{"id":"https://openalex.org/W3205077974","doi":"https://doi.org/10.1145/3458817.3476154","title":"Reducing redundancy in data organization and arithmetic calculation for stencil computations","display_name":"Reducing redundancy in data organization and arithmetic calculation for stencil computations","publication_year":2021,"publication_date":"2021-11-13","ids":{"openalex":"https://openalex.org/W3205077974","doi":"https://doi.org/10.1145/3458817.3476154","mag":"3205077974"},"language":"en","primary_location":{"id":"doi:10.1145/3458817.3476154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/A5100377529","display_name":"Kun Li","orcid":"https://orcid.org/0000-0002-1013-1325"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072946868","display_name":"Liang Yuan","orcid":"https://orcid.org/0000-0003-3406-2907"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yuan","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001666028","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0002-2618-5088"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021007081","display_name":"Yue Yue","orcid":"https://orcid.org/0000-0002-0277-5032"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Yue","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9446,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73817904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"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/T10829","display_name":"Interconnection Networks and 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/stencil","display_name":"Stencil","score":0.9132052063941956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7992243766784668},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7042928338050842},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6329417824745178},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6114853024482727},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5647875666618347},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5289121866226196},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.5100839734077454},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.463650107383728},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41665130853652954},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41134709119796753},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3791888952255249},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35729461908340454},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.28846123814582825},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.1292743682861328}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9132052063941956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7992243766784668},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7042928338050842},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6329417824745178},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6114853024482727},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5647875666618347},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5289121866226196},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.5100839734077454},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.463650107383728},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41665130853652954},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41134709119796753},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3791888952255249},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35729461908340454},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.28846123814582825},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.1292743682861328},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458817.3476154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W174757544","https://openalex.org/W1492882524","https://openalex.org/W1494930385","https://openalex.org/W1506984869","https://openalex.org/W1559264847","https://openalex.org/W1561247983","https://openalex.org/W1964322740","https://openalex.org/W1968013322","https://openalex.org/W1968347730","https://openalex.org/W1973271197","https://openalex.org/W1979457157","https://openalex.org/W1987588924","https://openalex.org/W1997375049","https://openalex.org/W2003798513","https://openalex.org/W2004711550","https://openalex.org/W2008005532","https://openalex.org/W2015935981","https://openalex.org/W2016618963","https://openalex.org/W2034761517","https://openalex.org/W2039378765","https://openalex.org/W2049510645","https://openalex.org/W2063249715","https://openalex.org/W2070961300","https://openalex.org/W2104512032","https://openalex.org/W2107725926","https://openalex.org/W2119609467","https://openalex.org/W2121082877","https://openalex.org/W2123463031","https://openalex.org/W2129471558","https://openalex.org/W2135682468","https://openalex.org/W2151764765","https://openalex.org/W2154786353","https://openalex.org/W2167713801","https://openalex.org/W2198872802","https://openalex.org/W2296218291","https://openalex.org/W2786544209","https://openalex.org/W2902566644","https://openalex.org/W2913533776","https://openalex.org/W2962946415","https://openalex.org/W2962978274","https://openalex.org/W2984795004","https://openalex.org/W2984920043","https://openalex.org/W3149084271","https://openalex.org/W3152199537","https://openalex.org/W4232301837","https://openalex.org/W4234592442","https://openalex.org/W4249968602","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W3092174096","https://openalex.org/W3205799311","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W4300860486","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W1511204342","https://openalex.org/W2010557350"],"abstract_inverted_index":{"Stencil":[0],"computation":[1,53,84],"is":[2,55],"one":[3],"of":[4,17,82,103],"the":[5,27,40,59,67,73,101,108,112,118],"most":[6],"important":[7],"kernels":[8],"in":[9,72],"various":[10],"scientific":[11],"and":[12,65,92,106,120],"engineering":[13],"applications.":[14],"A":[15],"variety":[16],"work":[18],"has":[19],"focused":[20],"on":[21,117],"vectorization":[22,64],"techniques,":[23],"aiming":[24],"at":[25],"exploiting":[26],"in-core":[28],"data":[29,36,41,60,68,74],"parallelism.":[30],"However,":[31],"they":[32],"either":[33],"incur":[34],"spatial":[35,52],"conflicts":[37],"or":[38],"hurt":[39],"locality":[42,69],"when":[43],"integrated":[44],"with":[45,87,132],"tiling.":[46],"In":[47],"this":[48],"paper,":[49],"a":[50],"novel":[51],"folding":[54,85],"devised":[56],"to":[57,98],"reduce":[58,100],"reorganization":[61],"overhead":[62],"for":[63,70],"preserve":[66],"tiling":[71],"space":[75],"simultaneously.":[76],"We":[77],"then":[78],"propose":[79],"an":[80],"approach":[81,126],"temporal":[83],"enhanced":[86],"shifts":[88],"reusing,":[89],"tessellate":[90],"tiling,":[91],"semi-automatic":[93],"code":[94],"generation.":[95],"It":[96],"aims":[97],"further":[99],"redundancy":[102],"arithmetic":[104],"calculations":[105],"exploit":[107],"register":[109],"reuse":[110],"along":[111],"time":[113],"dimension.":[114],"Experimental":[115],"results":[116],"AVX2":[119],"AVX-512":[121],"CPUs":[122],"show":[123],"that":[124],"our":[125],"obtains":[127],"significant":[128],"performance":[129],"improvements":[130],"compared":[131],"state-of-the-art":[133],"techniques.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-27T08:28:00.272161","created_date":"2025-10-10T00:00:00"}
