{"id":"https://openalex.org/W2587852840","doi":"https://doi.org/10.1145/3038228.3038238","title":"Directive-based tile abstraction to distribute loops on accelerators","display_name":"Directive-based tile abstraction to distribute loops on accelerators","publication_year":2017,"publication_date":"2017-02-04","ids":{"openalex":"https://openalex.org/W2587852840","doi":"https://doi.org/10.1145/3038228.3038238","mag":"2587852840"},"language":"en","primary_location":{"id":"doi:10.1145/3038228.3038238","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038228.3038238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","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/A5044003518","display_name":"Tristan Vanderbruggen","orcid":"https://orcid.org/0000-0003-0609-3925"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tristan Vanderbruggen","raw_affiliation_strings":["University of Delaware"],"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103791820","display_name":"John Cavazos","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Cavazos","raw_affiliation_strings":["University of Delaware"],"affiliations":[{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034222191","display_name":"Chunhua Liao","orcid":"https://orcid.org/0000-0001-6477-0547"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunhua Liao","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051201607","display_name":"Daniel J. Quinlan","orcid":"https://orcid.org/0000-0001-7467-9173"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Quinlan","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044003518"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.01631147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"62"},"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":0.9980999827384949,"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":0.9977999925613403,"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":0.8654385805130005},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8197591304779053},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.643115222454071},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6330860257148743},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5509294271469116},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.49874210357666016},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.44543036818504333},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4280232787132263},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.42414408922195435},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4144396185874939},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.37642499804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8654385805130005},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8197591304779053},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.643115222454071},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6330860257148743},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5509294271469116},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.49874210357666016},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.44543036818504333},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4280232787132263},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.42414408922195435},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4144396185874939},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37642499804496765},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3038228.3038238","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038228.3038238","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5623082902","display_name":null,"funder_award_id":"B617435","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W143948075","https://openalex.org/W1503700136","https://openalex.org/W1574790150","https://openalex.org/W1606512765","https://openalex.org/W1988888548","https://openalex.org/W2009552174","https://openalex.org/W2025032781","https://openalex.org/W2063249715","https://openalex.org/W2093708648","https://openalex.org/W2148542244","https://openalex.org/W2160786443","https://openalex.org/W2168519934","https://openalex.org/W2482915108","https://openalex.org/W2561675875","https://openalex.org/W3085984841"],"related_works":["https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W3146558274","https://openalex.org/W4246454774","https://openalex.org/W2162051035","https://openalex.org/W1597127505"],"abstract_inverted_index":{"Optimizing":[0],"applications":[1,55],"for":[2,19,56,177,191],"the":[3,20,24,101,120,133,137,185],"next":[4,9,30,72],"generation":[5,10,31,73],"of":[6,27,45,70,104,116,123,171,174,187],"super-computers":[7],"requires":[8],"compilers.":[11],"These":[12],"compilers":[13,32],"need":[14,33,52],"to":[15,22,34,37,41,53,86,99,146,163],"provide":[16],"an":[17,67,111],"abstraction":[18,84,97,135],"developer":[21],"describe":[23],"inner":[25],"working":[26],"applications.":[28,50],"And,":[29],"be":[35],"able":[36],"intelligently":[38],"apply":[39],"optimizations":[40],"a":[42,82,95,167,188,192,197],"wide":[43],"variety":[44],"algorithms":[46],"solved":[47],"by":[48],"scientific":[49],"They":[51],"optimize":[54],"any":[57,60,71],"workload":[58],"targeting":[59,153],"architecture.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,77],"present":[66],"important":[68],"component":[69],"supercomputer":[74],"compiler":[75],"that":[76,184],"call":[78],"TileK.":[79],"TileK":[80,145,160],"is":[81,196],"tile":[83,134],"used":[85,98,144],"generate":[87],"distributed":[88],"kernels":[89,150,176],"from":[90],"nested":[91],"loops.":[92],"It":[93],"provides":[94],"high-level":[96],"decompose":[100],"iteration":[102],"space":[103,170],"loop":[105],"nests.":[106],"Its":[107],"directives-based":[108],"language":[109],"enables":[110],"effective":[112],"and":[113,136,151,157,165],"efficient":[114],"placement":[115],"multi-dimensional":[117],"computations":[118],"on":[119],"3D":[121],"topology":[122],"accelerators":[124],"(e.g.":[125],"graphics":[126],"processing":[127],"units,":[128],"GPUs).":[129],"We":[130,143],"implemented":[131],"both":[132],"kernel":[138],"generator":[139],"in":[140],"ROSE":[141],"Compiler.":[142],"parallelize":[147],"linear":[148],"algebra":[149],"stencils,":[152],"multicore":[154],"CPUs":[155],"(pThread)":[156],"GPUs":[158],"(OpenCL).":[159],"enabled":[161],"us":[162],"explore":[164],"evaluate":[166],"large":[168],"optimization":[169,190],"many":[172],"versions":[173],"these":[175],"varying":[178],"input":[179,194],"sizes.":[180],"Our":[181],"results":[182],"shows":[183],"selection":[186],"given":[189],"specific":[193],"size":[195],"challenging":[198],"problem.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}