{"id":"https://openalex.org/W2984920043","doi":"https://doi.org/10.1145/3295500.3356210","title":"Exploiting reuse and vectorization in blocked stencil computations on CPUs and GPUs","display_name":"Exploiting reuse and vectorization in blocked stencil computations on CPUs and GPUs","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2984920043","doi":"https://doi.org/10.1145/3295500.3356210","mag":"2984920043"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356210","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3295500.3356210","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356210","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356210","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033875105","display_name":"Tuowen Zhao","orcid":"https://orcid.org/0000-0002-6347-7135"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuowen Zhao","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032219555","display_name":"Protonu Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Protonu Basu","raw_affiliation_strings":["Facebook"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Lawrence Berkeley National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Lab","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082013692","display_name":"Hans Johansen","orcid":"https://orcid.org/0000-0002-9644-9982"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Johansen","raw_affiliation_strings":["Lawrence Berkeley National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Lab","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1771,"has_fulltext":true,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96743831,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"44"},"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":0.9993000030517578,"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":0.9915000200271606,"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":0.9132577180862427},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8161695003509521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8042920231819153},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6801522970199585},{"id":"https://openalex.org/keywords/instruction-prefetch","display_name":"Instruction prefetch","score":0.6692400574684143},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.6238894462585449},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6106849908828735},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5723854899406433},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5382708311080933},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5328994393348694},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.4780324399471283},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.42479783296585083},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3959883451461792},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14153316617012024}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9132577180862427},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8161695003509521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042920231819153},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6801522970199585},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.6692400574684143},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.6238894462585449},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6106849908828735},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5723854899406433},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5382708311080933},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5328994393348694},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.4780324399471283},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.42479783296585083},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3959883451461792},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14153316617012024},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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:10.1145/3295500.3356210","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3295500.3356210","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356210","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":{"id":"doi:10.1145/3295500.3356210","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3295500.3356210","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3295500.3356210","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1071216263","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G1143651532","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2900453181","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3232922872","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6859237865","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7354628648","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G7368046788","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8306346728","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2984920043.pdf","grobid_xml":"https://content.openalex.org/works/W2984920043.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1492882524","https://openalex.org/W1553808293","https://openalex.org/W1559264847","https://openalex.org/W1774469134","https://openalex.org/W1795008753","https://openalex.org/W1820993528","https://openalex.org/W1825532946","https://openalex.org/W1968347730","https://openalex.org/W1979457157","https://openalex.org/W1997147891","https://openalex.org/W1997375049","https://openalex.org/W2002555321","https://openalex.org/W2003798513","https://openalex.org/W2016618963","https://openalex.org/W2018280830","https://openalex.org/W2019066866","https://openalex.org/W2035430533","https://openalex.org/W2039378765","https://openalex.org/W2076028817","https://openalex.org/W2076535184","https://openalex.org/W2103817093","https://openalex.org/W2104512032","https://openalex.org/W2109859355","https://openalex.org/W2113190809","https://openalex.org/W2119042753","https://openalex.org/W2128746953","https://openalex.org/W2147127704","https://openalex.org/W2148038801","https://openalex.org/W2150319905","https://openalex.org/W2152914333","https://openalex.org/W2154078685","https://openalex.org/W2154786353","https://openalex.org/W2160106616","https://openalex.org/W2173545083","https://openalex.org/W2418422265","https://openalex.org/W2486796129","https://openalex.org/W2528745529","https://openalex.org/W2561650451","https://openalex.org/W2620201258","https://openalex.org/W2786544209","https://openalex.org/W2902566644","https://openalex.org/W2903775786","https://openalex.org/W3147517636","https://openalex.org/W3152199537","https://openalex.org/W4229797772","https://openalex.org/W4232301837","https://openalex.org/W4249968602"],"related_works":["https://openalex.org/W3092174096","https://openalex.org/W3205799311","https://openalex.org/W4300860486","https://openalex.org/W3137777618","https://openalex.org/W1999524790","https://openalex.org/W3106055984","https://openalex.org/W2996929894","https://openalex.org/W4247641071","https://openalex.org/W4233319313","https://openalex.org/W2553481723"],"abstract_inverted_index":{"Stencil":[0],"computations":[1],"in":[2,51],"real-world":[3],"scientific":[4],"applications":[5],"may":[6],"contain":[7],"multiple":[8,12],"interrelated":[9],"stencils,":[10],"have":[11],"input":[13],"grids,":[14],"and":[15,24,63],"use":[16],"higher":[17],"order":[18],"discretizations":[19],"with":[20],"high":[21],"arithmetic":[22],"intensity":[23],"complex":[25],"expression":[26],"structures.":[27],"In":[28],"combination,":[29],"these":[30],"properties":[31],"place":[32],"immense":[33],"demands":[34],"on":[35],"the":[36],"memory":[37],"hierarchy":[38],"that":[39],"limit":[40],"performance.":[41],"Blocking":[42],"techniques":[43],"like":[44],"tiling":[45],"are":[46],"used":[47],"to":[48],"exploit":[49],"reuse":[50],"caches.":[52],"Additional":[53],"fine-grain":[54],"data":[55],"blocking":[56],"can":[57],"also":[58],"reduce":[59],"TLB,":[60],"hardware":[61],"prefetch,":[62],"cache":[64],"pressure.":[65]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":7}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}
