{"id":"https://openalex.org/W2766050918","doi":"https://doi.org/10.1145/3148173.3148190","title":"Applying Temporal Blocking with a Directive-based Approach","display_name":"Applying Temporal Blocking with a Directive-based Approach","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2766050918","doi":"https://doi.org/10.1145/3148173.3148190","mag":"2766050918"},"language":"en","primary_location":{"id":"doi:10.1145/3148173.3148190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148173.3148190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on the LLVM Compiler Infrastructure in HPC","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/A5070693855","display_name":"Shota Kuroda","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Kuroda","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011254074","display_name":"Toshio Endo","orcid":"https://orcid.org/0000-0001-7297-6211"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshio Endo","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16090762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.996999979019165,"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":0.9969000220298767,"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/stencil","display_name":"Stencil","score":0.9618208408355713},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8258112072944641},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7317848801612854},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7046815752983093},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5702135562896729},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5441303253173828},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.49069082736968994},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4868899881839752},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48014160990715027},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.47210612893104553},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.46469825506210327},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.41203564405441284},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34605708718299866},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.30590569972991943},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1940149962902069}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9618208408355713},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258112072944641},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7317848801612854},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7046815752983093},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5702135562896729},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5441303253173828},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.49069082736968994},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4868899881839752},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48014160990715027},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.47210612893104553},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.46469825506210327},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.41203564405441284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34605708718299866},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.30590569972991943},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1940149962902069},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3148173.3148190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3148173.3148190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Workshop on the LLVM Compiler Infrastructure in HPC","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/12","score":0.47999998927116394,"display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1506424797","https://openalex.org/W1558370006","https://openalex.org/W1979457157","https://openalex.org/W2026173834","https://openalex.org/W2034761517","https://openalex.org/W2039378765","https://openalex.org/W2057317268","https://openalex.org/W2074833026","https://openalex.org/W2102976251","https://openalex.org/W2119609467","https://openalex.org/W2129050115","https://openalex.org/W2153185479","https://openalex.org/W2574613442","https://openalex.org/W3099448935","https://openalex.org/W4246166885"],"related_works":["https://openalex.org/W1507301366","https://openalex.org/W2269110805","https://openalex.org/W2769005600","https://openalex.org/W3105739589","https://openalex.org/W2105221648","https://openalex.org/W2097757554","https://openalex.org/W2039378765","https://openalex.org/W2185562986","https://openalex.org/W2913533776","https://openalex.org/W4401408752"],"abstract_inverted_index":{"Stencil":[0],"kernels":[1,23,133],"are":[2],"important,":[3],"iterative":[4],"computation":[5],"patterns":[6],"heavily":[7],"used":[8],"in":[9,77,97],"scientific":[10],"simulations":[11],"and":[12,30,68,73,125,140,147],"other":[13],"operations":[14],"such":[15],"as":[16,43,105,107],"image":[17],"processing.":[18],"The":[19],"performance":[20,116,135],"of":[21,34,46,71,114,117],"stencil":[22,120,132],"is":[24,37,137],"usually":[25],"bound":[26],"by":[27,92],"memory":[28],"bandwidth,":[29],"the":[31,80,94,98,115,130],"common":[32],"method":[33],"overcoming":[35],"this":[36],"to":[38,53,61,111,139],"apply":[39],"Temporal":[40],"Blocking":[41],"(TB)":[42],"a":[44],"form":[45],"bandwidth":[47],"reducing":[48,102],"algorithm.":[49],"However,":[50],"applying":[51],"TB":[52,78,91],"existing":[54],"code":[55],"incurs":[56],"high":[57],"programming":[58,103],"cost":[59,104],"due":[60],"real-life":[62],"codes":[63,121],"embodying":[64],"complex":[65],"loop":[66],"structures,":[67],"moreover,":[69],"multitudes":[70],"parameters":[72],"blocking":[74],"schemes":[75],"involved":[76],"complicating":[79],"tuning":[81],"process.":[82],"We":[83],"propose":[84],"an":[85],"automated,":[86],"directive-based":[87],"compiler":[88],"approach":[89],"for":[90],"extending":[93],"polyhedral":[95],"compilation":[96],"Polly/LLVM":[99],"framework,":[100],"significantly":[101],"well":[106],"being":[108],"easily":[109],"subject":[110],"auto-tuning.":[112],"Evaluation":[113],"our":[118],"generated":[119],"on":[122,142],"Core":[123],"i7":[124],"Xeon":[126],"Phi":[127],"show":[128],"that":[129,136],"auto-generated":[131],"achieve":[134],"close":[138],"often":[141],"par":[143],"with":[144],"hand":[145],"TB-converted":[146],"optimized":[148],"codes.":[149]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}