020565","https://openalex.org/W1996345933","https://openalex.org/W2001258868","https://openalex.org/W2016618963","https://openalex.org/W2039417226","https://openalex.org/W2078034038","https://openalex.org/W2104512032","https://openalex.org/W2119042753","https://openalex.org/W2129161772","https://openalex.org/W2337884509","https://openalex.org/W3159938557"],"related_works":["https://openalex.org/W947442053","https://openalex.org/W4287182096","https://openalex.org/W4249323025","https://openalex.org/W27867058","https://openalex.org/W2317245370","https://openalex.org/W2283866686","https://openalex.org/W2148915962","https://openalex.org/W2030310580","https://openalex.org/W198851386","https://openalex.org/W1980160788"],"abstract_inverted_index":{"Manual":[0],"tuning":[1,107],"of":[2,49,85,105,113,124,132,138],"applications":[3,68,100,139],"for":[4,51],"heterogeneous":[5],"parallel":[6],"systems":[7,75],"is":[8],"tedious":[9],"and":[10,17,79,140],"complex.":[11],"Optimizations":[12],"are":[13],"often":[14],"not":[15],"portable,":[16],"the":[18,47,64,71,106],"whole":[19],"process":[20],"must":[21],"be":[22],"repeated":[23],"when":[24],"moving":[25],"to":[26,33,110],"a":[27,34,56,86,111],"new":[28],"system,":[29],"or":[30],"sometimes":[31],"even":[32],"different":[35],"problem":[36],"size.":[37],"Pattern-based":[38],"programming":[39],"models":[40],"provide":[41],"structure":[42],"which":[43,62,69],"can":[44],"assist":[45],"in":[46],"creation":[48],"autotuners":[50],"such":[52],"problems.":[53],"We":[54],"present":[55],"machine":[57,127],"learning":[58],"based":[59],"auto-tuning":[60],"framework":[61],"partitions":[63],"work":[65],"created":[66],"by":[67],"follow":[70],"wavefront":[72],"pattern":[73,87],"across":[74,136],"comprising":[76],"multicore":[77],"CPUs":[78],"multiple":[80],"GPU":[81],"accelerators.":[82],"The":[83],"use":[84],"facilitates":[88],"training":[89],"on":[90,98],"synthetically":[91],"generated":[92],"instances.":[93],"Exhaustive":[94],"search":[95],"space":[96],"exploration":[97],"real":[99],"indicates":[101],"that":[102],"correct":[103],"setting":[104],"factors":[108],"leads":[109],"maximum":[112],"20x":[114],"speedup":[115],"over":[116],"an":[117,122],"optimized":[118],"sequential":[119],"baseline,":[120],"with":[121],"average":[123],"7.8x.":[125],"Our":[126],"learned":[128],"heuristics":[129],"obtain":[130],"98%":[131],"this":[133],"speed-up,":[134],"averaged":[135],"range":[137],"architectures.":[141]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2671496873","counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2024-12-14T04:13:05.147277","created_date":"2017-06-30"}