{"id":"https://openalex.org/W2284845123","doi":"https://doi.org/10.1145/2832080.2832085","title":"Weighted dynamic scheduling with many parallelism grains for offloading of numerical workloads to multiple varied accelerators","display_name":"Weighted dynamic scheduling with many parallelism grains for offloading of numerical workloads to multiple varied accelerators","publication_year":2015,"publication_date":"2015-11-11","ids":{"openalex":"https://openalex.org/W2284845123","doi":"https://doi.org/10.1145/2832080.2832085","mag":"2284845123"},"language":"en","primary_location":{"id":"doi:10.1145/2832080.2832085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2832080.2832085","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2832085&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2832085&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101964224","display_name":"Azzam Haidar","orcid":"https://orcid.org/0000-0002-3177-2084"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Azzam Haidar","raw_affiliation_strings":["University of Tennessee"],"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108555267","display_name":"Yulu Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulu Jia","raw_affiliation_strings":["University of Tennessee"],"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073990539","display_name":"Piotr \u0141uszczek","orcid":"https://orcid.org/0000-0002-0089-6965"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Luszczek","raw_affiliation_strings":["University of Tennessee"],"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083604741","display_name":"Stanimire Tomov","orcid":"https://orcid.org/0000-0002-5937-7959"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stanimire Tomov","raw_affiliation_strings":["University of Tennessee"],"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087711762","display_name":"Asim YarKhan","orcid":"https://orcid.org/0000-0002-3901-9695"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Asim YarKhan","raw_affiliation_strings":["University of Tennessee"],"affiliations":[{"raw_affiliation_string":"University of Tennessee","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Dongarra","raw_affiliation_strings":["University of Tennessee, University of Manchester"],"affiliations":[{"raw_affiliation_string":"University of Tennessee, University of Manchester","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101964224"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":0.6595,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72132988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9998999834060669,"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":0.9987000226974487,"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":0.8947170972824097},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7428749799728394},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.7128025889396667},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5985761880874634},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5973450541496277},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5896743535995483},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.542980432510376},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5414935946464539},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.521561861038208},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.47328799962997437},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.4514748156070709},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3819788992404938},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3492259979248047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15676358342170715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8947170972824097},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7428749799728394},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.7128025889396667},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5985761880874634},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5973450541496277},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5896743535995483},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.542980432510376},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5414935946464539},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.521561861038208},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.47328799962997437},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.4514748156070709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3819788992404938},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3492259979248047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15676358342170715},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2832080.2832085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2832080.2832085","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2832085&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2832080.2832085","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2832080.2832085","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2832085&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1625423705","display_name":null,"funder_award_id":"ACI-1339822 and 1137097","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1687433189","display_name":null,"funder_award_id":"1339822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1836428231","display_name":null,"funder_award_id":"1339822","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"},{"id":"https://openalex.org/G2971811006","display_name":null,"funder_award_id":"1137097","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5781530723","display_name":null,"funder_award_id":"N14-11-00190","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"},{"id":"https://openalex.org/G7262430608","display_name":null,"funder_award_id":"ACI-1339822","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8473873697","display_name":null,"funder_award_id":"NICS-Beacon","funder_id":"https://openalex.org/F4320309541","funder_display_name":"University of Tennessee"},{"id":"https://openalex.org/G8753669605","display_name":null,"funder_award_id":"N14-11-00190","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320309541","display_name":"University of Tennessee","ror":"https://ror.org/00xzqjh13"},{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2284845123.pdf","grobid_xml":"https://content.openalex.org/works/W2284845123.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W47427672","https://openalex.org/W190121517","https://openalex.org/W1494445573","https://openalex.org/W1842923156","https://openalex.org/W1946080187","https://openalex.org/W1987643268","https://openalex.org/W1988888548","https://openalex.org/W2011903918","https://openalex.org/W2016358047","https://openalex.org/W2019013398","https://openalex.org/W2023096360","https://openalex.org/W2045271686","https://openalex.org/W2061781302","https://openalex.org/W2085118703","https://openalex.org/W2091597871","https://openalex.org/W2104861744","https://openalex.org/W2113277707","https://openalex.org/W2121893797","https://openalex.org/W2165904264","https://openalex.org/W2170597842","https://openalex.org/W2405076432","https://openalex.org/W2946724226","https://openalex.org/W3145506805","https://openalex.org/W3187688612","https://openalex.org/W4205190765"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W2003935582","https://openalex.org/W74409296","https://openalex.org/W1554644772","https://openalex.org/W2494130044","https://openalex.org/W29548032","https://openalex.org/W2593878938","https://openalex.org/W2468095077","https://openalex.org/W305742777","https://openalex.org/W2121547511"],"abstract_inverted_index":{"A":[0],"wide":[1],"variety":[2],"of":[3,20,62,85,150],"heterogeneous":[4,156],"compute":[5],"resources":[6,158],"are":[7],"available":[8,127],"to":[9,39,51,76,93,121,125],"modern":[10],"computers,":[11],"including":[12,136],"multiple":[13,83,134],"sockets":[14],"containing":[15],"multicore":[16],"CPUs,":[17],"one-or-more":[18],"GPUs":[19,53],"varying":[21],"power,":[22],"and":[23,41,78,87,113,144],"coprocessors":[24],"such":[25],"as":[26],"the":[27,55,98,123,126],"Intel":[28],"Xeon":[29],"Phi.":[30],"The":[31,71,129,148],"challenge":[32],"faced":[33],"by":[34,115,161],"domain":[35,72],"scientists":[36],"is":[37,131,159],"how":[38],"efficiently":[40],"productively":[42],"use":[43,52],"these":[44],"varied":[45],"resources.":[46,99,128],"For":[47],"example,":[48],"in":[49,82,91],"order":[50,92],"effectively,":[54],"workload":[56,66],"must":[57],"have":[58,75],"a":[59,65,69,102,117],"greater":[60],"degree":[61],"parallelism":[63,86,112],"than":[64],"designed":[67],"for":[68,153],"multicore-CPU.":[70],"scientist":[73],"would":[74],"design":[77],"schedule":[79],"an":[80],"application":[81],"degrees":[84],"task":[88,141,146],"grain":[89,142],"sizes":[90],"obtain":[94],"efficient":[95],"performance":[96],"from":[97,107],"We":[100],"propose":[101],"productive":[103],"programming":[104],"model":[105],"starting":[106],"serial":[108],"code,":[109],"which":[110],"achieves":[111],"scalability":[114],"using":[116],"task-superscalar":[118],"runtime":[119],"environment":[120],"adapt":[122],"computation":[124],"adaptation":[130],"done":[132],"at":[133],"points,":[135],"multi-level":[137],"data":[138],"partitioning,":[139],"adaptive":[140],"sizes,":[143],"dynamic":[145],"scheduling.":[147],"effectiveness":[149],"this":[151],"approach":[152],"utilizing":[154],"multi-way":[155],"hardware":[157],"demonstrated":[160],"implementing":[162],"dense":[163],"linear":[164],"algebra":[165],"applications.":[166]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}